Image processing method and device, storage medium, electronic equipment and program product

Abstract

The invention discloses an image processing method and device, a storage medium, electronic equipment and a program product. Relates to the financial science and technology field or other fields. The method comprises the following steps: acquiring a seal image of which the authenticity is to be verified; performing image decomposition processing on the seal image by adopting a non-subsampled contourlet transform method to obtain a plurality of sub-band images; performing feature extraction processing on the plurality of sub-band images by adopting a gray-level co-occurrence matrix method to obtain image features of the seal image; the absolute correlation degree between the image features of the seal image and the image features of the reference seal image is calculated through a grey correlation clustering analysis method, a verification result is determined based on the absolute correlation degree, and the verification result is used for representing whether the seal image is real or not. According to the invention, the method solves a problem that the recognition accuracy is low when the authenticity of the seal image is recognized in the prior art.

Description

Technical Field

[0001] The present application relates to the field of financial technology or other fields, and specifically, to an image processing method, device, storage medium, electronic device and program product. Background Art

[0002] With the rapid development and continuous advancement of modern science and technology, the application of electronic seals has been widely promoted and used in various fields (such as finance). Thanks to the development of digital image processing technology, the technology for counterfeiting seal images has become increasingly sophisticated, making the difference between counterfeit images and authentic seal images increasingly small. When using simple image analysis techniques (such as preset rule matching, feature point detection, machine learning algorithms, etc.), it is difficult to effectively distinguish the authenticity of seal images, resulting in low recognition accuracy.

[0003] Currently, no effective solution has been proposed for the above-mentioned problems in related technologies. Summary of the Invention

[0004] The main purpose of this application is to provide an image processing method, device, storage medium, electronic device and program product to solve the problem of low recognition accuracy when identifying the authenticity of seal images in related technologies.

[0005] To achieve the above-mentioned objectives, according to one aspect of the present application, an image processing method is provided. The method comprises: obtaining a seal image to be verified for authenticity; performing image decomposition processing on the seal image using a non-subsampled contourlet transform method to obtain multiple sub-band images; performing feature extraction processing on the multiple sub-band images using a gray-level co-occurrence matrix method to obtain image features of the seal image; and calculating the absolute correlation between the image features of the seal image and the image features of a reference seal image using a gray correlation cluster analysis method, and determining a verification result based on the absolute correlation, wherein the verification result is used to indicate whether the seal image is authentic.

[0006] Furthermore, the image processing method also includes: obtaining at least one preset direction value and at least one preset distance value; determining at least one parameter combination based on the at least one direction value and the at least one distance value; for each parameter combination, determining the image sub-features of each sub-band image under the parameter combination based on the gray-level co-occurrence matrix method; determining the target image sub-features of each sub-band image based on the image sub-features of each sub-band image under at least one parameter combination; and determining the image features of the seal image based on the target image sub-features of multiple sub-band images.

[0007] Furthermore, the image processing method also includes: for each sub-band image, determining the gray level co-occurrence matrix of the sub-band image under the parameter combination according to the gray level co-occurrence matrix method; determining the parameter value of the sub-band image under multiple texture feature parameters according to the gray level co-occurrence matrix; and determining the image sub-features of the sub-band image under the parameter combination according to the parameter values of the sub-band image under multiple texture feature parameters.

[0008] Furthermore, the image processing method also includes: for each texture feature parameter of each sub-band image, determining the target parameter value of the texture feature parameter of the sub-band image based on the parameter value of the texture feature parameter of the sub-band image under at least one parameter combination; and determining the target image sub-feature of the sub-band image based on the target parameter values of multiple texture feature parameters of the sub-band image.

[0009] Furthermore, the image processing method also includes: standardizing the image features of the seal image to obtain a first image feature; standardizing the image features of the reference seal image to obtain a second image feature; for each feature component in the first image feature, calculating the relationship coefficient corresponding to the feature component based on the component values of the first image feature and the second image feature on the feature component, wherein the relationship coefficient represents the correlation between the image features of the seal image and the reference seal image on the feature component; and determining the absolute correlation between the image features of the seal image and the image features of the reference seal image based on the relationship coefficients corresponding to the respective feature components.

[0010] Furthermore, the image processing method also includes: calculating the component difference between the component values of the first image feature and the second image feature on the feature component; determining the maximum difference and the minimum difference from the component differences corresponding to each feature component; and calculating the relationship coefficient based on the component difference, maximum difference and minimum difference of the feature component.

[0011] Furthermore, the image processing method also includes: when the absolute correlation degree is greater than or equal to a preset value, determining that the verification result represents the seal image as a real seal image; when the absolute correlation degree is less than the preset value, determining that the verification result represents the seal image as a forged seal image.

[0012] To achieve the above-mentioned purpose, according to another aspect of the present application, an image processing device is provided. The device comprises: an acquisition module for acquiring a seal image to be verified for authenticity; a first processing module for performing image decomposition processing on the seal image using a non-subsampled contourlet transform method to obtain multiple sub-band images; a second processing module for performing feature extraction processing on the multiple sub-band images using a gray-level co-occurrence matrix method to obtain image features of the seal image; and a determination module for calculating the absolute correlation between the image features of the seal image and the image features of a reference seal image using a gray correlation cluster analysis method, and determining a verification result based on the absolute correlation, wherein the verification result is used to indicate whether the seal image is authentic.

[0013] Furthermore, the second processing module also includes: an acquisition submodule for acquiring at least one preset direction value and at least one preset distance value; a first determination submodule for determining at least one parameter combination based on at least one direction value and at least one distance value; a second determination submodule for determining, for each parameter combination, the image subfeatures of each subband image under the parameter combination according to the gray level co-occurrence matrix method; a third determination submodule for determining the target image subfeatures of each subband image based on the image subfeatures of each subband image under at least one parameter combination; and a fourth determination submodule for determining the image features of the seal image based on the target image subfeatures of multiple subband images.

[0014] Furthermore, the second determination submodule also includes: a first determination unit, used to determine, for each sub-band image, the gray level co-occurrence matrix of the sub-band image under the parameter combination according to the gray level co-occurrence matrix method; a second determination unit, used to determine the parameter value of the sub-band image under multiple texture feature parameters according to the gray level co-occurrence matrix; and a third determination unit, used to determine the image sub-features of the sub-band image under the parameter combination according to the parameter value of the sub-band image under multiple texture feature parameters.

[0015] Furthermore, the third determination submodule also includes: a fourth determination unit, which is used to determine, for each texture feature parameter of each sub-band image, a target parameter value of the texture feature parameter of the sub-band image based on the parameter value of the texture feature parameter of the sub-band image under at least one parameter combination; and a fifth determination unit, which is used to determine the target image sub-feature of the sub-band image based on the target parameter values of multiple texture feature parameters of the sub-band image.

[0016] Furthermore, the determination module also includes: a first processing submodule, used to standardize the image features of the seal image to obtain the first image features; a second processing submodule, used to standardize the image features of the reference seal image to obtain the second image features; a calculation submodule, used to calculate the relationship coefficient corresponding to each feature component in the first image feature according to the component values of the first image feature and the second image feature on the feature component, wherein the relationship coefficient represents the correlation between the image features of the seal image and the reference seal image on the feature component; a fifth determination submodule, used to determine the absolute correlation between the image features of the seal image and the image features of the reference seal image based on the relationship coefficients corresponding to each feature component.

[0017] Furthermore, the calculation submodule also includes: a first calculation unit, used to calculate the component difference between the component values of the first image feature and the second image feature on the feature component; a sixth determination unit, used to determine the maximum difference and the minimum difference from the component differences corresponding to each feature component; a second calculation unit, used to calculate the relationship coefficient based on the component difference, maximum difference and minimum difference of the feature component.

[0018] Furthermore, the determination module also includes: a sixth determination submodule, used to determine that the verification result represents that the seal image is a real seal image when the absolute correlation degree is greater than or equal to a preset value; and a seventh determination submodule, used to determine that the verification result represents that the seal image is a forged seal image when the absolute correlation degree is less than a preset value.

[0019] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer-readable storage medium is provided, which includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned image processing method.

[0020] In order to achieve the above-mentioned purpose, according to another aspect of the present application, an electronic device is provided, which includes a memory storing an executable program; and a processor for running the program, wherein the above-mentioned image processing method is executed when the program is running.

[0021] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer program product is provided, comprising computer instructions, which implement the steps of the above-mentioned image processing method when executed by a processor.

[0022] In an embodiment of the present application, by obtaining a seal image whose authenticity is to be verified and decomposing it using a non-subsampled contourlet transform method, the multi-level features of the image can be captured. By using a gray-level co-occurrence matrix method to perform feature extraction processing on the multiple sub-band images obtained by decomposition, image features are obtained, thereby achieving effective quantification of the visual characteristics of the seal image. By using a gray correlation cluster analysis method to determine the absolute correlation between the image features of the seal image and the image features of the reference seal image, an effective evaluation of the feature correlation between the seal to be verified and the reference seal is achieved, thereby improving the accuracy of identifying the authenticity of the seal image when determining the verification result based on the absolute correlation.

[0023] It can be seen that the method provided in this embodiment achieves the purpose of using NSCT-GLCM to extract features of the seal image to be verified, and verifying the authenticity of the seal image based on the grey relational cluster analysis method and image features, thereby achieving the technical effect of improving the accuracy of identifying the authenticity of the seal image, and solving the technical problem of low recognition accuracy when identifying the authenticity of the seal image in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings, which constitute part of this application, are intended to provide a further understanding of this application. The exemplary embodiments and descriptions of this application are intended to explain this application and do not constitute an improper limitation on this application. In the accompanying drawings:

[0025] Figure 1 This is a hardware structure block diagram of a computer terminal provided according to an embodiment of the present application;

[0026] Figure 2 is a flowchart of an image processing method provided according to an embodiment of the present application;

[0027] Figure 3 This is a flowchart of determining image features according to an embodiment of the present application;

[0028] Figure 4 is a schematic diagram of an image processing device provided according to an embodiment of the present application;

[0029] Figure 5 This is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] It should be noted that the image processing method, device, storage medium, electronic device and program product disclosed in the present invention can be used in the field of financial technology, and can also be used in any field other than the field of financial technology. The application field of the image processing method, device, storage medium, electronic device and program product and device disclosed in the present invention is not limited.

[0033] It should be noted that the collected information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of the relevant data comply with relevant laws, regulations and standards, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation portals for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions to provide users with corresponding operation portals for users to choose to agree or refuse the automated decision-making results; if the user chooses to refuse, the expert decision-making process will be entered.

[0034] Example 1

[0035] According to an embodiment of the present application, an embodiment of an image processing method is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0036] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG1 shows a hardware structure block diagram of a computer terminal (or mobile device) for implementing an image processing method. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more (illustrated as 102a, 102b, ..., 102n in the figure) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0037] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuitry may be a single independent processing module, or may be incorporated in whole or in part into any of the other components of the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuitry serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0038] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the image processing method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implementing the above-mentioned image processing method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0039] The transmission device 106 is configured to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by the communications provider of the computer terminal 10. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is configured to communicate with the Internet wirelessly.

[0040] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0041] Under the above operating environment, this application provides Figure 2 The image processing method shown. Figure 2 This is a flowchart of an image processing method provided according to an embodiment of the present application.

[0042] Step S201: Acquire a seal image to be verified for authenticity.

[0043] Optionally, electronic devices, application systems, servers and other devices may be used as the execution subject of the present application. In this embodiment, the target processing system is used as the execution subject to execute the above-mentioned image processing method.

[0044] Optionally, the seal image may be extracted from a target file, which includes but is not limited to documents such as bills and contracts, and the target file may be a document in a financial institution.

[0045] Step S202 : performing image decomposition processing on the seal image using a non-subsampled contourlet transform method to obtain a plurality of sub-band images.

[0046] Alternatively, the Non-Subsampled Contourlet Transform (NSCT) is an image processing technique used to decompose an input image into multiple sub-images of different frequency components, which can also be referred to as sub-band images. During the decomposition process, NSCT employs a non-subsampled structure, which is robust to noise. Unlike traditional downsampling transforms, it is less prone to information loss and can preserve image details to a certain extent, including those that may be interfered with by noise. For example, in an image containing Gaussian noise, the sub-bands decomposed by NSCT can still retain the image's main contours and texture information.

[0047] Optionally, the input seal image is decomposed using NSCT technology to obtain multiple sub-band images, wherein the multiple sub-band images represent different frequency band components of the seal image.

[0048] In order to improve the image processing effect, before the seal image is processed by the NSCT technology, the seal image can be normalized, and then the normalized seal image is decomposed by the NSCT technology to obtain multiple sub-band images.

[0049] Step S203 , performing feature extraction processing on the multiple sub-band images using a gray level co-occurrence matrix method to obtain image features of the seal image.

[0050] Alternatively, a Gray Level Co-occurrence Matrix (GLCM) is a statistical matrix used to describe the neighboring relationships and texture characteristics of gray levels in an image. By calculating the probability of pixels in an image appearing at a specific direction and distance, the GLCM can reveal the texture characteristics of the image.

[0051] Optionally, the target processing system may determine the target sub-features of each sub-band image according to a gray level co-occurrence matrix method, thereby determining the image features of the seal image according to the target image sub-features of the plurality of sub-band images.

[0052] Optionally, the target image sub-feature of the sub-band image may include target parameter values of the sub-band image under multiple texture feature parameters. The multiple texture feature parameters include: second-order moment, contrast, correlation, variance, inverse moment, and entropy.

[0053] It should be noted that applying GLCM to the NSCT subbands can reduce the impact of local noise on texture feature extraction by integrating texture information from multiple subbands. For example, in noisy environments, the NSCT-GLCM method can effectively suppress the interference of noise on texture feature extraction through multi-subband texture analysis, thereby more accurately determining feature information in the image and facilitating subsequent feature comparison.

[0054] Step S204 , using a grey correlation cluster analysis method to calculate the absolute correlation between the image features of the seal image and the image features of the reference seal image, and determining a verification result based on the absolute correlation, wherein the verification result is used to indicate whether the seal image is authentic.

[0055] Alternatively, the grey relational clustering method is a method that uses grey system theory to perform relational analysis and clustering.

[0056] Optionally, the reference seal image is an image corresponding to a real seal. The target processing system may have preset matching relationships between different files and different real seal identifiers. The target processing system may determine the target file to which the seal image belongs, and then determine the real seal identifier corresponding to the target file from the matching relationship, thereby determining the seal image associated with the real seal identifier as the reference seal image.

[0057] Optionally, after determining the reference seal image, the target processing system may use a grey correlation cluster analysis method to calculate the absolute correlation between the image features of the seal image and the image features of the reference seal image. The absolute correlation represents the correlation between the image features of the seal image to be verified and the image features of the reference seal image.

[0058] After obtaining the absolute correlation, the target processing system may determine a verification result based on the absolute correlation, for example, by setting a preset value and then comparing the absolute correlation with the preset value to obtain a comparison result, thereby determining a verification result based on the comparison result.

[0059] In an embodiment of the present application, by obtaining a seal image whose authenticity is to be verified and decomposing it using a non-subsampled contourlet transform method, the multi-level features of the image can be captured. By using a gray-level co-occurrence matrix method to perform feature extraction processing on the multiple sub-band images obtained by decomposition, image features are obtained, thereby achieving effective quantification of the visual characteristics of the seal image. By using a gray correlation cluster analysis method to determine the absolute correlation between the image features of the seal image and the image features of the reference seal image, an effective evaluation of the feature correlation between the seal to be verified and the reference seal is achieved, thereby improving the accuracy of identifying the authenticity of the seal image when determining the verification result based on the absolute correlation.

[0060] It can be seen that the method provided in this embodiment achieves the purpose of using NSCT-GLCM to extract features of the seal image to be verified, and verifying the authenticity of the seal image based on the grey relational cluster analysis method and image features, thereby achieving the technical effect of improving the accuracy of identifying the authenticity of the seal image, and solving the technical problem of low recognition accuracy when identifying the authenticity of the seal image in the related art.

[0061] Optionally, in the image processing method provided in the embodiment of the present application, Figure 3 This is a flow chart of determining image features according to an embodiment of the present application. Figure 3 As shown, in the process of performing feature extraction processing on multiple sub-band images using the gray level co-occurrence matrix method to obtain the image features of the seal image, the target processing system can perform the following steps:

[0062] Step S301: Obtain at least one preset direction value and at least one preset distance value.

[0063] Alternatively, GLCM is a statistical method used to describe image texture features. It reflects image texture information by calculating the joint distribution of grayscale values of pairs of pixels in the image. CLCM calculation requires specifying two parameters: direction and distance. Direction refers to the relative orientation of pixel pairs. For example, an angle of 0° represents horizontal pixel pairs, while a 45° angle represents diagonal pixel pairs. Distance refers to the distance between pixel pairs; for example, a distance of 1 indicates adjacent pixel pairs.

[0064] In an optional embodiment, the at least one direction value may include at least one of the following: 0°, 45°, 90°, 135°.

[0065] In an optional embodiment, the distance may be a fixed distance (eg, 1), or multiple distances (eg, 1, 2, 3, etc.) may be selected to analyze texture features of different scales.

[0066] Step S302: determining at least one parameter combination according to at least one direction value and at least one distance value.

[0067] After obtaining at least one preset direction value and at least one preset distance value, at least one parameter combination can be determined based on the at least one direction value and the at least one distance value, wherein each parameter combination includes a direction value and a distance value, and the values in different parameter combinations are not completely the same.

[0068] Step S303 : for each parameter combination, determine the image sub-features of each sub-band image under the parameter combination according to the gray level co-occurrence matrix method.

[0069] For example, under a certain parameter combination, for each sub-band image, the gray level co-occurrence matrix of the sub-band image under the parameter combination is determined according to the gray level co-occurrence matrix method, so as to determine the image sub-features of the sub-band image under the parameter combination based on the gray level co-occurrence matrix of the sub-band image under the parameter combination. Each parameter combination defines a gray level co-occurrence matrix under a specific situation. For example, a combination of a direction value of 0° and a distance value of 1 can construct a gray level co-occurrence matrix in the horizontal direction.

[0070] Step S304 : determining target image sub-features of each sub-band image according to the image sub-features of each sub-band image under at least one parameter combination.

[0071] Optionally, after extracting the image subfeatures of each subband image under at least one parameter combination, the target image subfeatures of each native image can be determined through feature selection or feature fusion. For example, the image subfeatures under a specific parameter combination can be selected as the target image subfeatures, or the features of the subband images under at least one parameter combination can be weighted and averaged to obtain the target image subfeatures corresponding to the subband image.

[0072] Step S305 : determining image features of the seal image according to target image sub-features of the plurality of sub-band images.

[0073] Optionally, after obtaining the target image sub-features of multiple sub-band images, the target image sub-features of the multiple sub-band images can be averaged to obtain the image features of the seal image, or the target image sub-features of the multiple sub-band images can be weighted summed to obtain the image features of the seal image. Regardless of whether the averaging or weighted summing method is adopted, the calculation process is based on the dimension of the texture feature parameter, that is, the parameter values belonging to the same texture feature parameter in the target image sub-features of the multiple sub-band images are averaged (or weighted summed), and then the image features of the seal image are composed of the calculation results corresponding to the various texture feature parameters.

[0074] It should be noted that by determining different parameter combinations, the texture features of each sub-band image can be comprehensively analyzed from multiple perspectives, thereby improving the diversity and accuracy of feature extraction.

[0075] Optionally, in the image processing method provided in an embodiment of the present application, the image sub-features of each sub-band image under the parameter combination are determined according to the gray-level co-occurrence matrix method, including: for each sub-band image, determining the gray-level co-occurrence matrix of the sub-band image under the parameter combination according to the gray-level co-occurrence matrix method; determining the parameter values of the sub-band image under multiple texture feature parameters according to the gray-level co-occurrence matrix; and determining the image sub-features of the sub-band image under the parameter combination according to the parameter values of the sub-band image under multiple texture feature parameters.

[0076] Optionally, for each sub-band image, the sub-band image can be divided into grayscale levels, and then the frequency of occurrence of pairs of pixels with different grayscale levels at a specific direction and distance (i.e., a specific parameter combination) is calculated to form a grayscale co-occurrence matrix. Each element in the grayscale co-occurrence matrix represents the probability that the grayscale values of two pixels in an image (e.g., the seal image to be verified) appear simultaneously at a specified distance and angle. For example, the element p(i, j) in the GLCM represents the probability that a pixel with grayscale value i and a pixel with grayscale value j appear adjacent to each other at a given distance and angle.

[0077] After determining the gray level co-occurrence matrix of a sub-band image under a certain parameter combination, the target processing system can determine the parameter values of the sub-band image under multiple texture feature parameters based on the gray level co-occurrence matrix. The multiple texture feature parameters include: second-order moment, contrast, correlation, variance, inverse moment, and entropy. For example, they can be determined in the following way:

[0078] (1) Second-order moment: It represents the sum of squares of each element in the GLCM, reflecting the grayscale distribution and details of the image. The larger the ASM, the rougher the image; conversely, the smaller the ASM, the more accurate the image.

[0079]

[0080] Wherein, ASM represents the second-order moment, L represents the number of gray levels of the image, for example, if the image is an 8-bit grayscale image, then L = 256, and p(i, j) represents an element in GLCM.

[0081] (2) Contrast: This reflects the unevenness of the image surface and the clarity of the image. The higher the contrast, the smaller the surface unevenness and the clearer the image effect; conversely, the lower the contrast, the greater the surface unevenness and the blurrier the image effect.

[0082]

[0083] Where Con represents contrast.

[0084] (3) Correlation: Correlation describes the degree of horizontal or vertical correlation between elements on the image. When the elements in the matrix are equal, the correlation is large; otherwise, the correlation is small.

[0085]

[0086] Among them, Cor represents the correlation, μ x Represents the grayscale mean of the sub-band image in the horizontal direction, μ y Represents the grayscale mean of the sub-band image in the vertical direction, σ x Indicates the grayscale standard deviation of the sub-band image in the horizontal direction, σ y Indicates the grayscale standard deviation of the sub-band image in the vertical direction,

[0087] (4) Variance: reflects the periodicity of local features of the image. The larger the variance, the longer the periodicity.

[0088]

[0089] Among them, Var represents variance, μ represents the grayscale mean of the sub-band image,

[0090] (5) Inverse moment difference: It is mainly used to distinguish the degree of change in the local area of the image. The larger the inverse moment difference, the smaller the local change of the image, indicating that the image distribution is relatively more uniform.

[0091]

[0092] Where IDM stands for inverse difference moment.

[0093] (6) Entropy: reflects the amount of useful information in an image. The greater the entropy, the greater the amount of information output by the image. When the entropy value is 0, there is no useful information.

[0094]

[0095] Where Ent represents entropy.

[0096] Afterwards, the parameter values of the sub-band image under the multiple texture feature parameters may be used to form the image sub-features of the sub-band image under the parameter combination.

[0097] It should be noted that by determining the parameter values of the sub-band image under multiple texture feature parameters based on the gray-level co-occurrence matrix, and then using them to determine the image sub-features, the comprehensiveness and accuracy of feature extraction are effectively improved, and the accurate determination of image sub-features is achieved.

[0098] Optionally, in the image processing method provided in an embodiment of the present application, the target image sub-features of each sub-band image are determined based on the image sub-features of each sub-band image under at least one parameter combination, including: for each texture feature parameter of each sub-band image, determining the target parameter value of the texture feature parameter of the sub-band image based on the parameter value of the texture feature parameter of the sub-band image under at least one parameter combination; determining the target image sub-features of the sub-band image based on the target parameter values of multiple texture feature parameters of the sub-band image.

[0099] For example, for a texture feature parameter, the second-order moment, of a sub-band image, the values of the second-order moment of the sub-band image under at least one parameter combination are averaged (or weighted summed) to obtain a target parameter value for the second-order moment of the sub-band image. The weights corresponding to different parameter combinations may be manually preset.

[0100] Optionally, after obtaining target parameter values of multiple texture feature parameters of the sub-band image, the target parameter values of the multiple texture feature parameters of the sub-band image are used to form target image sub-features of the sub-band image.

[0101] It should be noted that, through the above approach, it is possible to determine the sub-features of the target image based on multiple texture features of the sub-band image under different parameter combinations, thereby improving the accuracy of the determined sub-features of the target image.

[0102] Optionally, in the image processing method provided in the embodiment of the present application, a grey correlation cluster analysis method is used to calculate the absolute correlation between the image features of the seal image and the image features of the reference seal image, including: standardizing the image features of the seal image to obtain a first image feature; standardizing the image features of the reference seal image to obtain a second image feature; for each feature component in the first image feature, calculating the relationship coefficient corresponding to the feature component based on the component values of the first image feature and the second image feature on the feature component, wherein the relationship coefficient represents the correlation between the image features of the seal image and the reference seal image on the feature component; and determining the absolute correlation between the image features of the seal image and the image features of the reference seal image based on the relationship coefficients corresponding to each feature component.

[0103] Optionally, the image features of the seal image include multiple components, and different components (also referred to as feature components) in the image features represent parameter values of the seal image under different texture feature parameters. The image features of the reference seal image have the same content and form as the image features of the seal image.

[0104] Optionally, the target processing system may perform standardization processing on the image features of the seal image to obtain a first image feature, which may be expressed as:

[0105]

[0106] Among them, X i (0) represents the first image feature, X il (0) For sequence X i Medium Weight X il The ratio of the actual value of (1,2,3,…,p) to the standard value, X irepresents the image feature of the seal image, p represents the number of components in the image feature (that is, the number of texture feature parameters), and

[0107] Optionally, the calculation method of the second image feature is the same as the principle of the calculation method of the first image feature, so it is not repeated here.

[0108] After obtaining the first image feature and the second image feature, the target processing system can calculate the relationship coefficient corresponding to each feature component in the first image feature according to the component values of the first image feature and the second image feature on the feature component.

[0109] After obtaining the correlation coefficient, the target processing system can determine the absolute correlation between the image features of the seal image and the image features of the reference seal image based on the correlation coefficient corresponding to each feature component. For example, the calculation formula of the absolute correlation is as follows:

[0110]

[0111] Among them, r ij Image feature X representing the seal image i and the image feature X of the reference stamp image j The absolute correlation between them, l represents the lth characteristic component, ε ij (l) represents the image feature X of the seal image i and the image feature X of the reference stamp image j The relationship coefficient between them on the lth eigencomponent.

[0112] It should be noted that, through the above formula, the absolute correlation between the image features of the seal image and the image features of the reference seal image can be accurately calculated, thereby improving the accuracy of seal authenticity identification.

[0113] Optionally, in the image processing method provided in the embodiment of the present application, the relationship coefficient corresponding to the feature component is calculated based on the component values of the first image feature and the second image feature on the feature component, including: calculating the component difference between the component values of the first image feature and the second image feature on the feature component; determining the maximum difference and the minimum difference from the component differences corresponding to each feature component; and calculating the relationship coefficient based on the component difference, maximum difference and minimum difference of the feature component.

[0114] For example, the target processing system can calculate the relationship coefficient as follows:

[0115] Let the first image feature X i (0) With the second image feature Xj (0) The absolute value of the difference between the lth component of ij (l), then Δ ij (l)=|X il (0) -X jl (0) |, thus p Δ il (l).

[0116] The component difference Δ between the component values of the first image feature and the second image feature on the feature component is obtained. ij (l) Then, the maximum difference Δ is determined from the component differences corresponding to each characteristic component. max and the minimum difference Δ min .

[0117] The relationship coefficient can then be expressed as:

[0118]

[0119] Among them, ε ij (l) represents the image feature X of the seal image i and the image feature X of the reference stamp image j The relationship coefficient between them on the lth characteristic component, δ represents the preset resolution coefficient.

[0120] It should be noted that, through the above method, accurate calculation of the relationship coefficient is achieved, thereby improving the accuracy of the calculated absolute correlation degree.

[0121] Optionally, in the image processing method provided in an embodiment of the present application, the verification result is determined based on the absolute correlation degree, including: when the absolute correlation degree is greater than or equal to a preset value, determining that the verification result represents that the seal image is a real seal image; when the absolute correlation degree is less than the preset value, determining that the verification result represents that the seal image is a forged seal image.

[0122] Optional, r ij The value range of is [0, 1], and the preset value may be a value greater than 0.5, for example, the preset value may be 0.75.

[0123] For example, assuming the preset value is 0.75, if the absolute correlation degree is 0.6, the verification result indicates that the seal image is a forged seal image; if the absolute correlation degree is 0.8, the verification result indicates that the seal image is a genuine seal image.

[0124] It should be noted that, through the above method, accurate determination of the verification result is achieved.

[0125] It can be seen that the method provided in this embodiment achieves the purpose of using NSCT-GLCM to extract features of the seal image to be verified, and verifying the authenticity of the seal image based on the grey relational cluster analysis method and image features, thereby achieving the technical effect of improving the accuracy of identifying the authenticity of the seal image, and solving the technical problem of low recognition accuracy when identifying the authenticity of the seal image in the related art.

[0126] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0127] Example 2

[0128] The present application also provides an image processing device. It should be noted that the image processing device of the present application can be used to execute the image processing method provided in the present application. The image processing device provided in the present application is introduced below.

[0129] According to an embodiment of the present application, a device for implementing the above-mentioned image processing method is also provided, such as Figure 4 As shown, the device includes:

[0130] An acquisition module 401 is used to acquire a seal image to be verified for authenticity;

[0131] The first processing module 402 is configured to perform image decomposition processing on the seal image using a non-subsampled contourlet transform method to obtain a plurality of sub-band images;

[0132] The second processing module 403 is used to perform feature extraction processing on the multiple sub-band images using a gray level co-occurrence matrix method to obtain image features of the seal image;

[0133] The determination module 404 is used to calculate the absolute correlation between the image features of the seal image and the image features of the reference seal image using a grey correlation cluster analysis method, and determine a verification result based on the absolute correlation, wherein the verification result is used to indicate whether the seal image is authentic.

[0134] In an embodiment of the present application, by obtaining a seal image whose authenticity is to be verified and decomposing it using a non-subsampled contourlet transform method, the multi-level features of the image can be captured. By using a gray-level co-occurrence matrix method to perform feature extraction processing on the multiple sub-band images obtained by decomposition, image features are obtained, thereby achieving effective quantification of the visual characteristics of the seal image. By using a gray correlation cluster analysis method to determine the absolute correlation between the image features of the seal image and the image features of the reference seal image, an effective evaluation of the feature correlation between the seal to be verified and the reference seal is achieved, thereby improving the accuracy of identifying the authenticity of the seal image when determining the verification result based on the absolute correlation.

[0135] It can be seen that the method provided in this embodiment achieves the purpose of using NSCT-GLCM to extract features of the seal image to be verified, and verifying the authenticity of the seal image based on the grey relational cluster analysis method and image features, thereby achieving the technical effect of improving the accuracy of identifying the authenticity of the seal image, and solving the technical problem of low recognition accuracy when identifying the authenticity of the seal image in the related art.

[0136] Optionally, in the image processing device provided in the embodiment of the present application, the second processing module also includes: an acquisition submodule for acquiring at least one preset direction value and at least one preset distance value; a first determination submodule for determining at least one parameter combination based on at least one direction value and at least one distance value; a second determination submodule for determining, for each parameter combination, the image subfeatures of each subband image under the parameter combination according to the gray level co-occurrence matrix method; a third determination submodule for determining the target image subfeatures of each subband image based on the image subfeatures of each subband image under at least one parameter combination; and a fourth determination submodule for determining the image features of the seal image based on the target image subfeatures of multiple subband images.

[0137] Optionally, in the image processing device provided in the embodiment of the present application, the second determination submodule also includes: a first determination unit, used to determine, for each sub-band image, the gray level co-occurrence matrix of the sub-band image under the parameter combination according to the gray level co-occurrence matrix method; a second determination unit, used to determine the parameter value of the sub-band image under multiple texture feature parameters according to the gray level co-occurrence matrix; and a third determination unit, used to determine the image sub-features of the sub-band image under the parameter combination according to the parameter value of the sub-band image under multiple texture feature parameters.

[0138] Optionally, in the image processing device provided in the embodiment of the present application, the third determination submodule also includes: a fourth determination unit, used to determine, for each texture feature parameter of each sub-band image, the target parameter value of the texture feature parameter of the sub-band image based on the parameter value of the texture feature parameter of the sub-band image under at least one parameter combination; and a fifth determination unit, used to determine the target image sub-feature of the sub-band image based on the target parameter values of multiple texture feature parameters of the sub-band image.

[0139] Optionally, in the image processing device provided in the embodiment of the present application, the determination module also includes: a first processing sub-module, used to standardize the image features of the seal image to obtain a first image feature; a second processing sub-module, used to standardize the image features of the reference seal image to obtain a second image feature; a calculation sub-module, used to calculate the relationship coefficient corresponding to each feature component in the first image feature according to the component values of the first image feature and the second image feature on the feature component, wherein the relationship coefficient represents the correlation between the image features of the seal image and the reference seal image on the feature component; a fifth determination sub-module, used to determine the absolute correlation between the image features of the seal image and the image features of the reference seal image based on the relationship coefficients corresponding to each feature component.

[0140] Optionally, in the image processing device provided in the embodiment of the present application, the calculation submodule also includes: a first calculation unit, used to calculate the component difference between the component values of the first image feature and the second image feature on the feature component; a sixth determination unit, used to determine the maximum difference and the minimum difference from the component differences corresponding to each feature component; and a second calculation unit, used to calculate the relationship coefficient based on the component difference, maximum difference and minimum difference of the feature component.

[0141] Optionally, in the image processing device provided in the embodiment of the present application, the determination module also includes: a sixth determination submodule, used to determine that the verification result represents that the seal image is a real seal image when the absolute correlation degree is greater than or equal to a preset value; and a seventh determination submodule, used to determine that the verification result represents that the seal image is a forged seal image when the absolute correlation degree is less than a preset value.

[0142] It should be noted that the acquisition module 401, the first processing module 402, the second processing module 403, and the determination module 404 correspond to steps S201 to S204 in Example 1. The examples and application scenarios implemented by the four modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned Example 1. It should be noted that the above-mentioned modules or units can be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above-mentioned modules can also be part of the device and can be run in the computer terminal 10 provided in Example 1.

[0143] Example 3

[0144] An embodiment of the present application may provide an electronic device, Figure 5 This is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 5 As shown, the electronic device may include: one or more ( Figure 5 Only one is shown) processor 1002, memory 1004, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0145] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, implementing the above-mentioned method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network and a combination thereof.

[0146] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: obtain the seal image whose authenticity is to be verified; use the non-subsampled contourlet transform method to perform image decomposition processing on the seal image to obtain multiple sub-band images; use the gray level co-occurrence matrix method to perform feature extraction processing on the multiple sub-band images to obtain image features of the seal image; use the gray correlation cluster analysis method to calculate the absolute correlation between the image features of the seal image and the image features of the reference seal image, and determine the verification result based on the absolute correlation, wherein the verification result is used to characterize whether the seal image is authentic.

[0147] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: obtaining the seal image to be verified for authenticity; using the non-subsampled contourlet transform method to perform image decomposition processing on the seal image to obtain multiple sub-band images; using the gray level co-occurrence matrix method to perform feature extraction processing on the multiple sub-band images to obtain the image features of the seal image; using the gray correlation cluster analysis method to calculate the absolute correlation between the image features of the seal image and the image features of the reference seal image, and determining the verification result based on the absolute correlation, wherein the verification result is used to characterize whether the seal image is authentic.

[0148] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: for each sub-band image, determine the gray level co-occurrence matrix of the sub-band image under the parameter combination according to the gray level co-occurrence matrix method; determine the parameter value of the sub-band image under multiple texture feature parameters according to the gray level co-occurrence matrix; determine the image sub-features of the sub-band image under the parameter combination according to the parameter values of the sub-band image under multiple texture feature parameters.

[0149] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: for each texture feature parameter of each sub-band image, determine the target parameter value of the texture feature parameter of the sub-band image based on the parameter value of the texture feature parameter of the sub-band image under at least one parameter combination; determine the target image sub-feature of the sub-band image based on the target parameter values of multiple texture feature parameters of the sub-band image.

[0150] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: standardize the image features of the seal image to obtain a first image feature; standardize the image features of the reference seal image to obtain a second image feature; for each feature component in the first image feature, calculate the relationship coefficient corresponding to the feature component based on the component values of the first image feature and the second image feature on the feature component, wherein the relationship coefficient represents the correlation between the image features of the seal image and the reference seal image on the feature component; determine the absolute correlation between the image features of the seal image and the image features of the reference seal image based on the relationship coefficients corresponding to each feature component.

[0151] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: calculating the component difference between the component values of the first image feature and the second image feature on the feature component; determining the maximum difference and the minimum difference from the component differences corresponding to each feature component; and calculating the relationship coefficient based on the component difference, maximum difference and minimum difference of the feature component.

[0152] The processor can also call the information and application stored in the memory through the transmission device to perform the following steps: when the absolute correlation degree is greater than or equal to a preset value, determine that the verification result represents the seal image as a real seal image; when the absolute correlation degree is less than the preset value, determine that the verification result represents the seal image as a forged seal image.

[0153] In an embodiment of the present application, by obtaining a seal image whose authenticity is to be verified and decomposing it using a non-subsampled contourlet transform method, the multi-level features of the image can be captured. By using a gray-level co-occurrence matrix method to perform feature extraction processing on the multiple sub-band images obtained by decomposition, image features are obtained, thereby achieving effective quantification of the visual characteristics of the seal image. By using a gray correlation cluster analysis method to determine the absolute correlation between the image features of the seal image and the image features of the reference seal image, an effective evaluation of the feature correlation between the seal to be verified and the reference seal is achieved, thereby improving the accuracy of identifying the authenticity of the seal image when determining the verification result based on the absolute correlation.

[0154] It can be seen that the method provided in this embodiment achieves the purpose of using NSCT-GLCM to extract features of the seal image to be verified, and verifying the authenticity of the seal image based on the grey relational cluster analysis method and image features, thereby achieving the technical effect of improving the accuracy of identifying the authenticity of the seal image, and solving the technical problem of low recognition accuracy when identifying the authenticity of the seal image in the related art.

[0155] It can be understood by those skilled in the art that Figure 5 The structure shown is for illustration only, and the electronic device may also be a smart phone, a tablet computer, a PDA, a mobile Internet device (MID), a PAD or other terminal device. Figure 5 It does not limit the structure of the above electronic device. For example, the electronic device may also include Figure 5 More or fewer components (such as network interfaces, display devices, etc.) shown in, or with Figure 5 Different configurations shown.

[0156] A person skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0157] Example 4

[0158] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the image processing method provided in the first embodiment.

[0159] Optionally, in this embodiment, the above-mentioned storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0160] The present application also provides a computer program product, which, when executed on a data processing device, is adapted to perform the steps of the image processing method.

[0161] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0162] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0163] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0164] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0165] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0166] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0167] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. An image processing method, characterized in that: include: Obtaining a seal image to be verified for authenticity; Using a non-subsampled contourlet transform method to perform image decomposition processing on the seal image to obtain a plurality of sub-band images; performing feature extraction processing on the plurality of sub-band images using a gray level co-occurrence matrix method to obtain image features of the seal image; The absolute correlation between the image features of the seal image and the image features of the reference seal image is calculated using a grey correlation cluster analysis method, and a verification result is determined based on the absolute correlation, wherein the verification result is used to characterize whether the seal image is authentic.

2. The method according to claim 1, characterized in that The gray level co-occurrence matrix method is used to perform feature extraction processing on the multiple sub-band images to obtain image features of the seal image, including: Obtaining at least one preset direction value and at least one preset distance value; determining at least one parameter combination based on the at least one direction value and the at least one distance value; For each parameter combination, determining the image sub-features of each sub-band image under the parameter combination according to the gray level co-occurrence matrix method; determining a target image sub-feature of each sub-band image according to an image sub-feature of each sub-band image under at least one parameter combination; The image features of the seal image are determined according to the target image sub-features of the multiple sub-band images.

3. The method according to claim 2, characterized in that Determining the image sub-features of each sub-band image under the parameter combination according to the gray level co-occurrence matrix method includes: For each sub-band image, determining the gray level co-occurrence matrix of the sub-band image under the parameter combination according to the gray level co-occurrence matrix method; Determining parameter values of the sub-band image under multiple texture feature parameters according to the gray level co-occurrence matrix; According to the parameter values of the sub-band image under the plurality of texture feature parameters, the image sub-features of the sub-band image under the parameter combination are determined.

4. The method according to claim 3, characterized in that Determining target image sub-features of each sub-band image according to image sub-features of each sub-band image under at least one parameter combination includes: For each texture feature parameter of each sub-band image, determining a target parameter value of the texture feature parameter of the sub-band image according to a parameter value of the texture feature parameter of the sub-band image under at least one parameter combination; The target image sub-feature of the sub-band image is determined according to the target parameter values of the plurality of texture feature parameters of the sub-band image.

5. The method according to claim 1, wherein The grey correlation cluster analysis method is used to calculate the absolute correlation between the image features of the seal image and the image features of the reference seal image, including: performing standardization processing on the image feature of the seal image to obtain a first image feature; performing standardization processing on the image features of the reference seal image to obtain a second image feature; For each feature component of the first image feature, calculating a correlation coefficient corresponding to the feature component based on component values of the first image feature and the second image feature, wherein the correlation coefficient represents a degree of association between the image features of the seal image and the reference seal image on the feature component; The absolute correlation between the image features of the seal image and the image features of the reference seal image is determined according to the relationship coefficients corresponding to the respective feature components.

6. The method according to claim 5, characterized in that Calculating a relationship coefficient corresponding to the feature component based on component values of the first image feature and the second image feature on the feature component includes: Calculating a component difference between component values of the first image feature and the second image feature on the feature component; Determine the maximum difference and the minimum difference from the component differences corresponding to each characteristic component; The relationship coefficient is calculated based on the component difference of the characteristic component, the maximum difference and the minimum difference.

7. The method according to claim 1, characterized in that Determining a verification result based on the absolute correlation degree includes: In a case where the absolute correlation degree is greater than or equal to a preset value, determining that the verification result indicates that the seal image is a genuine seal image; When the absolute correlation degree is less than the preset value, it is determined that the verification result indicates that the seal image is a forged seal image.

8. An image processing device, characterized in that: include: An acquisition module, used for acquiring a seal image to be verified for authenticity; A first processing module is used for performing image decomposition processing on the seal image by adopting a non-subsampled contourlet transform method to obtain a plurality of sub-band images; A second processing module is used to perform feature extraction processing on the multiple sub-band images using a gray level co-occurrence matrix method to obtain image features of the seal image; The determination module is used to calculate the absolute correlation between the image features of the seal image and the image features of the reference seal image using a grey correlation cluster analysis method, and determine a verification result based on the absolute correlation, wherein the verification result is used to indicate whether the seal image is authentic.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a stored executable program, wherein when the executable program is run, the device where the computer-readable storage medium is located is controlled to execute the image processing method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: a memory storing an executable program; A processor is used to run the program, wherein the program executes the image processing method according to any one of claims 1 to 7 when running.

11. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by a processor, the steps of the image processing method according to any one of claims 1 to 7 are implemented.

Images