WO2018098697A1 - Image feature repeatability measurement method and device - Google Patents

Abstract

An image feature repeatability measurement method and device. The method comprises: obtaining multiple images, and preprocessing the multiple images; obtaining a region satisfying a preset condition in each of the preprocessed multiple images, and marking the region in each image; performing standardization processing on each image, so that a grayscale value of each pixel in each image falls within a preset grayscale value arrange; extracting an image feature of the marked region, and obtaining multiple factor values related to the image feature; computing an overall consistency correlation coefficient (OCCC) value of the image feature according to the multiple factor values; and if the OCCC value is greater than a preset threshold, determining that the image has repeatability. The problem in the prior art of low accuracy in the assessment of the repeatability of an image feature performed by generally using a single factor value only is resolved.

Description

Method and device for measuring repeatability of image features Technical field

The invention belongs to the technical field of medical imaging, and in particular relates to a method and a device for measuring repeatability of image features.

Background technique

Image omics is a rapidly emerging field that can extract a large number of high-dimensional quantitative image features from standard medical images with high-throughput, and build models by combining reproducible image features with clinicopathological features. Diagnosis, prediction and preoperative decision-making have important clinical value and application prospects. However, in the prior art, image feature repeatability is usually evaluated using only a single factor value, and the accuracy is relatively low.

Therefore, it is necessary to propose a new technical solution to solve the above technical problems.

Summary of the invention

In view of the above, the embodiments of the present invention provide a method and a device for measuring reproducibility of image features, which are to solve the problem that the image feature repeatability is generally evaluated by using only a single factor value in the prior art, and the accuracy is relatively low.

A first aspect of the embodiments of the present invention provides a method for measuring reproducibility of image features, the method comprising:

Acquiring multiple images and pre-processing the plurality of images;

Obtaining an area of each of the plurality of images after the pre-processing that meets a preset condition, and marking the area in each of the images;

Normalizing each image so that the gray value of each pixel in each image is within a preset gray value region;

Extracting image features of the marked area and acquiring a plurality of factor values related to the image features;

Calculating an overall consistency correlation coefficient OCCC value of the image feature according to the plurality of factor values;

If the OCCC value is greater than a predetermined threshold, then the image feature is determined to be repeatable.

A second aspect of the embodiments of the present invention provides a reproducibility measuring device for image features, the device comprising:

An image acquisition module, configured to acquire a plurality of images and perform preprocessing on the plurality of images;

a region obtaining module, configured to acquire an area of each of the plurality of images after the pre-processing that meets a preset condition, and mark the area in each of the images;

a normalization processing module, configured to perform normalization processing on each of the images such that a gray value of each pixel in each image is located in a preset gray value region;

An evaluation module, configured to extract image features of the marked area, and obtain a plurality of factor values related to the image features;

a calculation module, configured to calculate an overall consistency correlation coefficient OCCC value of the image feature according to the plurality of factor values;

And a determining module, configured to determine that the image feature is reproducible if the OCCC value is greater than a predetermined threshold.

Compared with the prior art, the embodiment of the present invention has the beneficial effects that: in the embodiment of the present invention, a plurality of images are acquired, and the plurality of images are preprocessed, and each pre-processed image is obtained to satisfy a preset condition. Area, and mark the area, normalize each image so that the gray value of each pixel in each image is within the preset gray value area, and extract the image features of the marked area, and obtain more A factor value associated with the image feature, the overall consistency correlation coefficient OCCC value of the image feature is calculated according to the plurality of factor values, and the image feature is determined to be repeatable when the OCCC value is greater than a predetermined threshold. The embodiment of the present invention evaluates the repeatability of image features by using OCCC values, thereby considering a plurality of factor values related to image features (for example, pixel size during image processing, gray level of pixels, quantization algorithm, etc.) on image features. An assessment is made to improve the accuracy of the assessment.

DRAWINGS

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the embodiments or the description of the prior art will be briefly described below. It is obvious that the drawings in the following description are only the present invention. For some embodiments, other drawings may be obtained from those of ordinary skill in the art in light of the inventive workability.

1 is a flowchart of an implementation of a method for measuring repeatability of image features according to Embodiment 1 of the present invention;

2 is an exemplary diagram of repeatability evaluation of multiple texture features;

3 is a schematic diagram of the composition of a repeatability measuring device for image features provided by Embodiment 2 of the present invention;

4 is a schematic diagram showing the composition of a repeatability measuring device for image features according to Embodiment 3 of the present invention.

detailed description

The present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It is understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

Embodiment 1:

FIG. 1 is a flowchart showing an implementation process of a repeatability measurement method for image features according to Embodiment 1 of the present invention. The implementation process is as follows:

Step S101: Acquire a plurality of images, and preprocess the plurality of images.

In the embodiment of the present invention, the plurality of images may be from Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Positron Emission Tomography (PET), etc. Medical image of a set of sample objects. Medical images indicate the pathological or anatomical information of various tissues through different levels of gray scale display, and analyzing the gray scale difference of the diseased tissue has a guiding effect on the research. Grayscale information usually There are two types of differences: differences caused by imaging factors (such as parameter settings) and gray-scale changes in the medical object itself. The gray-scale change of the medical object itself has a certain medical significance. It is the research value. The gray-scale change caused by the object itself can realize the segmentation of different tissues and different lesions, and the extraction of quantitative image features can A change is quantified to get more research-rich data. The influence of imaging factors (such as different parameter settings) will have certain effects on the pixels in the image. For example, image spatial resolution and image noise are affected by the scanning parameters. The influence of image quality will inevitably affect the subsequent processing and research. In order to study the influence of these parameters such as tube voltage, tube current, layer thickness and layer spacing on the image features, these parameters can be compared and analyzed, and different parameter combinations can be set. The experiment was repeated, and then the experimental results were used to analyze the influence of each parameter on the repeatability of image features. Furthermore, the image features with good robustness to these parameters are found for subsequent research.

Optionally, the preprocessing the multiple images includes:

Performing image registration on the plurality of images to obtain a feature point matching relationship between the plurality of images;

Smoothing the plurality of images.

In the embodiment of the present invention, image registration refers to a process of matching and superimposing two or more images acquired at different times, different sensors (imaging devices) or under different conditions (such as whether or not a contrast enhancer is injected). In order to obtain the feature point matching relationship between multiple images, the essence is that the physical points representing the same position in different images are in one-to-one correspondence. According to the interactive classification, it can be divided into the following three categories: First, manual registration, which is performed by people with experience. After inputting the computer, only the display work is performed, and no complicated registration algorithm is needed. Second, semi-automatic registration is A certain initial condition is given manually, such as manually delineating the contour and controlling the optimization parameters. The third is automatic registration, which is automatically completed by the computer, and the algorithm only needs to give the algorithm and image data. Preferably, the embodiment of the present invention can adopt automatic registration based on mutual information.

In the embodiment of the present invention, noise, uneven burrs, sharp edges, and the like may occur during the acquisition of multiple images. In order to improve the image quality of images, image segmentation and feature extraction The image needs to be smoothed before taking it. There are many commonly used image smoothing methods, such as spline interpolation and nonlinear filtering, which can be set by the user according to actual needs.

Step S102: Acquire an area of each of the plurality of images after the pre-processing that meets a preset condition, and mark the area in each of the images.

In the embodiment of the present invention, the region that satisfies the preset condition may refer to the user's region of interest, and the extraction and analysis of the region of interest information, which plays an important role in image feature analysis. Marking the user's region of interest in each of the images also means segmenting the user's region of interest from each of the images. Medical image segmentation is the separation of regions of interest from other regions, tissues or organs. The purpose of segmentation is to extract valid information from the image, so image segmentation is critical throughout the process. The following three methods can be used to segment the image: one is manual segmentation, which means that an experienced expert can outline the edge of a specific organ, tissue or lesion according to the anatomical structure; the second is semi-automatic segmentation, which is a kind Combining manual and computer processing interaction, it allows manual interactive operation to provide some useful information, and then computerized for segmentation; third, fully automatic segmentation, which refers to the complete division of the image by the computer, the segmentation speed is fast, and No labor is required. The method for dividing the image may be selected according to actual needs, which is not limited herein.

Optionally, the obtaining, in the pre-processed plurality of images, the area that meets the preset condition in each of the multiple images includes:

Obtaining an area of a certain image after preprocessing that satisfies a preset condition;

And obtaining an area that satisfies the preset condition among other images in the plurality of images according to a feature point matching relationship between the area and the plurality of images.

In the embodiment of the present invention, when an area that meets a preset condition in each of the plurality of images after the pre-processing is acquired, an area that satisfies a preset condition in an image of the plurality of images may be acquired first. And searching, according to a feature point matching relationship between the image and the other image, an area matching the area of the certain image that meets the preset condition is searched from the another image, where the area is An area of the other image that satisfies a preset condition, and so on, until an area that satisfies a preset condition among all of the plurality of images is found.

Step S103, normalizing each of the images so that the gray value of each pixel in each image is within a preset gray value region.

In the embodiment of the present invention, since the source of the plurality of images is relatively wide, such as CT, MRI, PET, etc., the plurality of images acquired in step S101 have no uniform standard, and therefore, the plurality of images may be Each image in the image is normalized, and the gray value of each pixel in each image is scaled so that the gray value of each pixel is within a preset gray value region (for example, 0 to 16 or 0 to 32, etc.).

Optionally, the normalizing the image for each of the images includes:

Obtaining a sequence of a certain image in the plurality of images, wherein the plurality of images belong to N sequences, and N is an integer greater than 1;

Obtaining a gray value of all pixels of the same sequence and all pixels of the image in the same sequence, and finding a maximum gray value max ALL from gray values of all pixels;

Finding a maximum gray value max A from gray values of all pixels of the image;

Calculating the gray value a'=a*[(max ALL+M)/max A] after normalization of each pixel in the image according to max A and max ALL, where a is the pixel before the normalization process Gray value, M is a positive number.

In the embodiment of the present invention, the plurality of images may be divided into N sequences according to the source of the plurality of images, for example, the plurality of images are divided into three sequences, and the image derived from the CT is a sequence, which is derived from The image of MRI is a sequence, and the image derived from PET is a sequence.

Exemplarily, six images A1, A2, B1, B2, C1, and C2 are acquired, wherein images A1 and A2 belong to the same sequence, and are derived from CT. Images B1 and B2 belong to the same sequence, and are derived from MRI, images C1 and C2. It belongs to the same sequence and is derived from PET. When the image A1 is normalized, the gray values of all the pixels in the images A1 and A2 are respectively obtained, and the maximum gray value max ALL is found, and then all the pixels in the image A1 are searched. Gray value, and find the maximum gray value max A, calculate the gray value after normalization of each pixel in image A1 according to max A and max ALL a'=a*[(max ALL+M)/max A], where a is the gray value of the pixel before the normalization process, and the M user can set the value of M according to actual needs. Preferably, M is 100.

Step S104, extracting image features of the marked area, and acquiring a plurality of factor values related to the image features.

In the embodiment of the present invention, the marked area refers to an area that is marked from each image and that meets a preset condition in step S102.

Optionally, after the image feature of the marked area is extracted, the embodiment of the present invention further includes:

The image features are quantized according to a preset quantization algorithm.

In the embodiment of the present invention, different quantization algorithms also have an influence on the repeatability of image features. In order to study the influence of the quantization algorithm on image feature calculation, several different algorithms may be selected for calculation and analysis, such as Uniform quantization algorithm, Equal. -probability quantization algorithm and Lloyd-Max quantization algorithm.

In the implementation of the present invention, the extracted image features are image ensemble features, and common image omics features mainly include first-order features, shape features, texture features, and the like based on histograms. Histogram features include mean, median, maximum, minimum, range, energy, entropy, skewness, kurtosis, standard deviation, variance, etc. Shape features include volume, longest diameter, surface area, hardness, density, Spherical unbalance, curvature, eccentricity, surface area volume ratio, etc. Texture features include gray level co-occurrence matrix, gray run matrix, gray area size matrix, neighborhood gray difference matrix, wavelet transform, Laplace transform , Gaussian transformation and other related features.

In the embodiment of the present invention, multiple image features can be extracted simultaneously, and multiple image features are evaluated at the same time, for example, 1564 image features are extracted, including 28 shape features, 288 first-order features, and 1248 texture features, one of which The order features and texture features are extracted in six regions under four modes. One mode extracts 12 first-order features and 52 texture features in one region. The calculated image features are shown in Table 1.

Table 1 Image Group Characteristics Table

In the embodiment of the present invention, the value of the factor related to the image feature may refer to a factor that affects the image feature involved in the process from steps S101 to S104, for example, in the process of acquiring an image. Factors: layer thickness, layer spacing, tube voltage, tube current and reconstruction algorithm, different segmentation algorithms in the segmentation process, and different quantization methods in the quantization process.

Step S105, calculating an overall consistency correlation coefficient OCCC value of the image feature according to the plurality of factor values.

Step S106, if the OCCC value is greater than a predetermined threshold, determining that the image feature is repeatable Sex.

In the embodiment of the present invention, in order to study the influence of various factors on the repeatability of image features, multiple sets of parameter values may be set for the factors to be studied for repeated experiments. There are many factors influencing the whole process, such as factors affecting the acquisition process: layer thickness, layer spacing, tube voltage, tube current and reconstruction algorithm, different segmentation methods in the segmentation process and different quantization methods in the quantization process.

It should be noted that when calculating the Overall Concordance Correlation Coefficient (OCCC) value of the image feature according to the plurality of factor values, the OCCC values of the plurality of image features may be calculated at one time.

Experiments have been selected for parameter pixel size, gray level and quantization algorithm. The selected parameter values are pixel size (1, 2, 3), gray level (16, 32, 64, 128) and quantization algorithm (Uniform). , Equal-probability and Lloyd-Max), combining these parameters, you can find 3*4*3=36 by arrangement and combination: {1,16, Uniform}, {2,16, Uniform}, {3, 16, Uniform}... So 36 experiments were performed on these 36 different combinations. Then change a parameter, keep the other two parameters unchanged for comparative analysis, calculate the OCCC value of the image feature, such OCCC value has 33 kinds: {1,16, Uniform}vs{2,16,Uniform}vs{3 ,16,Uniform},{1,32,Uniform}vs{2,32,Uniform}vs{3,32,Uniform},...,{1,16,Uniform}vs{1,32,Uniform}vs {1,64, Uniform}vs{1,128, Uniform}.... Then repeatability evaluation is performed. First, a threshold is selected. This threshold is not fixed and can be selected according to the actual situation. For this experiment, the selected threshold size is 0.85. When OCCC>0.85, it is determined that the image feature is reproducible. Otherwise, the image feature is not reproducible, as shown in FIG. 2 for multiple texture features. An example diagram of the repeatability evaluation, where V1 to V33 are 33 OCCC values, and the OCCC value of 1 is the most repeatable. It should be noted that the reproducibility of the image feature means that the image feature is reproducible under certain factor values, for example, {1, 16, Uniform} vs {2, 16, Uniform} vs {3, 16, Uniform} OCCC value is greater than 0.85, indicating that the image features are reproducible when the pixel size is (1, 2, 3), the gray level is 16, and the quantization algorithm is Uniform.

It should be noted that when the parameter of the pixel size is changed, and the parameters of the gray level and the quantization algorithm are kept unchanged, the number of OCCC values is 4*3=12, wherein 4 is the number of parameters of the gray level, 3 is the number of parameters of the quantization algorithm; when the parameters of the gray level are changed, and the parameters of the pixel size and the quantization algorithm are kept unchanged, the number of OCCC values is 3*3=12, wherein two 3 are respectively pixels The number of parameters of the size and the number of parameters of the quantization algorithm; when the parameters of the quantization algorithm are changed while the parameters of the pixel size and the gray level are kept unchanged, the number of OCCC values is 3*4=12, wherein 3 is The number of parameters of the pixel size, 4 is the number of parameters of the gray level; the number of the above three OCCC values is added to be 33.

The embodiment of the present invention evaluates the repeatability of image features by using OCCC values, thereby considering a plurality of factor values related to image features (for example, pixel size during image processing, gray level of pixels, quantization algorithm, etc.) on image features. An assessment is made to improve the accuracy of the assessment.

Embodiment 2:

FIG. 3 is a schematic diagram showing the composition of the repeatability measuring apparatus for image features provided by Embodiment 2 of the present invention. For convenience of description, only parts related to the embodiments of the present invention are shown, which are described in detail as follows:

The device includes:

The image acquisition module 31 is configured to acquire a plurality of images and perform preprocessing on the plurality of images.

The area obtaining module 32 is configured to obtain an area of each of the plurality of images after the pre-processing that meets a preset condition, and mark the area in each of the images;

a normalization processing module 33, configured to perform normalization processing on each of the images such that a gray value of each pixel in each image is located in a preset gray value region;

The factor value obtaining module 34 is configured to extract image features of the marked area, and obtain a plurality of factor values related to the image features;

The calculating module 35 is configured to calculate an overall consistency correlation coefficient OCCC value of the image feature according to the plurality of factor values;

The determining module 36 is configured to determine that the image feature is repeatable if the OCCC value is greater than a predetermined threshold.

Optionally, the normalization processing module 33 includes:

The sequence obtaining unit 331 is configured to acquire a sequence of a certain image in the plurality of images, where the plurality of images belong to N sequences, and N is an integer greater than 1.

The gray value acquisition unit 332 is configured to acquire gray values of all the pixels of the plurality of images that belong to the same sequence as the image and all pixels of the image, and from the gray values of all the pixels Find the maximum gray value max ALL;

The searching unit 333 is configured to find a maximum gray value max A from gray values of all pixels of the certain image;

The gray value calculation unit 334 is configured to calculate, according to max A and max ALL, a gray value a'=a*[(max ALL+M)/max A] after normalization of each pixel in the image. , a is the gray value of the pixel before the normalization process, and M is a positive number.

Optionally, the image obtaining module 31 includes:

The registration unit 311 is configured to perform image registration on the plurality of images to obtain a feature point matching relationship between the plurality of images;

The processing unit 312 is configured to perform smoothing processing on the multiple images.

Optionally, the area obtaining module 32 includes:

The area obtaining unit 321 is configured to obtain an area of the certain image after the pre-processing that meets the preset condition;

The relationship obtaining unit 322 is configured to acquire an area that satisfies the preset condition among other images in the plurality of images according to a feature point matching relationship between the area and the plurality of images.

Optionally, the factor value obtaining module 34 is further configured to quantize the image feature according to a preset quantization algorithm after extracting the image feature of the marked area.

The reproducibility measuring device of the image feature provided by the embodiment of the present invention can be used in the first embodiment of the foregoing method. For details, refer to the description of the first embodiment, and details are not described herein again.

Embodiment 3:

4 is a diagram showing the composition of a repeatability measuring device for image features provided by Embodiment 3 of the present invention. intention. The reproducibility measuring device 400 of the image feature may be a device or a functional module or the like in the computing capability. The specific embodiment of the present invention does not limit the specific implementation of the repeatability measuring device for image features. The image feature repeatability measuring device 400 includes:

a processor 410, a communication interface 420, a memory 430 and a bus 440;

The processor 410, the communication interface 420, and the memory 430 complete communication with each other through the bus 440.

a communication interface 420, configured to communicate with an external device, such as a personal computer, a server, or the like;

The processor 410 is configured to execute the program 432;

In particular, program 432 can include program code, the program code including computer operating instructions.

The processor 410 may be a central processing unit CPU, or an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits configured to implement embodiments of the present invention.

The memory 430 is configured to store the program 432. The memory 430 may include a high speed RAM memory and may also include a non-volatile memory such as at least one disk memory. The program 432 may specifically include:

The image acquisition module 401 is configured to acquire a plurality of images and perform preprocessing on the plurality of images.

The area obtaining module 402 is configured to obtain an area that meets a preset condition in each of the plurality of images after the pre-processing, and mark the area in each of the images;

a normalization processing module 403, configured to perform normalization processing on each of the images, so that a gray value of each pixel in each image is located in a preset gray value area;

The factor value obtaining module 404 is configured to extract image features of the marked area, and obtain a plurality of factor values related to the image features;

The calculating module 405 is configured to calculate an overall consistency correlation coefficient OCCC value of the image feature according to the plurality of factor values;

The determining module 406 is configured to determine that the image feature is repeatable if the OCCC value is greater than a predetermined threshold.

It will be clearly understood by those skilled in the art that for the convenience and brevity of the description, only the division of the above functional modules is illustrated. In practical applications, the above function assignments may be completed by different functional modules as needed. That is, the internal structure of the device is divided into different functional modules, and the above functional modules may be implemented in the form of hardware or in the form of software. In addition, the specific names of the respective functional modules are only for the purpose of facilitating mutual differentiation, and are not intended to limit the scope of protection of the present application.

In summary, the embodiment of the present invention evaluates the reproducibility of image features by using OCCC values, thereby considering a plurality of factor values related to image features (eg, pixel size, pixel gray level, and quantization algorithm during image processing). Etc.) Evaluate image features to improve the accuracy of the assessment.

It will also be understood by those skilled in the art that all or part of the steps of the foregoing embodiments may be implemented by a program to instruct related hardware, and the program may be stored in a computer readable storage medium. The storage medium described includes a ROM/RAM, a magnetic disk, an optical disk, and the like.

The above is only the preferred embodiment of the present invention, and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection of the present invention. Within the scope.

Claims (11)

A method for measuring repeatability of an image feature, the method comprising: Acquiring multiple images and pre-processing the plurality of images; Obtaining an area of each of the plurality of images after the pre-processing that meets a preset condition, and marking the area in each of the images; Normalizing each image so that the gray value of each pixel in each image is within a preset gray value region; Extracting image features of the marked area and acquiring a plurality of factor values related to the image features; Calculating an overall consistency correlation coefficient OCCC value of the image feature according to the plurality of factor values; If the OCCC value is greater than a predetermined threshold, then the image feature is determined to be repeatable. The method of claim 1 wherein said each of said images The line standardization process includes: the normalization process includes: Obtaining a sequence of a certain image in the plurality of images, wherein the plurality of images belong to N sequences, and N is an integer greater than 1; Obtaining gray values of all pixels of the plurality of images belonging to the same sequence as the image and all pixels of the image, and finding a maximum gray value max ALL from gray values of all pixels ; Finding a maximum gray value max A from gray values of all pixels of the image; Calculating the gray value a'=a*[(max ALL+M)/max A] after normalization of each pixel in the image according to max A and max ALL, where a is the pixel before the normalization process Gray value, M is a positive number. The method according to claim 1, wherein the preprocessing the plurality of images comprises: Performing image registration on the plurality of images to obtain a feature point matching relationship between the plurality of images; Smoothing the plurality of images. The method according to claim 3, wherein the obtaining an area of each of the plurality of images after the pre-processing that meets a preset condition comprises: Obtaining an area of a certain image after preprocessing that satisfies a preset condition; And obtaining an area that satisfies the preset condition among other images in the plurality of images according to a feature point matching relationship between the area and the plurality of images. The method according to any one of claims 1 to 4, further comprising: after extracting the image features of the marked area, further comprising: The image features are quantized according to a preset quantization algorithm. A reproducibility measuring device for image features, characterized in that the device comprises: An image acquisition module, configured to acquire a plurality of images and perform preprocessing on the plurality of images; a region obtaining module, configured to acquire an area of each of the plurality of images after the pre-processing that meets a preset condition, and mark the area in each of the images; a normalization processing module, configured to perform normalization processing on each of the images such that a gray value of each pixel in each image is located in a preset gray value region; a factor value obtaining module, configured to extract image features of the marked area, and obtain a plurality of factor values related to the image features; a calculation module, configured to calculate an overall consistency correlation coefficient OCCC value of the image feature according to the plurality of factor values; And a determining module, configured to determine that the image feature is reproducible if the OCCC value is greater than a predetermined threshold. The apparatus according to claim 6, wherein said normalization processing module comprises: a sequence acquiring unit, configured to acquire a sequence of a certain image in the plurality of images, where The plurality of images belong to N sequences, and N is an integer greater than one; a gray value acquisition unit, configured to acquire gray values of all pixels of the plurality of images that belong to the same sequence as the image and all pixels of the image, and search for gray values of all pixels The maximum gray value max ALL; a searching unit, configured to find a maximum gray value max A from gray values of all pixels of the image; a gray value calculation unit for calculating a gray value a'=a*[(max ALL+M)/max A] after normalization of each pixel in the image according to max A and max ALL, wherein a is the gray value of the pixel before the normalization process, and M is a positive number. The device according to claim 6, wherein the image acquisition module comprises: a registration unit, configured to perform image registration on the plurality of images to obtain a feature point matching relationship between the plurality of images; a processing unit, configured to perform smoothing on the plurality of images. The device according to claim 8, wherein the area obtaining module comprises: An area obtaining unit, configured to acquire an area of a certain image after preprocessing that meets a preset condition; And a relationship acquiring unit, configured to acquire an area that satisfies the preset condition among other images in the plurality of images according to a feature point matching relationship between the area and the plurality of images. The device according to any one of claims 6 to 9, wherein the factor value acquisition module is further configured to: After extracting the image features of the marked area, the image features are quantized according to a preset quantization algorithm. A reproducibility measuring device for image features, characterized in that the device comprises: Processor, communication interface, memory and bus; The processor, the communication interface, and the memory complete communication with each other through the bus; The communication interface is configured to communicate with an external device; The processor is configured to execute a program; The memory is configured to store the program; The program includes: And an image acquisition module, configured to acquire a plurality of images and perform pre-processing on the plurality of images; and an area acquiring module, configured to acquire an area of each of the plurality of images after the pre-processing, that meets a preset condition, And marking the area in each of the images; a normalization processing module, configured to perform normalization processing on each of the images such that a gray value of each pixel in each image is located in a preset gray value region; a factor value obtaining module, configured to extract image features of the marked area, and obtain a plurality of factor values related to the image features; a calculation module, configured to calculate an overall consistency correlation coefficient OCCC value of the image feature according to the plurality of factor values; And a determining module, configured to determine that the image feature is reproducible if the OCCC value is greater than a predetermined threshold.

Images