CN103995895A - Image recognition method and device based on image - Google Patents

Abstract

The invention provides a picture-based picture recognition method and device, realizing a scheme of picture recognition through picture information. In this method, after receiving the picture input by the user, determine the subject word of the picture and the type corresponding to the content of the picture. When the subject word exists in the entry stored in the database corresponding to the type, the onebox form corresponding to the type is used. Display the content corresponding to the entry in the database. Since the subject word of the picture is determined in the embodiment of the present invention, and when the subject term exists in the entry stored in the database, the onebox form corresponding to the type of content of the picture is used to display the content corresponding to the entry in the database, thereby Realize the image recognition method based on image information, expand the scope of application of image recognition, and facilitate the use of users.

Description

Image-based image recognition method and device

technical field

The invention relates to the technical field of picture recognition, in particular to a picture-based picture recognition method and device.

Background technique

Image search is a service that provides users with relevant image data on the Internet through a search program. The purpose of image search is to enable users to find out the specific image they need.

In the prior art, when searching for a picture, the user inputs the description text of the picture in the search box, so that the server can search for the picture according to the description text of the picture.

Figure 1 is a schematic diagram of a search box provided by the prior art. When a user performs a picture search, after opening the browser, click on the type "picture" above the search box, enter the description text of the picture in the search box, such as "Andy Lau", and click on the left side After clicking the search button, the corresponding request is sent to the server, and the server returns the searched picture information to the user according to the received request.

The image search method in the prior art is only applicable to the search for the description text of the image. If a user knows a certain picture and needs to identify relevant information of the picture, such as attribute information of the original picture of the picture, the prior art does not provide a corresponding solution. Therefore, how to obtain relevant information of the picture based on known pictures has become an urgent problem to be solved.

Contents of the invention

In view of the above problems, the present invention is proposed to provide a picture-based image recognition method and device that overcomes the above problems or at least partially solves the above problems.

An embodiment of the present invention provides a picture-based picture recognition method, the method comprising:

Receive the picture input by the user, determine the subject word of the picture and the type corresponding to the content of the picture;

According to the database corresponding to the type, it is judged whether there is the subject word in the entry stored in the database;

When the subject word exists in the entry stored in the database, the content corresponding to the entry in the database is displayed in a onebox form corresponding to the type.

In order to further provide users with more accurate map recognition results, the method further includes:

According to the picture, search the picture database for the picture resource related information matching the picture;

Display the relevant information of the image resource in the form of onebox.

Preferably, the displaying the image resource-related information in the form of onebox includes:

identifying the size of each picture that is the same as the picture in the picture resource related information;

Determine the size range of the size of each picture, and display the pictures in each size range in the form of onebox.

In order to further provide users with more accurate image recognition results, the display of the image resource-related information in the form of onebox includes:

identifying the size of each picture that is the same as the picture in the picture resource related information;

Determine the size range of the size of each picture, and display the pictures in each size range in the form of onebox.

In order to further provide users with more accurate picture recognition results, the subject words for determining the pictures include:

According to the picture, search the picture database for the picture resource related information matching the picture;

According to the subject words corresponding to each picture in the picture resource related information, the subject words of the pictures are determined.

In order to further provide users with more accurate picture recognition results, the determination of the type corresponding to the content of the picture includes:

According to the picture, search the picture database for the picture resource related information matching the picture;

According to the type corresponding to each picture in the picture resource related information, determine the type corresponding to the content of the picture.

An embodiment of the present invention provides a picture-based map recognition device, which includes:

Receiving and determining module, used to receive the picture input by the user, determine the subject word of the picture and the type corresponding to the content of the picture;

Judging module, used for judging whether there is the subject word in the entry stored in the database according to the database corresponding to the type;

The display module is used to display the content corresponding to the entry in the database in a onebox form corresponding to the type when the judging module judges that the subject word exists in the entry stored in the database.

In order to further provide users with more accurate map recognition results, the device also includes:

The image database is used to save information about image resources;

The display module is further configured to search the picture database for relevant information about picture resources matching the picture according to the picture; and to display the relevant information about picture resources in the form of onebox.

In order to further provide users with more accurate image recognition results, the display module is specifically used to identify the size of each image in the image resource related information that is the same as the image; determine the size range of the size of each image, and The pictures of each size range are displayed in onebox form.

In order to further provide users with more accurate picture recognition results, the picture database is specifically used to store information about picture resources, and store each picture and its corresponding subject words;

The receiving and determining module is specifically configured to, according to the picture, search for picture resource related information matching the picture in the picture database; determine the picture's content according to the subject words corresponding to each picture in the picture resource related information Subject headings.

In order to further provide users with more accurate picture recognition results, the picture database is specifically used to store information related to picture resources, and store each picture and the type corresponding to its content;

The receiving and determining module is specifically configured to, according to the picture, search for picture resource related information matching the picture in the picture database; determine the content of the picture according to the type corresponding to each picture in the picture resource related information corresponding type.

In order to further provide users with more accurate map recognition results, the device further includes a knowledge database for storing each entry of the character type and the corresponding content of the entry.

Embodiments of the present invention provide a picture-based picture recognition method and device. In the method, after receiving a picture input by a user, the subject word of the picture and the type corresponding to the content of the picture are determined. When the type is stored in the database corresponding to When the subject word exists in the entry of , the content corresponding to the entry in the database is displayed in the form of onebox corresponding to this type. Since the subject word of the picture is determined in the embodiment of the present invention, and when the subject term exists in the entry stored in the database, the onebox form corresponding to the type of content of the picture is used to display the content corresponding to the entry in the database, thereby Realize the image recognition method based on image information, expand the scope of application of image recognition, and facilitate the use of users.

The above description is only an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention, it can be implemented according to the contents of the description, and in order to make the above and other purposes, features and advantages of the present invention more obvious and understandable , the specific embodiments of the present invention are enumerated below.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiment. The drawings are only for the purpose of illustrating a preferred embodiment and are not to be considered as limiting the invention. Also throughout the drawings, the same reference numerals are used to designate the same components. In the attached picture:

FIG. 1 is a schematic diagram of a search box provided by the prior art;

FIG. 2 is a schematic diagram of an image-based image recognition process provided by an embodiment of the present invention;

FIG. 3 is a schematic diagram of interface presentation when image-based image recognition is provided by an embodiment of the present invention;

Fig. 4 is the information presentation format of the drag and drop input box provided by the embodiment of the present invention;

FIG. 5 is a schematic diagram of a picture-based image recognition process provided by Embodiment 1 of the present invention;

FIG. 6 is a schematic structural diagram of an image-based image recognition device provided by an embodiment of the present invention.

Detailed ways

In order to realize the scheme of image recognition through image information, expand the scope of application of image recognition, and facilitate the use of users. Embodiments of the present invention provide a picture-based picture recognition method and device.

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided for more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

Embodiments of the present invention will be described below in conjunction with the accompanying drawings.

FIG. 2 is a schematic diagram of a picture-based image recognition process provided by an embodiment of the present invention, and the process includes the following steps:

S201: Receive a picture input by a user, and determine a subject word of the picture and a type corresponding to the content of the picture.

In the embodiment of the present invention, when the user performs picture recognition, the picture-based recognition device may be a search engine or other devices.

The client installed on the user's local device provides the user with a picture recognition box for inputting picture information, obtains a picture through the user's input in the picture recognition box, and sends the picture to the device. Wherein, the picture input by the user in the picture recognition box of the client can be a picture dragged from a local device based on a drag operation, or a picture dragged from the Internet based on a drag operation, or a picture drawn from a clipboard of a local device by a paste operation. Pictures etc. obtained from .

S202: According to the database corresponding to the type, judge whether the subject word exists in the entry stored in the database, if the judgment result is yes, go to step S203, otherwise, go to step S204.

In the embodiment of the present invention, for each type of picture content, a database corresponding to the type is saved, and the types of picture content corresponding to include: people, scenery, news, animals, vehicles and so on. Corresponding entry information corresponding to the type is stored in each database.

S203: Display the content corresponding to the entry in the database in a onebox form corresponding to the type.

Each type corresponds to a different onebox display form, and each onebox display form can be the same or different. When a user enters a search service requirement in the search box and is clearly recognized by the search engine, it will be allocated to a preset high-quality content resource or application provider for processing, so as to accurately and efficiently return application results that match the user's needs. In the search service, the application result that matches the user's needs on the search result page can be called onebox, or application box or application box. .

S204: Display information about image resources matching the image.

Since the subject word of the picture is determined in the embodiment of the present invention, and when the subject term exists in the entry stored in the database, the onebox form corresponding to the type of content of the picture is used to display the content corresponding to the entry in the database, thereby Realize the image recognition method based on image information, expand the scope of application of image recognition, and facilitate the use of users.

Fig. 3 is a schematic diagram of the interface presentation when image-based image recognition is provided by the embodiment of the present invention. In the embodiment of the present invention, when the client is opened, the client provides the user with a picture for image information input as shown in Fig. 3 An identification box, the user identification box is used to receive the picture input by the user. The picture input by the user may be a picture dragged into the picture recognition box based on a drag operation, or a picture pasted into the picture recognition box based on a paste operation.

When the client recognizes the user's drag operation in the set area, it uses the drag and drop input box to replace the image recognition box, and provides the drag and drop input box to the user, as shown in Figure 4, uses the drag and drop input box to replace the image recognition box The interface behind the box presents a schematic diagram. In order to facilitate the user's dragging and dropping, the client may display a prompt message "Please drag the picture here" in the dragging and dropping input box, prompting the user to place the picture to be dragged and dropped.

After the browser obtains the picture input by the user based on the picture recognition box or the drag-and-drop input box, it sends the picture input by the user to the picture recognition device. After the picture recognition device receives the picture input by the user, when determining the subject words of the picture, According to the picture, look up picture resource related information matching the picture in the picture database; according to the subject word corresponding to each picture in the picture resource related information, determine the subject word of the picture.

The image resource-related information includes images that are the same as or similar to the image input by the user, other images related to the image input by the user, and web pages including the above images. For example, if the picture input by the user is a picture of an apple, the relevant information of the picture resource includes the picture of an apple that is identical or similar to the picture of an apple input by the user, or other pictures of an apple, etc. Enter the page of the apple picture and so on.

Specifically, the image database may be stored in the image recognition device, or may exist independently of the image recognition device. A plurality of pictures are stored in the picture database, and a keyword corresponding to the picture is stored for each picture. According to the received picture input by the user, the server matches the picture with each picture in the picture database, determines the relevant information of the picture resource matching the picture, and according to the subject words corresponding to each picture in the relevant information of each picture resource, Determine the keywords of the picture entered by the user.

When matching, there may be multiple picture resource-related information in the picture database that matches the picture input by the user, and each picture in the picture resource-related information has a corresponding keyword. When determining the theme of the picture input by the user Words, determine the subject words corresponding to the pictures in the relevant information of each picture resource that match the picture input by the user, and count the number of occurrences of each subject word in the corresponding subject terms, and the subject that appears most often word as the subject word of the picture input by the user.

After the picture recognition device receives the picture input by the user, when determining the type corresponding to the content of the picture, according to the picture, search for the picture resource related information matching the picture in the picture database; according to the picture resource related information The type corresponding to each picture determines the type corresponding to the content of the picture.

The picture database stores a plurality of pictures, and stores a type corresponding to the content of the picture for each picture, for example, recording the picture as a person, landscape, news, animal, vehicle, and the like. When matching, there may be multiple image resource-related information in the image database that matches the image input by the user, and the image in each image resource-related information has its corresponding type. type, determine the type corresponding to the picture in the relevant information of each picture resource that matches the picture input by the user, count the number of occurrences of each type in the corresponding type, and use the type with the largest number of occurrences as the type The type corresponding to the content of the picture input by the user.

FIG. 5 is a schematic diagram of a picture-based image recognition process provided by Embodiment 1 of the present invention. The process includes the following steps:

S501: Receive the picture input by the user sent by the browser.

S502: Search the picture input by the user with each picture in the picture database, and determine information about picture resources matching the picture.

S503: According to the keyword corresponding to each picture and the type corresponding to each picture in the relevant information of each picture resource, determine the keyword of the picture input by the user and the type corresponding to the content of the picture.

S504: According to the database corresponding to the type, judge whether the subject word exists in the entry stored in the database, if the judgment result is yes, go to step S505, otherwise, go to step S506.

S505: Display the content corresponding to the entry in the database in a onebox form corresponding to the type.

S506: Display information about image resources matching the image.

In the embodiment of the present invention, there are multiple databases, and each database has multiple entries, and the entries in each database belong to one type, for example, the first database contains entries of multiple characters, and the second The database stores entries of multiple landscapes, the third database stores entries of multiple news items, the fourth database stores entries of various animals, the fifth database stores entries of various vehicles, and so on. Because each type of entry has its own characteristics, in order to provide users with detailed image recognition information, in the embodiment of the present invention, for each type, a corresponding onebox form display is provided, through which the corresponding onebox form display Show the results of the image recognition.

After determining the type corresponding to the content of the picture input by the user, according to the database corresponding to each type, it is judged whether there is a subject word of the picture input by the user in the entry stored in the database. When a subject term is used, the onebox format corresponding to this type is used to display the content corresponding to the term in the database.

Specifically, after the server receives the picture input by the user, it searches the picture database for related information about picture resources that match the picture according to the picture, and uses the keywords corresponding to each picture in the found relevant information of each picture resource For the type corresponding to the content of the picture, it is determined that the subject word of the picture is the female star "Fan XX", and the type corresponding to the content of the picture is "person".

The database corresponding to the character type is a knowledge database, for example, "360 Encyclopedia" can be used as a knowledge database. Find whether there is a subject word "Fan XX" in the entries saved in the knowledge database. So-and-so" entry corresponding content. The corresponding aggregated content is displayed in the onebox form.

The onebox display of character types includes "personal file", "brief introduction", "personal experience", "main works", "honors", "naked exposure", "character evaluation", "wax modeling", " Cannes Controversy," "Interviews," and more. In the "Personal Profile" displayed in the form of onebox, the person's profile is aggregated. Click "Personal Profile" to display the corresponding profile content. "Brief Introduction" aggregates the introduction information of the person. Click "Brief Introduction" Display the corresponding introductory content and so on. The above is only a brief description of the onebox display in the embodiment of the present invention, as long as the onebox display is used, the specific display form is not limited.

In order to improve the accuracy of the map recognition result, the image-based map recognition process provided in the embodiment of the present invention also includes:

According to the picture, search the picture database for the picture resource-related information matching the picture; and display the picture resource-related information in the form of onebox.

Specifically, displaying the image resource-related information in the form of onebox includes:

identifying the size of each picture that is the same as the picture in the picture resource related information;

Determine the size range of the size of each picture, and display the pictures in each size range in the form of onebox.

In the embodiment of the present invention, in order to display the picture information in the form of onebox, multiple sizes are set, and each size has its corresponding size range. The multiple sizes include, for example: all sizes, large sizes, medium sizes, small sizes, etc. , each size has its corresponding size range, for example, all sizes include the size of all the pictures found that are the same as the picture, the size range of the large size is 1024*1024～1600*1200, and the size range of the medium size is 500 *500～1024*1024, the size range of the small size is below the size of 500*500.

When recognizing pictures based on pictures, identify the size of each picture in the picture resource-related information based on the picture resource-related information found in the picture database that matches the picture input by the user. The size of each picture obtained, determine the size range of the size of each picture, aggregate the pictures of each size range, and display the pictures of each size range in the form of onebox.

In another embodiment, according to the received picture input by the user, search the picture database for information related to picture resources matching the picture, identify the same picture as the picture input by the user, and identify the size of each picture , after determining the size range of the size of each picture, the pictures of each size are displayed under "full size", "large size", "medium size" and "small size" in the form of onebox, and under "full size ", "Large Size", "Medium Size" and "Small Size" are aggregated with pictures of the same size as the input picture. In addition, in order to improve the accuracy of image recognition, the keyword of the picture input by the user is determined according to the keyword of the relevant information of each picture resource in the picture database, that is, the best guess "Fan Bingbing".

In addition, in order to improve the comprehensiveness of image recognition, in the embodiment of the present invention, the server also provides the user with information about other image resources that match the image, such as the image related to the image input by the user, the webpage containing the image, etc. information. The above figure is just a brief description of the embodiment of the present invention. According to the picture input by the user, the embodiment of the present invention can perform the picture recognition operation and display the corresponding picture recognition result to the user, among which the identified picture is the same as the picture input by the user. The picture is displayed in onebox form according to the size of the picture. When there is an entry identical to the subject word in the database, the content of the entry in the database is displayed in onebox form. In addition, the embodiment of the present invention also provides a Other related pictures related to the picture, and information such as the web page containing the picture.

Fig. 6 is a schematic structural diagram of an image-based map recognition device provided by an embodiment of the present invention, the device comprising:

Receiving and determining module 61, used to receive the picture input by the user, and determine the type corresponding to the subject words of the picture and the content of the picture;

Judgment module 62, is used for according to the database corresponding to this type, judges whether described subject word exists in the entry that this database preserves;

The display module 63 is configured to display the content corresponding to the entry in the database in a onebox form corresponding to the type when the judging module judges that the subject word exists in the entry stored in the database.

The device also includes:

The picture database 64 is used to save relevant information of picture resources;

The presentation module 63 is further configured to search the picture database for relevant information about picture resources matching the picture according to the picture; and to display the relevant information about picture resources in the form of onebox.

The display module 63 is specifically used to identify the size of each picture in the picture resource related information that is the same as the picture; determine the size range of the size of each picture, and display the pictures in each size range in the form of onebox.

The picture database 64 is specifically used for storing picture resource related information, and storing each picture and its corresponding subject words;

The receiving determination module 61 is specifically configured to search the picture database for related information about picture resources matching the picture according to the picture; and determine the picture according to the subject words corresponding to each picture in the picture resource related information subject words.

The picture database 64 is specifically used to store information about picture resources, and store the type corresponding to each picture and its content;

The receiving determination module 61 is specifically configured to search the picture database for related information about picture resources matching the picture according to the picture; The corresponding type of content.

The device also includes:

The knowledge database 65 is used to store each entry of the character type and the corresponding content of the entry.

Embodiments of the present invention provide a picture-based picture recognition method and device. In the method, after receiving a picture input by a user, the subject word of the picture and the type corresponding to the content of the picture are determined. When the type is stored in the database corresponding to When the subject word exists in the entry of , the content corresponding to the entry in the database is displayed in the form of onebox corresponding to this type. Since the subject word of the picture is determined in the embodiment of the present invention, and when the subject term exists in the entry stored in the database, the onebox form corresponding to the type of content of the picture is used to display the content corresponding to the entry in the database, thereby Realize the image recognition method based on image information, expand the scope of application of image recognition, and facilitate the use of users.

The algorithms and displays presented herein are not inherently related to any particular computer, virtual system, or other device. Various generic systems can also be used with the teachings based on this. The structure required to construct such a system is apparent from the above description. Furthermore, the present invention is not specific to any particular programming language. It should be understood that various programming languages can be used to implement the content of the present invention described herein, and the above description of specific languages is for disclosing the best mode of the present invention.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure the understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, in order to streamline this disclosure and to facilitate an understanding of one or more of the various inventive aspects, various features of the invention are sometimes grouped together in a single embodiment, figure, or its description. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the Detailed Description are hereby expressly incorporated into this Detailed Description, with each claim standing on its own as a separate embodiment of this invention.

Those skilled in the art can understand that the modules in the device in the embodiment can be adaptively changed and arranged in one or more devices different from the embodiment. Modules or units or components in the embodiments may be combined into one module or unit or component, and furthermore may be divided into a plurality of sub-modules or sub-units or sub-assemblies. All features disclosed in this specification (including accompanying claims, abstract and drawings) and any method or method so disclosed may be used in any combination, except that at least some of such features and/or processes or units are mutually exclusive. All processes or units of equipment are combined. Each feature disclosed in this specification (including accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will understand that although some embodiments described herein include some features included in other embodiments but not others, combinations of features from different embodiments are meant to be within the scope of the invention. and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art should understand that a microprocessor or a digital signal processor (DSP) may be used in practice to implement some or all functions of some or all components in the image recognition device according to the embodiment of the present invention. The present invention can also be implemented as an apparatus or an apparatus program (for example, a computer program and a computer program product) for performing a part or all of the methods described herein. Such a program for realizing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet site, or provided on a carrier signal, or provided in any other form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention can be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In a unit claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The use of the words first, second, and third, etc. does not indicate any order. These words can be interpreted as names.

Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these modifications and variations.

Claims (10)

1. the knowledge drawing method based on picture, is characterized in that, the method comprises:

Receive the picture of user's input, determine the descriptor of described picture and type corresponding to the content of this picture;

The database corresponding according to the type, judges in the entry that this database preserves whether have described descriptor;

While there is described descriptor in the entry that this database is preserved, adopt onebox form corresponding to the type to show content corresponding to this entry in described database.

2. the method for claim 1, is characterized in that, described method also comprises:

According to described picture, in picture database, search the picture resource relevant information of mating with described picture;

Adopt onebox form to show described picture resource relevant information.

3. the method as described in claim 1～2 any one, is characterized in that, described employing onebox form shows that described picture resource relevant information comprises:

The size of each picture identical with described picture in identification picture resource relevant information;

Determine the range of size at the size place of each picture, adopt onebox form to show in the picture of every kind of range of size.

4. the method as described in claim 1～3 any one, is characterized in that, the descriptor of described definite described picture comprises:

According to described picture, in picture database, search the picture resource relevant information of mating with described picture;

According to descriptor corresponding to each picture in described picture resource relevant information, determine the descriptor of this picture.

5. the method as described in claim 1～4 any one, is characterized in that, the type corresponding to content of described definite this picture comprises:

According to described picture, in picture database, search the picture resource relevant information of mating with described picture;

According to type corresponding to each picture in described picture resource relevant information, determine the type corresponding to content of this picture.

6. the method as described in claim 1～5 any one, is characterized in that, when the type corresponding to content of described picture is personage, database corresponding to the type is knowledge data base.

7. the knowledge map device based on picture, is characterized in that, described device comprises:

Receive determination module, for receiving the picture of user's input, determine the descriptor of described picture and type corresponding to the content of this picture;

Judge module, for the database corresponding according to the type, judges in the entry that this database preserves whether have described descriptor;

Display module, when judging that when judge module entry that this database is preserved exists described descriptor, adopts onebox form corresponding to the type to show content corresponding to this entry in described database.

8. device as claimed in claim 7, is characterized in that, described device also comprises:

Picture database, for preserving picture resource relevant information;

Described display module also, for according to described picture, is searched the picture resource relevant information of mating with described picture in picture database; Adopt onebox form to show described picture resource relevant information.

9. install as claimed in claim 7 or 8, it is characterized in that, described display module, specifically for the size of each picture identical with described picture in identification picture resource relevant information; Determine the range of size at the size place of each picture, adopt onebox form to show in the picture of every kind of range of size.

10. the device as described in claim 7～9 any one, is characterized in that, described picture database specifically for preserving picture resource relevant information, and is preserved each picture and corresponding descriptor thereof;

Described reception determination module specifically for according to described picture, is searched the picture resource relevant information of mating with described picture in picture database; According to descriptor corresponding to each picture in described picture resource relevant information, determine the descriptor of this picture.