CN116843942A - Tape information identification method, device, storage medium and electronic equipment - Google Patents
Tape information identification method, device, storage medium and electronic equipment Download PDFInfo
- Publication number
- CN116843942A CN116843942A CN202310576804.5A CN202310576804A CN116843942A CN 116843942 A CN116843942 A CN 116843942A CN 202310576804 A CN202310576804 A CN 202310576804A CN 116843942 A CN116843942 A CN 116843942A
- Authority
- CN
- China
- Prior art keywords
- tape
- target
- model
- image
- sub
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/413—Classification of content, e.g. text, photographs or tables
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Image Analysis (AREA)
Abstract
本申请公开了一种磁带信息识别方法、装置、存储介质以及电子设备。涉及人工智能领域。该方法包括：获取目标磁带的图像信息，其中，图像信息中包括磁带外观图片；通过文字识别模型获取磁带外观图片中的目标图像，并识别目标图像，得到磁带编号，其中，目标图像中包括磁带编号；通过图像识别模型识别磁带外观图片，得到目标磁带所属的目标机构和目标磁带的目标型号；将磁带编号、目标机构以及目标型号发送至目标磁带对应的用户端。通过本申请，解决了相关技术中通过人工识别的方式对磁带进行区分的方法效率低的问题。
This application discloses a magnetic tape information identification method, device, storage medium and electronic equipment. Involving the field of artificial intelligence. The method includes: obtaining image information of a target tape, wherein the image information includes a tape appearance picture; obtaining a target image in the tape appearance picture through a text recognition model, and identifying the target image to obtain a tape number, wherein the target image includes a tape number; identify the appearance picture of the tape through the image recognition model, and obtain the target mechanism to which the target tape belongs and the target model of the target tape; send the tape number, target mechanism, and target model to the client corresponding to the target tape. Through this application, the problem in the related art that the method of distinguishing tapes through manual identification is inefficient is solved.
Description
Technical Field
The application relates to the field of artificial intelligence, in particular to a tape information identification method, a tape information identification device, a storage medium and electronic equipment.
Background
The magnetic tape is the main backup medium of the data backup operation and maintenance system, and is usually stored in a magnetic tape library for the magnetic tape drive to capture and write data. However, as the volume of data center backups continues to rise, tape libraries have limited slots, which have not met tape storage requirements, and the tape is moved to tape libraries for storage. Meanwhile, in recent years, backup technology is continuously innovated, tape and tape library manufacturers are numerous, tape versions are continuously upgraded, tapes of different manufacturers and versions are different in performance configuration and the like, and compatibility to tape libraries is also different, so that accurate distinction and partition storage of the tapes are very important.
Because currently used tape backup software has no capability of identifying tape manufacturers and versions, the current method for identifying and distinguishing the tapes still relies on manual statistics to identify the versions, manufacturers and other information of each tape. However, because the manual statistics is easy to make mistakes, the security measures of the data center are strict, the magnetic tape belongs to important data assets, and the examination and approval flow of the magnetic tape warehouse is complicated, so that the efficiency of identifying and partitioning storage of the magnetic tape is lower.
Aiming at the problem that the method for distinguishing the magnetic tape by the manual identification method in the related art is low in efficiency, no effective solution is proposed at present.
Disclosure of Invention
The application provides a tape information identification method, a device, a storage medium and electronic equipment, which are used for solving the problem of low efficiency of a method for distinguishing a tape by a manual identification mode in the related art.
According to one aspect of the present application, a tape information identification method is provided. The method comprises the following steps: acquiring image information of a target tape, wherein the image information comprises a tape appearance picture; obtaining a target image in the tape appearance picture through a character recognition model, and recognizing the target image to obtain a tape number, wherein the target image comprises the tape number; identifying the appearance picture of the magnetic tape through an image identification model to obtain a target mechanism to which the target magnetic tape belongs and a target model of the target magnetic tape; and sending the tape number, the target mechanism and the target model to a user terminal corresponding to the target tape.
Optionally, acquiring the image information of the target tape includes: identifying whether the target tape is located at a preset position; under the condition that the target tape is positioned at a preset position, controlling a camera to shoot the target tape to obtain a current image of the target tape; identifying the current image and determining whether a tape number exists in the current image; under the condition that the tape number exists in the current image, determining the current image as image information; and sending out alarm information under the condition that no tape number exists in the current image, wherein the alarm information represents that the photographed interface of the target tape is abnormal.
Optionally, obtaining the target image in the tape appearance picture through the text recognition model, and recognizing the target image, and obtaining the tape number includes: determining the position information of the tape number in the image information; intercepting an image in which a tape number is positioned from image information according to the position information to obtain a target image; inputting the target image into a character recognition model to obtain a tape number, wherein the character recognition model is obtained through training of a plurality of sample number images and sample numbers in each sample number image.
Optionally, the image recognition model includes a first image recognition sub-model and a plurality of second image recognition sub-models, and recognizing the appearance picture of the magnetic tape through the image recognition model, and obtaining the target mechanism to which the target magnetic tape belongs and the target model of the target magnetic tape includes: inputting the tape appearance picture into a first image recognition sub-model to obtain a target mechanism to which the tape appearance picture belongs, wherein the first image recognition sub-model is obtained through training of a plurality of sample appearance pictures and sample mechanisms to which each sample appearance picture belongs; determining a target recognition sub-model associated with the target institution from the plurality of second image recognition sub-models; and inputting the tape appearance pictures into a target recognition sub-model to obtain a target model of the target tape, wherein the target recognition sub-model is obtained through training a plurality of sample appearance pictures and sample models of each sample appearance picture.
Optionally, the sub-model in the image recognition model is trained by: for each sub-model, acquiring a first sample data set associated with the sub-model, wherein the first sample data set is used for training the sub-model, and the sub-model comprises a first image recognition sub-model or a second image recognition sub-model; obtaining M preset functions, and sequentially taking each function as a function in the submodel to obtain M initial submodels; inputting the first sample data set into each initial sub-model to obtain M groups of recognition results; calculating the accuracy of each group of recognition results to obtain M accuracy rates, selecting the maximum value of the M accuracy rates to obtain the first maximum accuracy rate, and determining an initial sub-model corresponding to the first maximum accuracy rate as the sub-model applied to the image recognition model.
Optionally, before acquiring the M preset functions, the method further includes: for each preset function, acquiring a second sample data set associated with the preset function, wherein the second sample data set is used for calculating parameters of the preset function; setting a preset function as a function in the submodel to obtain a first preset submodel; randomly generating parameter values of N groups of preset functions to obtain N groups of parameter values, and configuring each group of parameter values in a first preset sub-model to obtain N second preset sub-models; sequentially inputting the second sample data into each second preset sub-model to obtain N groups of identification results; calculating the accuracy of each group of identification results to obtain N accuracy rates, selecting the accuracy rate which is larger than the preset accuracy rate from the N accuracy rates to obtain P accuracy rates, and obtaining parameter values corresponding to the P accuracy rates to obtain P groups of parameter values; the P groups of parameter values form a parameter value selection interval, and the parameter value with the maximum accuracy is determined in the parameter value selection interval through a genetic algorithm to obtain a target parameter value; and adding the target parameter value into a preset function.
Optionally, determining, by a genetic algorithm, a parameter value with the maximum accuracy in a parameter value selection interval, and obtaining the target parameter value includes: selecting any parameter value in the parameter value selecting interval to obtain an initial parameter value; configuring the initial parameter value in a first preset sub-model to obtain a candidate sub-model; inputting the second sample data into the candidate sub-model to obtain a candidate result, and calculating the accuracy according to the candidate result to obtain the candidate accuracy; carrying out iterative computation on the initial parameter value according to a genetic algorithm to obtain an updated initial parameter value, wherein the updated initial parameter value is positioned in a parameter value selection interval; repeatedly calculating candidate accuracy rates according to the updated initial parameter values until the genetic algorithm completes H iterative computations to obtain H candidate accuracy rates; and determining a parameter value corresponding to the maximum candidate accuracy rate in the H candidate accuracy rates as a target parameter value.
According to another aspect of the present application, there is provided a tape information identifying apparatus. The device comprises: a first acquisition unit configured to acquire image information of a target tape, where the image information includes a tape appearance picture; the second acquisition unit is used for acquiring a target image in the tape appearance picture through the character recognition model and recognizing the target image to obtain a tape number, wherein the target image comprises the tape number; the identification unit is used for identifying the appearance picture of the magnetic tape through the image identification model to obtain a target mechanism to which the target magnetic tape belongs and a target model of the target magnetic tape; and the sending unit is used for sending the tape number, the target mechanism and the target model to the user end corresponding to the target tape.
According to another aspect of the present application, there is also provided a computer storage medium for storing a program, wherein the program is operative to control an apparatus in which the computer storage medium is located to perform a tape information identification method.
According to another aspect of the present application, there is also provided an electronic device comprising one or more processors and a memory; the memory has stored therein computer readable instructions, and the processor is configured to execute the computer readable instructions, wherein the computer readable instructions when executed perform a tape information identification method.
According to the application, the following steps are adopted: acquiring image information of a target tape, wherein the image information comprises a tape appearance picture; obtaining a target image in the tape appearance picture through a character recognition model, and recognizing the target image to obtain a tape number, wherein the target image comprises the tape number; identifying the appearance picture of the magnetic tape through an image identification model to obtain a target mechanism to which the target magnetic tape belongs and a target model of the target magnetic tape; and sending the tape number, the target mechanism and the target model to a user terminal corresponding to the target tape. The problem of the method inefficiency of distinguishing the magnetic tape through the mode of manual identification in the related art is solved. The method comprises the steps of obtaining the image of the magnetic tape, identifying the number of the magnetic tape from the image, obtaining the number information, obtaining an image identification model through machine learning model training, and identifying the image of the magnetic tape, thereby obtaining the information which can be obtained by the appearance of the mechanism, the model and the like of the magnetic tape, further sending the obtained information to a user side, and further achieving the effect of accurately and efficiently identifying and distinguishing the magnetic tape.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application. In the drawings:
FIG. 1 is a flow chart of a method for identifying tape information provided in accordance with an embodiment of the present application;
FIG. 2 is a schematic illustration one of an alternative target tape provided in accordance with an embodiment of the present application;
FIG. 3 is a schematic diagram II of an alternative target tape provided in accordance with an embodiment of the present application;
FIG. 4 is a flow chart of an alternative magnetic tape information identification process provided in accordance with an embodiment of the present application;
FIG. 5 is a schematic diagram of a distribution of alternative accuracy values provided in accordance with an embodiment of the present application;
FIG. 6 is a schematic diagram of a tape information identification apparatus provided in accordance with an embodiment of the present application;
fig. 7 is a schematic diagram of an electronic device according to an embodiment of the present application.
Detailed Description
It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the application herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that, related information (including, but not limited to, user equipment information, user personal information, etc.) and data (including, but not limited to, data for presentation, analyzed data, etc.) related to the present disclosure are information and data authorized by a user or sufficiently authorized by each party. For example, an interface is provided between the system and the relevant user or institution, before acquiring the relevant information, the system needs to send an acquisition request to the user or institution through the interface, and acquire the relevant information after receiving the consent information fed back by the user or institution.
It should be noted that the tape information identification method, apparatus, storage medium and electronic device determined by the present disclosure may be used in the field of artificial intelligence, and may also be used in any field other than the field of artificial intelligence, and the application fields of the tape information identification method, apparatus, storage medium and electronic device determined by the present disclosure are not limited.
For convenience of description, the following will describe some terms or terminology involved in the embodiments of the present application:
magnetic tape: the data backup operation and maintenance system is a main backup medium which is usually stored in a tape library for a tape drive to capture and write data.
According to an embodiment of the present application, there is provided a tape information identification method.
FIG. 1 is a flow chart of a method for identifying tape information provided in accordance with an embodiment of the present application. As shown in fig. 1, the method comprises the steps of:
step S101, obtaining image information of a target tape, wherein the image information includes a tape appearance picture.
Specifically, after the production of the magnetic tape, information about the magnetic tape, such as the tape number, the tape name, and the like, is externally added. Therefore, when the magnetic tape is required to be identified and put in storage, the target magnetic tape can be shot first, so that the image information of the target magnetic tape is obtained, and the magnetic tape appearance image is obtained from the image information, so that the information of the magnetic tape is determined according to the magnetic tape appearance image, and the effect of identifying and classifying the magnetic tape is achieved.
Step S102, obtaining a target image in the tape appearance picture through the character recognition model, and recognizing the target image to obtain a tape number, wherein the target image comprises the tape number.
Specifically, because the number information of the magnetic tape is printed on the outer part of the magnetic tape, when the number information is acquired, a numbered image can be positioned in the magnetic tape image to obtain a target image, and the target image is identified in the magnetic tape appearance picture through the character identification model, wherein the target image comprises the magnetic tape number, and the target image can be identified to obtain the magnetic tape number.
Step S103, recognizing the appearance picture of the magnetic tape through the image recognition model to obtain a target mechanism to which the target magnetic tape belongs and a target model of the target magnetic tape.
Specifically, after the tape number is obtained, the production mechanism and model of the tape need to be determined, and since the mechanism and model do not make text labels on the tape, the production mechanism and model of the target tape need to be determined by the appearance of the tape. At this time, the tape appearance image can be recognized by the image recognition model, and the tape production mechanism and the type of the tape can be accurately determined from the appearance.
Step S104, the tape number, the target mechanism and the target model are sent to the user end corresponding to the target tape.
Specifically, after the tape number, the target mechanism and the target model are obtained, the information can be sent to the user side, and the tapes are classified and stored in the user side according to the identified information, so that the effect of accurately and efficiently identifying and distinguishing the tapes is achieved.
The tape information identification method provided by the embodiment of the application is characterized in that the image information of the target tape is obtained, wherein the image information comprises a tape appearance picture; obtaining a target image in the tape appearance picture through a character recognition model, and recognizing the target image to obtain a tape number, wherein the target image comprises the tape number; identifying the appearance picture of the magnetic tape through an image identification model to obtain a target mechanism to which the target magnetic tape belongs and a target model of the target magnetic tape; and sending the tape number, the target mechanism and the target model to a user terminal corresponding to the target tape. The problem of the method inefficiency of distinguishing the magnetic tape through the mode of manual identification in the related art is solved. The method comprises the steps of obtaining the image of the magnetic tape, identifying the number of the magnetic tape from the image, obtaining the number information, obtaining an image identification model through machine learning model training, and identifying the image of the magnetic tape, thereby obtaining the information which can be obtained by the appearance of the mechanism, the model and the like of the magnetic tape, further sending the obtained information to a user side, and further achieving the effect of accurately and efficiently identifying and distinguishing the magnetic tape.
Optionally, in the tape information identifying method provided by the embodiment of the present application, acquiring image information of the target tape includes: identifying whether the target tape is located at a preset position; under the condition that the target tape is positioned at a preset position, controlling a camera to shoot the target tape to obtain a current image of the target tape; identifying the current image and determining whether a tape number exists in the current image; under the condition that the tape number exists in the current image, determining the current image as image information; and sending out alarm information under the condition that no tape number exists in the current image, wherein the alarm information represents that the photographed interface of the target tape is abnormal.
Specifically, when acquiring the image information of the target tape, it is required to determine whether the target tape is located at a preset position, for example, a camera may be used to photograph the tape, however, in order to ensure the integrity and clarity of the photographed image, the target tape needs to be placed at the preset position, where the preset position may be a fixed position point or a preset area.
In the case of being located in the preset area, the characterization can shoot the target tape, at this time, the camera can be controlled to shoot the target tape to obtain the current image of the target tape, however, because the tape number may be located on any surface of the target tape, it is also required to determine whether the tape number exists in the current image, in the case of the existence of the tape number, the shot current image can be determined as the image information of the target tape, and in the case of the absence of the tape number, the staff is informed to adjust the tape by sending alarm information.
Fig. 2 is a schematic diagram of an alternative target tape according to an embodiment of the present application, as shown in fig. 2, first, it is determined whether the target tape is placed in a preset position, in the case of being placed in the preset position, a current image is acquired, and whether a tape number exists in the current image is determined, as shown in fig. 2, in the case of being present, the current image is determined as image information of the target tape, so that identification of tape information can be performed using the image information.
Optionally, in the tape information identification method provided by the embodiment of the present application, obtaining the target image in the tape appearance picture through the text identification model, and identifying the target image, the obtaining the tape number includes: determining the position information of the tape number in the image information; intercepting an image in which a tape number is positioned from image information according to the position information to obtain a target image; inputting the target image into a character recognition model to obtain a tape number, wherein the character recognition model is obtained through training of a plurality of sample number images and sample numbers in each sample number image.
Specifically, when the serial number is identified by the text recognition model, since the content in the tape appearance picture in the image information is more, for example, there may be the identification information of the tape, the production date of the tape, etc., the position of the tape number needs to be determined from the tape appearance picture, where the method for determining the position may be: the method comprises the steps of identifying font colors, identifying preset marks, such as 'numbering' patterns, and the like, intercepting a target image containing a tape number from a tape appearance picture according to position information after identification, and determining the tape number by directly scanning the characters in the target image, so that the effect of accurately acquiring the tape number is achieved.
For example, fig. 3 is a schematic diagram second of an alternative target tape according to an embodiment of the present application, as shown in fig. 3, there may be a lot of text content in the tape appearance picture, so when identifying the tape number, it is necessary to intercept the target picture including the tape number from the tape appearance picture, so that the efficiency and accuracy of identifying the tape number can be improved when identifying the tape number.
When the tape image in the tape appearance image is in an inclined state, the picture can be adaptively rotated by a corresponding angle, so that the text in the tape image can be recognized under the condition of front view.
Optionally, in the tape information identifying method provided by the embodiment of the present application, the image identifying model includes a first image identifying sub-model and a plurality of second image identifying sub-models, identifying the tape appearance picture through the image identifying model, and obtaining the target mechanism to which the target tape belongs and the target model of the target tape includes: inputting the tape appearance picture into a first image recognition sub-model to obtain a target mechanism to which the tape appearance picture belongs, wherein the first image recognition sub-model is obtained through training of a plurality of sample appearance pictures and sample mechanisms to which each sample appearance picture belongs; determining a target recognition sub-model associated with the target institution from the plurality of second image recognition sub-models; and inputting the tape appearance pictures into a target recognition sub-model to obtain a target model of the target tape, wherein the target recognition sub-model is obtained through training a plurality of sample appearance pictures and sample models of each sample appearance picture.
It should be noted that, each sub-model may be set as an SVM (Support Vector Machine ) model, and because the mechanisms to which the identifying target tape belongs and the training samples required for identifying the model of the target tape are different, in order to ensure accurate identification of the mechanisms and the model, different models may be used to identify the mechanisms and the model respectively, thereby improving the accuracy of identification.
Specifically, when determining the mechanism and model of the target tape, the target mechanism to which the tape appearance picture belongs can be obtained through the first image recognition sub-model, and under the condition that the target mechanism is determined, the target recognition sub-model corresponding to the target mechanism is determined, and the target model of the target tape is determined according to the target recognition sub-model, so that the mechanism and model of the target tape are respectively determined through the two models.
Fig. 4 is a flowchart of an alternative geomagnetic tape information identification flow provided according to an embodiment of the present application, as shown in fig. 4, where a model 1 is a first image identification sub-model, a model 2 and a model 3 are second image identification sub-models, a mechanism of a target magnetic tape is first determined to be a mechanism 1 or a mechanism 2 through the model 1, after the mechanism is determined, for example, the mechanism of the target model is the mechanism 1, and then the model 2 corresponding to the mechanism 1 is used to determine whether the model of the target magnetic tape is the model 1 or the model 2, so as to complete accurate identification of the mechanism and the model.
Optionally, in the tape information identifying method provided by the embodiment of the present application, the sub-model in the image identifying model is obtained by training in the following manner: for each sub-model, acquiring a first sample data set associated with the sub-model, wherein the first sample data set is used for training the sub-model, and the sub-model comprises a first image recognition sub-model or a second image recognition sub-model; obtaining M preset functions, and sequentially taking each function as a function in the submodel to obtain M initial submodels; inputting the first sample data set into each initial sub-model to obtain M groups of recognition results; calculating the accuracy of each group of recognition results to obtain M accuracy rates, selecting the maximum value of the M accuracy rates to obtain the first maximum accuracy rate, and determining an initial sub-model corresponding to the first maximum accuracy rate as the sub-model applied to the image recognition model.
The first image recognition sub-model and the second image recognition sub-model, and the distinction between the second image recognition sub-model and the second image recognition sub-model may be not only differences between training samples, but also differences between functions used in the models, that is, a function that maximizes the accuracy of each sub-model may be determined from among a plurality of functions according to the model recognition result, so as to improve the recognition accuracy of each sub-model, where tax may be a kernel function, for example, a linear kernel function, a polynomial kernel function, a gaussian kernel function, or the like.
Specifically, when selecting the function, sample information corresponding to the model may be determined first, for example, in the case of determining the first image recognition sub-model, the first sample data set may include images of tapes of a plurality of mechanisms and names of mechanisms corresponding to each image, after determining the first sample data set, a plurality of functions that may be currently used may be added one by one to the sub-model of the function to be determined, so as to obtain M initial sub-models, training the M initial sub-models through the first sample data set, testing the M initial sub-models after training through the test set, so as to obtain M mechanism recognition results, calculating a recognition accuracy of each model according to the recognition results, and determining the sub-model with the highest accuracy as the sub-model applied to the image recognition model.
Optionally, in the tape information identifying method provided by the embodiment of the present application, before obtaining M preset functions, the method further includes: for each preset function, acquiring a second sample data set associated with the preset function, wherein the second sample data set is used for calculating parameters of the preset function; setting a preset function as a function in the submodel to obtain a first preset submodel; randomly generating parameter values of N groups of preset functions to obtain N groups of parameter values, and configuring each group of parameter values in a first preset sub-model to obtain N second preset sub-models; sequentially inputting the second sample data into each second preset sub-model to obtain N groups of identification results; calculating the accuracy of each group of identification results to obtain N accuracy rates, selecting the accuracy rate which is larger than the preset accuracy rate from the N accuracy rates to obtain P accuracy rates, and obtaining parameter values corresponding to the P accuracy rates to obtain P groups of parameter values; the P groups of parameter values form a parameter value selection interval, and the parameter value with the maximum accuracy is determined in the parameter value selection interval through a genetic algorithm to obtain a target parameter value; and adding the target parameter value into a preset function.
Specifically, before obtaining M preset functions, determining that the parameters in each function are optimal parameters, selecting the functions, when determining the parameters of the functions, randomly generating the parameter values of N groups of preset functions, configuring the N groups of parameter values in a sub-model containing the preset functions, and obtaining N second preset sub-models, so that the functions are tested in the sub-models, and further determining the optimal values of the random parameters.
Training each second preset sub-model through the second sample data set, testing each trained second preset sub-model through the test set, and obtaining N groups of recognition results, so that the accuracy of each second preset sub-model can be determined through the recognition results, the parameter with the highest accuracy is determined as the optimal parameter of the preset function, and the parameter configuration in the preset function is completed.
Further, after obtaining N groups of recognition results and determining the accuracy of each group of recognition results, selecting an accuracy greater than a preset accuracy from the N accuracy to obtain P accuracy, obtaining parameter values corresponding to the P accuracy to obtain P groups of parameter values, and forming a parameter value selection interval by the P groups of parameter values, where fig. 5 is a schematic diagram of distribution of optional accuracy values provided according to an embodiment of the present application, and as shown in fig. 5, the preset accuracy may be 0.75, points in interval a meet the requirement, and interval a is a parameter value selection interval, where penalty factors and kernel parameters are parameter values in functions, and penalty factors represent fitness of kernel function classification.
After the parameter value selection interval is determined, the parameter value with the maximum accuracy rate can be determined in the parameter value selection interval through a genetic algorithm, and the parameter value is determined to be the optimal parameter value, so that the optimal parameter value is determined step by step, and the calculation amount for acquiring the parameter value is reduced. Optionally, in the tape information identification method provided by the embodiment of the present application, determining, by a genetic algorithm, a parameter value with the maximum accuracy in a parameter value selection interval, and obtaining the target parameter value includes: selecting any parameter value in the parameter value selecting interval to obtain an initial parameter value; configuring the initial parameter value in a first preset sub-model to obtain a candidate sub-model; inputting the second sample data into the candidate sub-model to obtain a candidate result, and calculating the accuracy according to the candidate result to obtain the candidate accuracy; carrying out iterative computation on the initial parameter value according to a genetic algorithm to obtain an updated initial parameter value, wherein the updated initial parameter value is positioned in a parameter value selection interval; repeatedly calculating candidate accuracy rates according to the updated initial parameter values until the genetic algorithm completes H iterative computations to obtain H candidate accuracy rates; and determining a parameter value corresponding to the maximum candidate accuracy rate in the H candidate accuracy rates as a target parameter value.
Specifically, an arbitrary parameter value can be selected in a parameter value selection interval to obtain an initial parameter value, the initial parameter value is configured in the first preset submodel to obtain a candidate submodel, the candidate submodel is trained to obtain a training result and an identification accuracy, the initial parameter value is subjected to iterative computation according to a genetic algorithm to obtain an updated initial parameter value, the steps are repeated to obtain a plurality of identification accuracy rates, after the iteration of the preset times is completed, the maximum accuracy rate is obtained in the plurality of identification accuracy rates, and parameters corresponding to the accuracy rate are determined as parameters in the preset function, so that the parameter configuration of the function in the first preset submodel is completed.
The optimal parameters of each function which can be set in any sub-model can be determined through the flow, so that a plurality of optimal functions are obtained, and the function which is most matched with the sub-model is determined in the optimal functions, so that different functions can be added for the sub-model according to different samples and application scenes, and a plurality of image recognition sub-models are obtained.
It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.
The embodiment of the application also provides a tape information identification device, and the tape information identification device can be used for executing the tape information identification method provided by the embodiment of the application. The following describes a tape information identifying apparatus provided in an embodiment of the present application.
Fig. 6 is a schematic diagram of a tape information identification apparatus provided according to an embodiment of the present application. As shown in fig. 6, the apparatus includes: a first acquisition unit 61, a second acquisition unit 62, an identification unit 63, a transmission unit 64.
A first obtaining unit 61, configured to obtain image information of a target tape, where the image information includes a tape appearance picture.
The second obtaining unit 62 is configured to obtain, through the text recognition model, a target image in the tape appearance picture, and identify the target image, to obtain a tape number, where the target image includes the tape number.
And the identifying unit 63 is used for identifying the appearance picture of the magnetic tape through the image identifying model to obtain a target mechanism to which the target magnetic tape belongs and a target model of the target magnetic tape.
And the sending unit 64 is configured to send the tape number, the target mechanism and the target model to the user end corresponding to the target tape.
The tape information identification device provided by the embodiment of the application acquires the image information of the target tape through the first acquisition unit 61, wherein the image information comprises a tape appearance picture; the second obtaining unit 62 obtains a target image in the tape appearance picture through the character recognition model, and recognizes the target image to obtain a tape number, wherein the target image comprises the tape number; the identifying unit 63 identifies the tape appearance picture through the image identifying model to obtain a target mechanism to which the target tape belongs and a target model of the target tape; the transmitting unit 64 transmits the tape number, the target organization and the target model to the user end corresponding to the target tape, which solves the problem of inefficiency of the method for distinguishing the tapes by means of manual identification in the related art. The method comprises the steps of obtaining the image of the magnetic tape, identifying the number of the magnetic tape from the image, obtaining the number information, obtaining an image identification model through machine learning model training, and identifying the image of the magnetic tape, thereby obtaining the information which can be obtained by the appearance of the mechanism, the model and the like of the magnetic tape, further sending the obtained information to a user side, and further achieving the effect of accurately and efficiently identifying and distinguishing the magnetic tape.
Alternatively, in the tape information identifying apparatus provided in the embodiment of the present application, the first obtaining unit 61 includes: the first identification module is used for identifying whether the target tape is positioned at a preset position or not; the control module is used for controlling the camera to shoot the target tape under the condition that the target tape is positioned at a preset position so as to obtain the current image of the target tape; the second identification module is used for identifying the current image and determining whether a tape number exists in the current image; the first determining module is used for determining the current image as image information under the condition that the tape number exists in the current image; and the alarm module is used for sending alarm information under the condition that the tape number does not exist in the current image, wherein the alarm information represents that the shot interface of the target tape is abnormal.
Alternatively, in the tape information identifying apparatus provided in the embodiment of the present application, the second acquisition unit 62 includes: a second determining module for determining the position information of the tape number in the image information; the intercepting module is used for intercepting the image where the tape number is positioned from the image information according to the position information to obtain a target image; the first input module is used for inputting the target image into a character recognition model to obtain the tape number, wherein the character recognition model is obtained through training of a plurality of sample number images and sample numbers in each sample number image.
Optionally, in the tape information identifying apparatus provided in the embodiment of the present application, the image identifying model includes a first image identifying sub-model and a plurality of second image identifying sub-models, and the identifying unit 63 includes: the second input module is used for inputting the tape appearance picture into the first image recognition sub-model to obtain a target mechanism to which the tape appearance picture belongs, wherein the first image recognition sub-model is obtained through training of a plurality of sample appearance pictures and sample mechanisms to which each sample appearance picture belongs; a third determining module, configured to determine a target recognition sub-model associated with the target institution from the plurality of second image recognition sub-models; the third input module is used for inputting the tape appearance pictures into the target recognition sub-model to obtain the target model of the target tape, wherein the target recognition sub-model is obtained through training of a plurality of sample appearance pictures and sample models of each sample appearance picture.
Optionally, in the tape information identifying apparatus provided by the embodiment of the present application, the sub-model in the image identifying model is obtained by training in the following manner: a third obtaining unit, configured to obtain, for each sub-model, a first sample data set associated with the sub-model, where the first sample data set is used to train the sub-model, and the sub-model includes a first image recognition sub-model or a second image recognition sub-model; a fourth obtaining unit, configured to obtain M preset functions, and sequentially use each function as a function in the submodel to obtain M initial submodels; the first input unit is used for inputting the first sample data set into each initial sub-model to obtain M groups of recognition results; the first calculation unit is used for calculating the accuracy of each group of recognition results to obtain M accuracy rates, selecting the maximum value of the M accuracy rates to obtain the first maximum accuracy rate, and determining an initial submodel corresponding to the first maximum accuracy rate as a submodel applied to the image recognition model.
Optionally, in the tape information identifying apparatus provided in the embodiment of the present application, before acquiring M preset functions, the apparatus further includes: a fifth obtaining unit, configured to obtain, for each preset function, a second sample data set associated with the preset function, where the second sample data set is used to calculate parameters of the preset function; the setting unit is used for setting a preset function as a function in the submodel to obtain a first preset submodel; the generating unit is used for randomly generating parameter values of N groups of preset functions to obtain N groups of parameter values, and configuring each group of parameter values in the first preset sub-model to obtain N second preset sub-models; the second input unit is used for inputting second sample data into each second preset sub-model in sequence to obtain N groups of recognition results; the second calculation unit is used for calculating the accuracy of each group of identification results to obtain N accuracy rates, selecting the accuracy rate which is larger than the preset accuracy rate from the N accuracy rates to obtain P accuracy rates, and obtaining parameter values corresponding to the P accuracy rates to obtain P groups of parameter values; the determining unit is used for forming a parameter value selecting interval by the P groups of parameter values, determining the parameter value with the maximum accuracy in the parameter value selecting interval through a genetic algorithm, and obtaining a target parameter value; and the adding unit is used for adding the target parameter value into the preset function.
Optionally, in the tape information identifying apparatus provided in the embodiment of the present application, the determining unit includes: the selection module is used for selecting any parameter value in the parameter value selection interval to obtain an initial parameter value; the configuration module is used for configuring the initial parameter value in a first preset sub-model to obtain a candidate sub-model; the fourth input module is used for inputting the second sample data into the candidate sub-model to obtain a candidate result, and calculating the accuracy according to the candidate result to obtain a candidate accuracy; the first calculation module is used for carrying out iterative calculation on the initial parameter value according to a genetic algorithm to obtain an updated initial parameter value, wherein the updated initial parameter value is positioned in a parameter value selection interval; the second calculation module is used for repeatedly calculating candidate accuracy rates according to the updated initial parameter values until the genetic algorithm completes H times of iterative computations to obtain H candidate accuracy rates; and the fourth determining module is used for determining a parameter value corresponding to the maximum candidate accuracy rate in the H candidate accuracy rates as a target parameter value.
The tape information identifying apparatus includes a processor and a memory, and the first acquiring unit 61, the second acquiring unit 62, the identifying unit 63, the transmitting unit 64, and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize the corresponding functions.
The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel can be provided with one or more than one kernel, and the problem of low efficiency of the method for distinguishing the magnetic tape by a manual identification mode in the related technology is solved by adjusting kernel parameters.
The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.
Embodiments of the present application provide a computer-readable storage medium having a program stored thereon, which when executed by a processor, implements the tape information identification method.
The embodiment of the application provides a processor which is used for running a program, wherein the program runs to execute the tape information identification method.
Fig. 7 is a schematic diagram of an electronic device according to an embodiment of the present application, and as shown in fig. 7, an electronic device 70 includes a processor, a memory, and a program stored in the memory and executable on the processor, where the processor implements steps in the above-mentioned tape information identification method when executing the program. The device herein may be a server, PC, PAD, cell phone, etc.
The present application also provides a computer program product adapted to perform a program initialized with the steps of the above-described tape information identification method when executed on a data processing device.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (10)
1. A method of identifying tape information, comprising:
acquiring image information of a target tape, wherein the image information comprises a tape appearance picture;
acquiring a target image in the tape appearance picture through a character recognition model, and recognizing the target image to obtain a tape number, wherein the target image comprises the tape number;
identifying the appearance picture of the magnetic tape through an image identification model to obtain a target mechanism to which the target magnetic tape belongs and a target model of the target magnetic tape;
and sending the tape number, the target mechanism and the target model to a user side corresponding to the target tape.
2. The method of claim 1, wherein acquiring image information of the target tape comprises:
identifying whether the target tape is located at a preset position;
Controlling a camera to shoot the target tape under the condition that the target tape is positioned at the preset position, so as to obtain the current image of the target tape;
identifying the current image and determining whether the tape number exists in the current image;
determining the current image as the image information under the condition that the tape number exists in the current image;
and sending out alarm information under the condition that the tape number does not exist in the current image, wherein the alarm information represents that the shot interface of the target tape is abnormal.
3. The method of claim 1, wherein obtaining a target image in the tape appearance picture by a text recognition model and recognizing the target image, the obtaining a tape number comprising:
determining position information of the tape number in the image information;
intercepting an image in which the tape number is positioned from the image information according to the position information to obtain the target image;
and inputting the target image into the character recognition model to obtain the tape number, wherein the character recognition model is obtained through training a plurality of sample number images and sample numbers in each sample number image.
4. The method of claim 1, wherein the image recognition model includes a first image recognition sub-model and a plurality of second image recognition sub-models, and wherein recognizing the tape appearance picture by the image recognition model to obtain the target mechanism to which the target tape belongs and the target model of the target tape includes:
inputting the tape appearance picture into the first image recognition sub-model to obtain a target mechanism to which the tape appearance picture belongs, wherein the first image recognition sub-model is obtained through training of a plurality of sample appearance pictures and sample mechanisms to which each sample appearance picture belongs;
determining a target recognition sub-model associated with the target institution from the plurality of second image recognition sub-models;
and inputting the tape appearance pictures into the target recognition sub-model to obtain the target model of the target tape, wherein the target recognition sub-model is obtained through training a plurality of sample appearance pictures and sample models of each sample appearance picture.
5. The method of claim 4, wherein the sub-models in the image recognition model are trained by:
For each sub-model, acquiring a first sample data set associated with the sub-model, wherein the first sample data set is used for training the sub-model, and the sub-model comprises the first image recognition sub-model or the second image recognition sub-model;
obtaining M preset functions, and sequentially taking each function as a function in the submodel to obtain M initial submodels;
inputting the first sample data set into each initial sub-model to obtain M groups of recognition results;
calculating the accuracy of each group of recognition results to obtain M accuracy rates, selecting the maximum value of the M accuracy rates to obtain a first maximum accuracy rate, and determining an initial submodel corresponding to the first maximum accuracy rate as a submodel applied to the image recognition model.
6. The method of claim 5, wherein prior to obtaining the M preset functions, the method further comprises:
for each preset function, acquiring a second sample data set associated with the preset function, wherein the second sample data set is used for calculating parameters of the preset function;
setting the preset function as a function in the submodel to obtain a first preset submodel;
Randomly generating parameter values of N groups of preset functions to obtain N groups of parameter values, and configuring each group of parameter values in the first preset sub-model to obtain N second preset sub-models;
inputting the second sample data into each second preset sub-model in sequence to obtain N groups of identification results;
calculating the accuracy of each group of identification results to obtain N accuracy rates, selecting the accuracy rate which is larger than the preset accuracy rate from the N accuracy rates to obtain P accuracy rates, and obtaining parameter values corresponding to the P accuracy rates to obtain P groups of parameter values;
constructing a parameter value selection interval by the P groups of parameter values, and determining the parameter value with the maximum accuracy in the parameter value selection interval by a genetic algorithm to obtain a target parameter value;
and adding the target parameter value to the preset function.
7. The method of claim 6, wherein determining the parameter value with the greatest accuracy in the parameter value selection interval by a genetic algorithm, the obtaining a target parameter value comprises:
selecting any parameter value in the parameter value selecting interval to obtain an initial parameter value;
configuring the initial parameter value in the first preset sub-model to obtain a candidate sub-model;
Inputting the second sample data into the candidate sub-model to obtain a candidate result, and calculating the accuracy according to the candidate result to obtain a candidate accuracy;
performing iterative computation on the initial parameter value according to the genetic algorithm to obtain an updated initial parameter value, wherein the updated initial parameter value is positioned in the parameter value selection interval;
repeatedly calculating candidate accuracy rates according to the updated initial parameter values until the genetic algorithm completes H iterative computations to obtain H candidate accuracy rates;
and determining a parameter value corresponding to the maximum candidate accuracy rate in the H candidate accuracy rates as the target parameter value.
8. A tape information identification apparatus, comprising:
a first acquisition unit, configured to acquire image information of a target tape, where the image information includes a tape appearance picture;
the second acquisition unit is used for acquiring a target image in the tape appearance picture through a character recognition model and recognizing the target image to obtain a tape number, wherein the target image comprises the tape number;
the identification unit is used for identifying the appearance picture of the magnetic tape through an image identification model to obtain a target mechanism to which the target magnetic tape belongs and a target model of the target magnetic tape;
And the sending unit is used for sending the tape number, the target mechanism and the target model to a user side corresponding to the target tape.
9. A computer storage medium for storing a program, wherein the program when run controls a device in which the computer storage medium is located to perform the tape information identification method according to any one of claims 1 to 7.
10. An electronic device comprising one or more processors and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the tape information identification method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310576804.5A CN116843942B (en) | 2023-05-19 | 2023-05-19 | Tape information identification method, device, storage medium and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310576804.5A CN116843942B (en) | 2023-05-19 | 2023-05-19 | Tape information identification method, device, storage medium and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116843942A true CN116843942A (en) | 2023-10-03 |
| CN116843942B CN116843942B (en) | 2025-12-16 |
Family
ID=88171403
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310576804.5A Active CN116843942B (en) | 2023-05-19 | 2023-05-19 | Tape information identification method, device, storage medium and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116843942B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1205105A (en) * | 1996-08-23 | 1999-01-13 | 索尼公司 | Apparatus for management of information of program recorded on video tape, method for management of program recorded on video tape, recorder/reproducer and recording/reproducing method |
| CN1228225A (en) * | 1997-06-09 | 1999-09-08 | 松下电器产业株式会社 | Video signal recording and reproducing device |
| CN1964257A (en) * | 2005-11-08 | 2007-05-16 | 国际商业机器公司 | Method and system for generating ciphertext and message authentication codes utilizing shared hardware |
| CN104246881A (en) * | 2012-04-27 | 2014-12-24 | 国际商业机器公司 | Method and apparatus for operating a tape storage device |
| CN113800253A (en) * | 2021-09-30 | 2021-12-17 | 中国工商银行股份有限公司 | Conveying devices and conveying systems |
| CN114862859A (en) * | 2022-07-08 | 2022-08-05 | 苏州景昱医疗器械有限公司 | Image recognition method, device, system and computer readable storage medium |
| CN115063798A (en) * | 2022-07-01 | 2022-09-16 | 中国工商银行股份有限公司 | OCR recognition method and device, processor and electronic equipment |
-
2023
- 2023-05-19 CN CN202310576804.5A patent/CN116843942B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1205105A (en) * | 1996-08-23 | 1999-01-13 | 索尼公司 | Apparatus for management of information of program recorded on video tape, method for management of program recorded on video tape, recorder/reproducer and recording/reproducing method |
| CN1228225A (en) * | 1997-06-09 | 1999-09-08 | 松下电器产业株式会社 | Video signal recording and reproducing device |
| CN1964257A (en) * | 2005-11-08 | 2007-05-16 | 国际商业机器公司 | Method and system for generating ciphertext and message authentication codes utilizing shared hardware |
| CN104246881A (en) * | 2012-04-27 | 2014-12-24 | 国际商业机器公司 | Method and apparatus for operating a tape storage device |
| CN113800253A (en) * | 2021-09-30 | 2021-12-17 | 中国工商银行股份有限公司 | Conveying devices and conveying systems |
| CN115063798A (en) * | 2022-07-01 | 2022-09-16 | 中国工商银行股份有限公司 | OCR recognition method and device, processor and electronic equipment |
| CN114862859A (en) * | 2022-07-08 | 2022-08-05 | 苏州景昱医疗器械有限公司 | Image recognition method, device, system and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116843942B (en) | 2025-12-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11935298B2 (en) | System and method for predicting formation in sports | |
| CN111914908B (en) | Image recognition model training method, image recognition method and related equipment | |
| CN109447156B (en) | Method and apparatus for generating a model | |
| CN109117848A (en) | A kind of line of text character identifying method, device, medium and electronic equipment | |
| US9811760B2 (en) | Online per-feature descriptor customization | |
| CN111686450B (en) | Game play generation and running method and device, electronic equipment and storage medium | |
| CN108596180A (en) | Parameter identification, the training method of parameter identification model and device in image | |
| CN109872026A (en) | Evaluation result generation method, device, equipment and computer readable storage medium | |
| Suárez et al. | BELID: Boosted efficient local image descriptor | |
| CN110427998A (en) | Model training, object detection method and device, electronic equipment, storage medium | |
| CN113255819A (en) | Method and apparatus for identifying information | |
| CN111476271B (en) | Icon identification method, device, system, computer equipment and storage medium | |
| KR102413588B1 (en) | Object recognition model recommendation method, system and computer program according to training data | |
| CN115063798A (en) | OCR recognition method and device, processor and electronic equipment | |
| CN116843942B (en) | Tape information identification method, device, storage medium and electronic equipment | |
| CN113486204A (en) | Picture marking method, device, medium and equipment | |
| CN113190444A (en) | Test method, test device and storage medium | |
| CN112100075A (en) | User interface playback method, device, equipment and storage medium | |
| CN114627542B (en) | Method, device, storage medium and electronic device for determining eye movement position | |
| CN111160429B (en) | Training method of image detection model, image detection method, device and equipment | |
| CN116977791A (en) | Multi-task model training method, task prediction method, device, computer equipment and media | |
| CN116862695A (en) | Data accounting management system, method, storage medium, and electronic device | |
| CN112149701B (en) | Image recognition method, virtual sample data generation method and storage medium | |
| CN114445340B (en) | Money bundle detection method, money bundle warehouse-in method and related devices | |
| CN114120005B (en) | Image processing method, neural network model training method, device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |