Image recognition method, device, equipment and medium

Abstract

The present disclosure provides an image recognition method, which can be applied to the field of artificial intelligence technology. The image recognition method comprises: obtaining information of image features corresponding to a preset frequency band of a to-be-identified fingerprint image; obtaining singular value decomposition information obtained after singular value decomposition is performed on the to-be-identified fingerprint image; inputting the information of the image features, the singular value decomposition information and to-be-identified fingerprint image information into a classification model to output a classification result, wherein the classification result comprises a target classification value of the to-be-identified fingerprint image; and determining an image recognition result according to the classification result, wherein the image recognition result comprises a category of the to-be-identified fingerprint image. The present disclosure also provides an image recognition device, equipment, storage medium and program product.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of artificial intelligence, and in particular, to an image recognition method, device, equipment, medium and program product. BACKGROUND

[0002] Finger has rich features, and fingerprint, as the main biological feature of finger, has several ideal characteristics such as universality, salience, permanence, collectability, acceptability and anti-avoidance. Fingerprint recognition technology is one of the most widely used biometric recognition technologies, and has been widely used in identity authentication, information security, access control and fast payment. The large amount of features contained in the fingerprint image can be used for gender classification.

[0003] However, in the process of implementing the present disclosure, it is found that using traditional algorithms to extract local features of images or manually selecting local features based on artificial methods has the problems of large error and poor generalization ability. SUMMARY

[0004] In view of the above problems, the present disclosure provides an image recognition method, device, equipment, medium and program product.

[0005] According to a first aspect of the present disclosure, an image recognition method is provided, comprising:

[0006] obtaining information of image features corresponding to a preset frequency band of a to-be-identified fingerprint image;

[0007] obtaining singular value decomposition information obtained after singular value decomposition of the to-be-identified fingerprint image;

[0008] inputting the information of image features, the singular value decomposition information and the to-be-identified fingerprint image information into a classification model, and outputting a classification result, wherein the classification result includes a target classification value of the to-be-identified fingerprint image; and

[0009] determining an image recognition result according to the classification result, wherein the image recognition result includes a category of the to-be-identified fingerprint image.

[0010] According to an embodiment of the present disclosure, the information of image features includes a plurality of sub-image information and an energy value matrix after discrete wavelet transform; and the obtaining of the information of image features corresponding to the preset frequency band of the to-be-identified fingerprint image comprises:

[0011] performing discrete wavelet transform on the to-be-identified fingerprint image to obtain a plurality of transformed sub-images;

[0012] using a preset energy value calculation formula to obtain an energy value corresponding to each sub-image in the plurality of transformed sub-images;

[0013] Fill the energy value corresponding to each sub-image into a matrix with the same size as the transformed plurality of sub-images to obtain an energy value matrix.

[0014] According to an embodiment of the present disclosure, obtaining singular value decomposition information obtained after singular value decomposition is performed on the to-be-identified fingerprint image comprises:

[0015] Performing singular value decomposition on the to-be-identified fingerprint image by using a singular value decomposition formula to obtain singular value decomposition information.

[0016] According to an embodiment of the present disclosure, inputting the information of the image features, the singular value decomposition information, and the to-be-identified fingerprint image information into the classification model and outputting a classification result comprises:

[0017] Superimposing the information of the image features, the singular value decomposition information, and the to-be-identified fingerprint image information to obtain superimposed information;

[0018] Inputting the superimposed information into the classification model;

[0019] Outputting the classification result.

[0020] According to an embodiment of the present disclosure, the image features comprise fingerprint ridge related attribute features, wherein the fingerprint ridge related attribute features comprise fingerprint ridge features, fingerprint ridge interval convex features, and fingerprint ridge density features.

[0021] According to an embodiment of the present disclosure, before obtaining the information of the image features corresponding to the preset frequency band of the to-be-identified fingerprint image, the method further comprises:

[0022] Obtaining authorization of a user on the input fingerprint image;

[0023] After obtaining the authorization, obtaining the to-be-identified fingerprint image.

[0024] A second aspect of the present disclosure provides an image recognition device, comprising:

[0025] A first obtaining module is configured to obtain information of image features corresponding to a preset frequency band of a to-be-identified fingerprint image;

[0026] A second obtaining module is configured to obtain singular value decomposition information obtained after singular value decomposition is performed on the to-be-identified fingerprint image;

[0027] A classification module is configured to input the information of the image features, the singular value decomposition information, and to-be-identified fingerprint image information into a classification model and output a classification result, wherein the classification result comprises a target classification value of the to-be-identified fingerprint image; and

[0028] A determination module is configured to determine an image recognition result according to the classification result, wherein the image recognition result comprises a category of the to-be-identified fingerprint image.

[0029] A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors perform the image recognition method described above.

[0030] A fourth aspect of the present disclosure also provides a computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the image recognition method described above.

[0031] A fifth aspect of the present disclosure also provides a computer program product comprising a computer program that, when executed by a processor, implements the image recognition method described above.

[0032] According to embodiments of the present disclosure, by taking the information of the image features screened from the to-be-identified fingerprint image and the singular value decomposition information obtained by singular value decomposition of the to-be-identified fingerprint image as inputs of the classification model, the details and features of the whole image can be separated, avoiding being trapped in local features and ignoring the whole, thereby affecting the model classification result and further affecting the image recognition result. At the same time, the original image to-be-identified fingerprint image information is also taken as an input of the classification model. In addition to using image features, the original image is also taken as part of the model input, so that the model also has a certain perception of the original image, and the model itself can also extract some features from the original image that are difficult to perceive by traditional algorithms, thereby improving the accuracy of the classification model. The influence of artificial or local features on the overall recognition result is eliminated, and the robustness and generalization of the classification model are also improved. BRIEF DESCRIPTION OF DRAWINGS

[0033] The above and other objects, features and advantages of the present disclosure will become more apparent from the following description of embodiments of the present disclosure, taken in conjunction with the accompanying drawings, in which:

[0034] Figure 1 An application scenario diagram of the image recognition method, apparatus, device, medium and program product according to embodiments of the present disclosure is schematically shown;

[0035] Figure 2 A flowchart of the image recognition method according to embodiments of the present disclosure is schematically shown;

[0036] Figure 3 A method flowchart for obtaining information of image features corresponding to a preset frequency band of a to-be-identified fingerprint image according to embodiments of the present disclosure is schematically shown;

[0037] Figure 4 A fingerprint image diagram according to embodiments of the present disclosure is schematically shown;

[0038] FIG. 5(a) schematically illustrates a diagram of a first-order discrete wavelet transform according to an embodiment of the present disclosure;

[0039] FIG. 5(b) schematically illustrates a diagram of a third-order discrete wavelet transform according to an embodiment of the present disclosure;

[0040] FIG. 5(c) schematically illustrates a diagram of a plurality of sub-images after the third-order discrete wavelet transform according to an embodiment of the present disclosure;

[0041] Figure 6 FIG. 5(d) schematically illustrates a diagram of an energy value matrix of an HH1 sub-image after the third-order discrete wavelet transform according to an embodiment of the present disclosure;

[0042] Figure 7 FIG. 6 schematically illustrates a block diagram of an image recognition device according to an embodiment of the present disclosure; and

[0043] Figure 8 FIG. 7 schematically illustrates a block diagram of an electronic device suitable for implementing the image recognition method according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0044] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood, however, that the description which follows is merely exemplary and is not intended to limit the scope of the present disclosure. In the following detailed description of the embodiments of the present disclosure, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. However, it would be apparent to one skilled in the art that the present disclosure can be practiced without these specific details. In other instances, well-known structures and functions have not been described in detail in order to avoid obscuring aspects of the present disclosure.

[0045] The terms used herein are merely used to describe specific embodiments and are not intended to limit the present disclosure. The terms "include", "comprise", and the like used herein indicate the presence of the described features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0046] All terms used herein (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of the present specification, and should not be interpreted in an idealized or overly formal manner.

[0047] In the case of using expressions similar to "at least one of A, B, and C, etc.", it is generally intended to include any of A, B, and C alone, or a combination of A, B, and C, etc. (for example, "a system having at least one of A, B, and C" should include a system having A alone, a system having B alone, a system having C alone, a system having A and B together, a system having A and C together, a system having B and C together, and a system having A, B, and C together, etc.).

[0048] In the technical solutions of the present disclosure, the collection, storage, use, processing, transmission, provision, disclosure, and application of user personal information comply with relevant laws and regulations, necessary security measures are taken, and the public order and good customs are not violated.

[0049] In the technical solutions of the present disclosure, the authorization or consent of the user is obtained before the user's personal information is acquired or collected.

[0050] The gender detection of the fingerprint can use a traditional CV algorithm to binarize the input image, calculate preset fingerprint features such as the density of several features (ridges, line thickness, or fingerprint missing caused by scars, etc.) in the fingerprint picture, and then compare them with a threshold value (calculated based on past samples) to determine the gender. However, this method of gender detection of the fingerprint is more dependent on the quality of the input image, and the quality of the fingerprint image generated by different fingerprint scanners will affect the determination of the feature density, and will also produce errors due to changes in the environment (such as sweating, recent finger injury, dirty scanner, etc.).

[0051] The gender detection of the fingerprint can also be achieved by manually selecting local features (fingerprint center, fingerprint edge, and special shape fingerprint, etc.) and then directly comparing the original features left in the fingerprint library through machine learning / deep learning. However, it needs to rely on manual selection and cutting of the fingerprint, which is time-consuming and labor-intensive.

[0052] Embodiments of the present disclosure provide an image recognition method, comprising: acquiring information of image features corresponding to a preset frequency band of a to-be-recognized fingerprint image; acquiring singular value decomposition information obtained by performing singular value decomposition on the to-be-recognized fingerprint image; inputting the information of the image features, the singular value decomposition information, and to-be-recognized fingerprint image information into a classification model to output a classification result, wherein the classification result comprises a target classification value of the to-be-recognized fingerprint image; and determining an image recognition result according to the classification result, wherein the image recognition result comprises a category of the to-be-recognized fingerprint image.

[0053] Figure 1 An application scenario diagram of the image recognition method, apparatus, device, medium, and program product according to an embodiment of the present disclosure is schematically shown.

[0054] As Figure 1As shown, the application scenario 100 according to this embodiment can include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is a medium for providing a communication link between the terminal devices 101, 102, 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links, or fiber optic cables, and the like.

[0055] A user can use the terminal devices 101, 102, 103 to interact with the server 105 through the network 104 to receive or send messages, and the like. Various communication client applications can be installed on the terminal devices 101, 102, 103, such as financial product applications, shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, and the like (only as examples).

[0056] The terminal devices 101, 102, 103 can be various electronic devices with display screens and support for web browsing, including but not limited to smartphones, tablet computers, laptop computers, desktop computers, and the like.

[0057] The server 105 can be a server that provides various services, such as a background management server that provides support for websites browsed by users using the terminal devices 101, 102, 103 (only as an example). The background management server can analyze and process received user requests and the like, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests, and the like) to the terminal devices.

[0058] It should be noted that the image recognition method provided by the embodiments of the present disclosure can generally be executed by the server 105. Accordingly, the image recognition apparatus provided by the embodiments of the present disclosure can generally be disposed in the server 105. The image recognition method provided by the embodiments of the present disclosure can also be executed by a server or a server cluster different from the server 105 and capable of communicating with the terminal devices 101, 102, 103 and / or the server 105. Accordingly, the image recognition apparatus provided by the embodiments of the present disclosure can also be disposed in a server or a server cluster different from the server 105 and capable of communicating with the terminal devices 101, 102, 103 and / or the server 105.

[0059] The image recognition method provided by the embodiments of the present disclosure can also be executed by the terminal device 101, 102, 103. Accordingly, the image recognition apparatus provided by the embodiments of the present disclosure can also be arranged in the terminal device 101, 102, 103. The image recognition method provided by the embodiments of the present disclosure can also be executed by other terminals different from the terminal device 101, 102, 103. Accordingly, the image recognition apparatus provided by the embodiments of the present disclosure can also be arranged in other terminals different from the terminal device 101, 102, 103. It should be understood that, Figure 1 The number of terminal devices, networks and servers in the above scenario is only illustrative. Any number of terminal devices, networks and servers can be provided according to the implementation needs.

[0060] The image recognition method of the embodiments of the present disclosure will be described in detail below based on the scenario described above. Figure 1 Figures 2 to 6 The image recognition method of the embodiments of the present disclosure will be described in detail below based on the scenario described above.

[0061] Figure 2 A flowchart of the image recognition method according to the embodiments of the present disclosure is schematically shown.

[0062] As shown in Figure 2 , the image recognition method 200 of this embodiment includes operation S201 to operation S204.

[0063] In operation S201, information of image features corresponding to a preset frequency band of a to-be-identified fingerprint image is acquired.

[0064] According to the embodiments of the present disclosure, the to-be-identified fingerprint image can be a fingerprint image of a user acquired after the user is authorized to input the fingerprint image. The information of image features corresponding to the preset frequency band can be high-frequency image feature information of the fingerprint image; wherein the high-frequency image feature information can be fingerprint ridge related attribute feature information, for example, can be fingerprint ridge, convex part between fingerprint ridges, fingerprint ridge density and other related attribute feature information. The preset frequency band can be obtained by discrete wavelet transform. For example, n-order discrete wavelet transform can obtain n high-frequency features and multiple low-frequency features containing high frequencies; wherein n is a positive integer. The high-frequency features can be fingerprint ridges, convex parts between fingerprint ridges, fingerprint ridge densities, etc. The low-frequency features can be the remaining features after separating the high-frequency features.

[0065] In operation S202, singular value decomposition information obtained after singular value decomposition is performed on the to-be-identified fingerprint image is acquired.

[0066] ​According to an embodiment of the present disclosure, performing singular value decomposition can be to obtain singular value decomposition information by singular value decomposition on the binarized to-be-recognized fingerprint image. The singular value decomposition information can be a plurality of different matrices. The singular value decomposition can denoise interference information in the to-be-recognized fingerprint image information, and obtain a plurality of different matrices without interference information after feature extraction and decomposition.

[0067] In operation S203, the information of the image features, the singular value decomposition information, and the to-be-recognized fingerprint image information are input into the classification model, and a classification result is output, where the classification result includes a target classification value of the to-be-recognized fingerprint image.

[0068] According to an embodiment of the present disclosure, the classification model can be a binary classification model, and the classification algorithm of the classification model is not limited. The classification model can be a model for image recognition trained by taking the information of the image features corresponding to the preset frequency band of the to-be-trained fingerprint image, the singular value decomposition information obtained by singular value decomposition on the to-be-trained fingerprint image, and the to-be-trained fingerprint image information as input. The target classification value of the to-be-recognized fingerprint image can be a numerical value such as 0 or 1. It can also be a gender detection probability value corresponding to the to-be-recognized fingerprint image.

[0069] For example, the information of the image features such as the fingerprint lines, the convex parts between the fingerprint lines, the fingerprint line density, and the singular value decomposition information of the plurality of different matrices, and the to-be-recognized fingerprint image information are input into the classification model, and a classification result of 0 or 1 is output.

[0070] In operation S204, an image recognition result is determined according to the classification result, where the image recognition result includes a category of the to-be-recognized fingerprint image.

[0071] According to an embodiment of the present disclosure, the image recognition result can be a gender detection result corresponding to the fingerprint image. The image recognition result can be determined according to the output classification result of the pre-defined classification model.

[0072] For example, the classification result of 0 is defined as female, and the classification result of 1 is defined as male. If the output is 0, the image recognition result is female; if the output is 1, the image recognition result is male. The classification result can also be a probability of gender detection corresponding to the to-be-recognized fingerprint image, and the gender can be determined according to a threshold value. The threshold value can be determined according to the actually used classification model.

[0073] According to an embodiment of the present disclosure, by taking the information of the image features screened from the to-be-identified fingerprint image and the singular value decomposition information obtained by singular value decomposition of the to-be-identified fingerprint image as the input of the classification model, the details and features of the image as a whole are separated. The model classification result is affected by avoiding falling into local features and ignoring the whole, and then the image recognition result is affected. At the same time, the original image to-be-identified fingerprint image information is also taken as the input of the classification model. In addition to using image features, the original image is also part of the model input, so that the model also has a certain perception of the original image, and the model itself can also extract some features that are difficult to perceive by traditional algorithms from the original image, thereby improving the accuracy of the classification model. The influence of artificial or local features on the overall recognition result is eliminated, and the robustness and generalization of the classification model are also improved.

[0074] The following will be described in detail in combination with Figures 3 to 6 The method for obtaining the information of the image features corresponding to the preset frequency band of the to-be-identified fingerprint image according to the embodiment of the present disclosure will be described in detail.

[0075] Figure 3 The method flowchart for obtaining the information of the image features corresponding to the preset frequency band of the to-be-identified fingerprint image according to the embodiment of the present disclosure is schematically shown; Figure 4 The fingerprint image schematic diagram according to the embodiment of the present disclosure is schematically shown. FIG. 5(a) schematically shows a first-order discrete wavelet transform schematic diagram according to the embodiment of the present disclosure. FIG. 5(b) schematically shows a third-order discrete wavelet transform schematic diagram according to the embodiment of the present disclosure. FIG. 5(c) schematically shows a plurality of sub-images after third-order discrete wavelet transform according to the embodiment of the present disclosure; Figure 6 The energy value matrix schematic diagram of the HH1 sub-image after third-order discrete wavelet transform according to the embodiment of the present disclosure is schematically shown.

[0076] As Figure 3 The method 300 for obtaining the information of the image features corresponding to the preset frequency band of the to-be-identified fingerprint image according to the embodiment includes operations S301-S303.

[0077] In operation S301, the to-be-identified fingerprint image is subjected to discrete wavelet transform to obtain a plurality of sub-images after transformation.

[0078] According to the embodiment of the present disclosure, the to-be-identified fingerprint image can be a picture generated after being scanned by a fingerprint machine. The discrete wavelet transform can refer to extracting high frequency (H) and low frequency (L) parts of the image in the X-axis direction and the Y-axis direction, respectively. The so-called high frequency can refer to the detail part corresponding to the high frequency image feature information in the image, and the low frequency can refer to the overall feature of the image. The discrete wavelet transform can be, but is not limited to, first-order discrete wavelet transform, second-order discrete wavelet transform, and third-order discrete wavelet transform. Preferably, the third-order discrete wavelet transform. Continuously extracting as much high frequency feature information as possible from the to-be-identified fingerprint image can improve the model accuracy.

[0079] For example, the bank can obtain a high-resolution fingerprint image through the authorization of the user, as shown in FIG. 1. Figure 4 The first-order discrete wavelet transform of the to-be-identified fingerprint image can be X-axis direction and Y-axis direction decomposition of the to-be-identified fingerprint image, and four sub-images LL1, LH1, HL1, and HH1 can be obtained, as shown in FIG. 5(a). The second-order discrete wavelet transform of the to-be-identified fingerprint image can be the decomposition of the LL1 part into new LL2, LH2, HL2, and HH2 on the basis of the first-order discrete wavelet transform. The third-order discrete wavelet transform of the to-be-identified fingerprint image can obtain 10 sub-images after the third-order discrete wavelet transform, as shown in FIG. 5(b), and the 10 sub-images after the third-order discrete wavelet transform are shown in FIG. 5(c).

[0080] In operation S302, a preset energy value calculation formula is used to obtain an energy value corresponding to each sub-image in the plurality of sub-images after the transformation.

[0081] According to the embodiment of the present disclosure, the preset energy value calculation formula can be formula (1):

[0082]

[0083] wherein k refers to the transformed mark, such as LL2, LH2; W refers to the width of the transformed image; H refers to the height of the transformed image; X k (i,j) refers to the value corresponding to the point (i,j) in the image.

[0084] For example, the 10 sub-images after the third-order discrete wavelet transform shown in FIG. 5(c) can obtain 10 energy values by using the above formula (1).

[0085] In operation S303, the energy value corresponding to each sub-image is filled into a matrix with the same size as the plurality of sub-images after the transformation, to obtain an energy value matrix.

[0086] According to the embodiment of the present disclosure, the matrix with the same size as the image can refer to an image with the same width and height.

[0087] For example, as shown in FIG. 5(b) and FIG. 5(c), the energy value matrix of the HH1 sub-image after the third-order discrete wavelet transform can be as shown in FIG. 5(b) and FIG. 5(c). Figure 6

[0088] According to the embodiments of the present disclosure, the plurality of sub-image information and the energy value matrix after the discrete wavelet transform are screened from the to-be-identified fingerprint image by the discrete wavelet transform, and the precision of image recognition can be improved by extracting the high-frequency corresponding features of the fingerprint image.

[0089] According to some other embodiments of the present disclosure, the singular value decomposition information obtained by performing singular value decomposition on the to-be-identified fingerprint image includes:

[0090] The singular value decomposition information is obtained by performing singular value decomposition on the to-be-identified fingerprint image by using the singular value decomposition formula.

[0091] According to the embodiments of the present disclosure, the to-be-identified fingerprint image after binarization can be decomposed by using the singular value decomposition formula, and the singular value decomposition formula (2) can be:

[0092] A=USV T , S=A T , V=A T (2)

[0093] wherein, A represents the matrix corresponding to the to-be-identified fingerprint image after binarization; T represents the matrix transposition; S represents the singular value of A; V and U represent the singular vector of A; V=A T A.

[0094] According to the embodiments of the present disclosure, the image features are obtained by using the singular value decomposition formula, which is beneficial to the noise reduction of the image and improves the precision of image recognition.

[0095] According to the embodiments of the present disclosure, the information of the image features, the singular value decomposition information, and the to-be-identified fingerprint image information are input into the classification model, and the classification result is output, which includes:

[0096] The information of the image features, the singular value decomposition information, and the to-be-identified fingerprint image information are superimposed to obtain superimposed information.

[0097] The superimposed information is input into the classification model.

[0098] The classification result is output.

[0099] ​According to an embodiment of the present disclosure, the information of the image features can include a plurality of sub-image information and an energy value matrix after discrete wavelet transform. Superimposing the information of the image features, the singular value decomposition information, and the to-be-identified fingerprint image information can be superimposing the plurality of sub-image information and the energy value matrix after the discrete wavelet transform in a vertical direction first, and then sequentially superimposing the singular value decomposition information and the to-be-identified fingerprint image information in the vertical direction to obtain superimposed information. The superimposed information can be all information fused from the information of the image features, the singular value decomposition information, and the to-be-identified fingerprint image information. The classification model can be a convolutional neural network model, and the classification algorithm is not specifically limited in the embodiment of the present disclosure. The classification result can be a probability of gender detection corresponding to the to-be-identified fingerprint image.

[0100] According to an embodiment of the present disclosure, by superimposing the high-frequency image feature information, the singular value decomposition information, and the to-be-identified fingerprint image information as the input of the model, the feature information is increased, the influence of artificial or local features on the overall recognition result is eliminated, and the robustness and generalization of the classification model are improved.

[0101] According to an embodiment of the present disclosure, the image features include fingerprint ridge related attribute features.

[0102] According to an embodiment of the present disclosure, the fingerprint ridge related attribute features can include fingerprint ridges, convex parts between fingerprint ridges, fingerprint ridge density, and the like.

[0103] According to an embodiment of the present disclosure, by acquiring the fingerprint ridge related attribute features and the overall features of the fingerprint image, image recognition is performed. For example, the method can be applied to help a bank determine whether there is a proxy when a user needs to perform fingerprint verification during a service.

[0104] According to an embodiment of the present disclosure, the image recognition method further includes:

[0105] obtaining authorization of a user on the input fingerprint image;

[0106] obtaining a to-be-identified fingerprint image after obtaining the authorization.

[0107] Based on the above image recognition method, the present disclosure further provides an image recognition device. The following will be described in combination with Figure 7 The image recognition device is described in detail.

[0108] Figure 7 A structural block diagram of an image recognition device according to an embodiment of the present disclosure is schematically shown.

[0109] As Figure 7 shown, the image recognition device 700 of the embodiment includes a first obtaining module 710, a second obtaining module 720, a classification module 730, and a determination module 740.

[0110] The first obtaining module 710 is configured to obtain information of image features corresponding to a preset frequency band of a to-be-identified fingerprint image. In an embodiment, the first obtaining module 710 can be configured to perform operation S201 described above, and details are not repeated here.

[0111] The second obtaining module 720 is configured to obtain singular value decomposition information obtained after singular value decomposition of the to-be-identified fingerprint image. In an embodiment, the second obtaining module 720 can be configured to perform operation S202 described above, and details are not repeated here.

[0112] The classification module 730 is configured to input the information of image features, the singular value decomposition information, and the to-be-identified fingerprint image information into a classification model, and output a classification result, wherein the classification result includes a target classification value of the to-be-identified fingerprint image. In an embodiment, the classification module 730 can be configured to perform operation S203 described above, and details are not repeated here.

[0113] The determination module 740 is configured to determine an image recognition result according to the classification result, wherein the image recognition result includes a category of the to-be-identified fingerprint image. In an embodiment, the determination module 740 can be configured to perform operation S204 described above, and details are not repeated here.

[0114] According to an embodiment of the present disclosure, the first obtaining module 710 includes a first obtaining subunit, a second obtaining subunit, and a third obtaining subunit.

[0115] The first obtaining subunit is configured to perform discrete wavelet transform on the to-be-identified fingerprint image to obtain a plurality of transformed sub-images.

[0116] The second obtaining subunit is configured to obtain an energy value corresponding to each of the plurality of transformed sub-images by using a preset energy value calculation formula.

[0117] The third obtaining subunit is configured to fill the energy value corresponding to each of the sub-images into a matrix with the same size as the plurality of transformed sub-images to obtain an energy value matrix.

[0118] According to an embodiment of the present disclosure, the classification module 730 includes a superimposed information unit, an input unit, and an output unit.

[0119] The superimposed information unit is configured to superimpose the information of image features, the singular value decomposition information, and the to-be-identified fingerprint image information to obtain superimposed information.

[0120] The input unit is configured to input the superimposed information into the classification model.

[0121] The output unit is configured to output the classification result.

[0122] According to an embodiment of the present disclosure, any of the first obtaining module 710, the second obtaining module 720, the classifying module 730 and the determining module 740 can be combined in one module, or any of them can be split into multiple modules. Alternatively, at least part of the function of one or more of these modules can be combined with at least part of the function of other modules, and implemented in one module. According to an embodiment of the present disclosure, at least one of the first obtaining module 710, the second obtaining module 720, the classifying module 730 and the determining module 740 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on board, a system on package, an application specific integrated circuit (ASIC), or any other reasonable way of hardware or firmware that can be integrated or packaged with a circuit, or implemented in any one of software, hardware and firmware or in a proper combination of any of them. Alternatively, at least one of the first obtaining module 710, the second obtaining module 720, the classifying module 730 and the determining module 740 can be at least partially implemented as a computer program module that can perform corresponding functions when it is run.

[0123] Figure 8 A block diagram of an electronic device suitable for implementing the image recognition method according to an embodiment of the present disclosure is schematically shown.

[0124] As shown in Figure 8 The electronic device 800 according to an embodiment of the present disclosure includes a processor 801 that can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 802 or loaded into a random access memory (RAM) 803 from a storage portion 908. The processor 801 can include, for example, a general-purpose microprocessor (such as a CPU), an instruction set processor and / or a related chipset, and / or a special-purpose microprocessor (such as an application specific integrated circuit (ASIC)), and the like. The processor 801 can also include an on-board memory for cache use. The processor 801 can include a single processing unit or a plurality of processing units for performing different actions of the method processes according to an embodiment of the present disclosure.

[0125] In the RAM 803, various programs and data required for the operation of the electronic device 800 are stored. The processor 801, the ROM 802, and the RAM 803 are connected to each other via the bus 804. The processor 801 performs various operations of the method flow according to the embodiments of the present disclosure by executing the programs in the ROM 802 and / or the RAM 803. It should be noted that the programs can also be stored in one or more memories other than the ROM 802 and the RAM 803. The processor 801 can also perform various operations of the method flow according to the embodiments of the present disclosure by executing the programs stored in the one or more memories.

[0126] According to an embodiment of the present disclosure, the electronic device 800 can further include an input / output (I / O) interface 805, which is also connected to the bus 804. The electronic device 800 can further include one or more of the following components connected to the I / O interface 805: an input part 806 including a keyboard, a mouse, etc.; an output part 807 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage part 808 including a hard disk, etc.; and a communication part 809 including a network interface card such as a LAN card, a modem, etc. The communication part 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the I / O interface 805 as necessary. A removable medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is mounted on the drive 810 as necessary, so that a computer program read out therefrom is installed in the storage part 808 as necessary.

[0127] The present disclosure also provides a computer readable storage medium, which can be included in the device / apparatus / system described in the above embodiments; or can exist separately without being assembled into the device / apparatus / system. The above computer readable storage medium carries one or more programs, when the one or more programs are executed, the method according to the embodiments of the present disclosure is implemented.

[0128] According to an embodiment of the present disclosure, the computer readable storage medium can be a nonvolatile computer readable storage medium, for example, can include, but is not limited to, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any appropriate combination thereof. In the present disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present disclosure, the computer readable storage medium can include the ROM 802 and / or the RAM 803 described above and / or one or more memory other than the ROM 802 and the RAM 803.

[0129] Embodiments of the present disclosure also include a computer program product, which includes a computer program containing program codes for executing the methods shown in the flowcharts. When the computer program product is run in a computer system, the program codes are used to make the computer system implement the image recognition method provided by the embodiments of the present disclosure.

[0130] The above-described functions defined in the system / device / apparatus of the embodiments of the present disclosure are performed when the computer program is executed by the processor 801. According to an embodiment of the present disclosure, the system, device, module, unit, etc. described above can be implemented by computer program modules.

[0131] In one embodiment, the computer program can rely on a tangible storage medium such as an optical storage device, a magnetic storage device, etc. In another embodiment, the computer program can also be transmitted, distributed, and downloaded in the form of a signal on a network medium and installed and downloaded through the communication part 809 and / or installed from the detachable medium 811. The program codes contained in the computer program can be transmitted by any appropriate network medium, including but not limited to wireless, wired, etc., or any appropriate combination thereof.

[0132] In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 809 and / or installed from the detachable medium 811. When the computer program is executed by the processor 801, the above-described functions defined in the system of the embodiments of the present disclosure are performed. According to an embodiment of the present disclosure, the system, device, apparatus, module, unit, etc. described above can be implemented by computer program modules.

[0133] According to embodiments of the present disclosure, program code of the computer program for performing the methods provided by the embodiments of the present disclosure can be written in any combination of one or more programming languages, and can be implemented in a computer program product. Specifically, the computer program can be implemented in a high-level procedural and / or object-oriented programming language, and / or in assembly / machine language. The programming language includes, but is not limited to, Java, C++, python, “C” language, or similar programming languages. The program code can execute entirely on the user's computing device, partly on the user's device, and partly on a remote computing device, or entirely on the remote computing device or server. In the latter scenario, the remote computing device can be connected to the user's computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computing device, such as through the Internet using an Internet Service Provider (ISP).

[0134] The computer program product of the present disclosure can be a computer program product, which is a machine-readable medium (or computer readable medium) having stored therein a sequence of instructions executable by a machine such as a personal digital assistant (PDA), a laptop, a desktop computer, or a server. Alternatively, the computer program product can be a propagated signal per se generated by using the program code, and the program code can be stored on a machine-readable medium that can be read by a machine such as a personal digital assistant (PDA), a laptop, a desktop computer, or a server. The program code of the computer program product defines a function, preferably a corresponding action, and / or implements the elements / object / means for performing this function or a part thereof as disclosed in the embodiments of the present disclosure. The program code can be executed by using one or more processors.

[0135] Those skilled in the art will understand that features of the various embodiments and / or claims of the present disclosure can be combined or / and integrated with one another, even though such a combination or integration is not expressly disclosed in the present disclosure. In particular, the features of the various embodiments and / or claims of the present disclosure can be combined or / and integrated with one another in any combination, without departing from the spirit and teachings of the present disclosure. All such combinations and / or integrations are within the scope of the present disclosure.

[0136] The above describes embodiments of the present disclosure. However, these embodiments are merely for illustrative purposes, and are not intended to limit the scope of the present disclosure. Although each embodiment is described above separately, this does not mean that the measures in each embodiment cannot be used advantageously in combination. The scope of the present disclosure is defined by the appended claims and their equivalents. Those skilled in the art can make various substitutions and modifications without departing from the scope of the present disclosure, and these substitutions and modifications should all fall within the scope of the present disclosure.

Claims

1. An image recognition method, comprising: Acquire information of image features corresponding to a preset frequency band of a fingerprint image to be identified, wherein the image feature information includes information of multiple sub-images after discrete wavelet transformation and an energy value matrix; Obtaining singular value decomposition information obtained by performing singular value decomposition on the fingerprint image to be identified; Vertically superimposing the plurality of sub-image information after discrete wavelet transformation and the energy value matrix, and then sequentially superimposing them vertically with the singular value decomposition information and the fingerprint image information to be identified to obtain superimposed information; Inputting the superimposed information into a classification model and outputting a classification result, wherein the classification result includes a target classification value of the fingerprint image to be identified; and An image recognition result is determined according to the classification result, wherein the image recognition result includes the category of the fingerprint image to be recognized.

2. The method according to claim 1, wherein The information of the image features includes information of multiple sub-images after discrete wavelet transformation and an energy value matrix; the information of the image features corresponding to the preset frequency band of the fingerprint image to be identified includes: Performing the discrete wavelet transform on the fingerprint image to be identified to obtain the multiple transformed sub-images; Obtaining an energy value corresponding to each of the plurality of sub-images after the transformation using a preset energy value calculation formula; Fill the energy value corresponding to each of the sub-images into a matrix having the same size as the multiple sub-images after the transformation to obtain the energy value matrix.

3. The method according to claim 1, wherein The acquiring of singular value decomposition information obtained by performing singular value decomposition on the fingerprint image to be identified includes: The singular value decomposition formula is used to perform the singular value decomposition on the fingerprint image to be identified to obtain the singular value decomposition information.

4. The method according to claim 1, wherein The image features include fingerprint pattern-related attribute features, wherein the fingerprint pattern-related attribute features include: fingerprint patterns, convex areas between fingerprint patterns, and fingerprint pattern density.

5. The method according to claim 1, further comprising, before obtaining information of image features of the fingerprint image to be identified corresponding to a preset frequency band: Obtain the user's authorization to enter the fingerprint image; After obtaining the authorization, the fingerprint image to be identified is obtained.

6. An image recognition device comprising: A first acquisition module is used to obtain image feature information corresponding to a preset frequency band of a fingerprint image to be identified, wherein the image feature information includes a plurality of sub-image information and an energy value matrix after discrete wavelet transformation; A second acquisition module is used to obtain singular value decomposition information obtained by performing singular value decomposition on the fingerprint image to be identified; a classification module, configured to input the image feature information, the singular value decomposition information, and the fingerprint image information to be identified into a classification model, and output a classification result, wherein the classification result includes a target classification value of the fingerprint image to be identified; and a determination module, configured to determine an image recognition result based on the classification result, wherein the image recognition result includes the category of the fingerprint image to be identified; The classification module specifically performs the following operations: Vertically superimposing the plurality of sub-image information after discrete wavelet transformation and the energy value matrix, and then sequentially superimposing them vertically with the singular value decomposition information and the fingerprint image information to be identified to obtain superimposed information; The superimposed information is input into a classification model, and a classification result is output.

7. An electronic device comprising: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors are enabled to execute the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, causes the processor to perform the method according to any one of claims 1 to 5.

9. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images