Biological recognition method and device based on local coding, equipment and medium

Abstract

The invention relates to the technical field of biological recognition, and relates to a biological recognition method and device based on local coding, equipment and a medium, the method comprises the steps that first information and second information are acquired, the first information comprises a finger vein image of a target object, and the second information comprises a palmprint image of the target object; respectively preprocessing the first information and the second information to obtain first image information and second image information; feature extraction is carried out on the first image information and the second image information through a local coding method, a first feature vector and a second feature vector are obtained, the first feature vector comprises finger vein local coding features, and the second feature vector comprises palm print image local coding features; the target object is recognized according to the first feature vector and the second feature vector, the implementation process of multi-modal biological recognition is effectively simplified, and the recognition efficiency is improved while the recognition precision is ensured.

Description

Technical Field

[0001] The present invention relates to the field of biometric identification technology, and in particular to a biometric identification method, device, equipment and medium based on local coding. Background Art

[0002] Multimodal biometrics technology combines multiple biometric features to achieve more efficient identity authentication. This technology can not only deal with the situation where a single feature information is lost or forged, but also improve the stability and robustness of recognition based on the complementarity of different feature information. However, multimodal biometrics technology collects more data, so its implementation process is more complicated and the recognition efficiency is low. Summary of the invention

[0003] The object of the present invention is to provide a biometric identification method, device, equipment and medium based on local coding to improve the above-mentioned problems.

[0004] In order to achieve the above objectives, the present application provides the following technical solutions:

[0005] On the one hand, an embodiment of the present application provides a biometric identification method based on local encoding, the method comprising:

[0006] Acquire first information and second information, wherein the first information includes a finger vein image of the target object, and the second information includes a palm print image of the target object;

[0007] Preprocessing the first information and the second information respectively to obtain first image information and second image information;

[0008] Using a local coding method to extract features from the first image information and the second image information respectively, to obtain a first feature vector and a second feature vector, wherein the first feature vector includes a finger vein local coding feature, and the second feature vector includes a palm print image local coding feature;

[0009] The target object is identified according to the first feature vector and the second feature vector.

[0010] In a second aspect, an embodiment of the present application provides a biometric recognition device based on local coding, the device comprising:

[0011] An acquisition module, configured to acquire first information and second information, wherein the first information includes a finger vein image of a target object, and the second information includes a palm print image of the target object;

[0012] A preprocessing module, used to preprocess the first information and the second information respectively to obtain first image information and second image information;

[0013] A feature extraction module, configured to extract features from the first image information and the second image information respectively by using a local coding method to obtain a first feature vector and a second feature vector, wherein the first feature vector includes a finger vein local coding feature, and the second feature vector includes a palm print image local coding feature;

[0014] A recognition module is used to recognize the target object according to the first feature vector and the second feature vector.

[0015] In a third aspect, an embodiment of the present application provides a biometric identification device based on local coding, the device comprising a memory and a processor. The memory is used to store a computer program; the processor is used to implement the steps of the above-mentioned biometric identification method based on local coding when executing the computer program.

[0016] In a fourth aspect, an embodiment of the present application provides a readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the above-mentioned biometric recognition method based on local coding are implemented.

[0017] The beneficial effects of the present invention are:

[0018] The present invention preprocesses the finger vein image and palm print image of the target object to obtain the first image information and the second image information for subsequent use, and then uses the local coding method to extract features from the acquired two modal biological images, which can effectively improve the efficiency of feature extraction while ensuring recognition accuracy. At the same time, since palm print images and finger vein images are both texture features, compared with other multimodal biometric recognition systems, there is no need to design specific feature extraction algorithms for different biological features, which simplifies the design and implementation of the system.

[0019] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 Schematic diagram of the process of the biometric identification method based on local coding described in an embodiment of the present invention.

[0022] Figure 2 Schematic diagram of the structure of a biometric recognition device based on local coding described in an embodiment of the present invention.

[0023] Figure 3 It is a schematic diagram of the structure of a biometric identification device based on local coding described in an embodiment of the present invention.

[0024] Labels in the figure: 901, acquisition module; 902, preprocessing module; 903, feature extraction module; 904, recognition module; 9021, first processing unit; 9022, second processing unit; 9023, enhancement unit; 9031, filling unit; 9032, seventh processing unit; 9033, eighth processing unit; 9034, ninth processing unit; 90221, third processing unit; 90222, fourth processing unit; 90223, fifth processing unit; 90224, sixth processing unit; 90311, traversal unit; 90312, judgment unit; 90313, sub-judgment unit; 90341, acquisition unit; 90342, tenth processing unit; 90343, eleventh processing unit; 800, biometric identification device based on local coding; 801, processor; 802, memory; 803, multimedia component; 804, I / O interface; 805, communication component. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0026] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0027] Embodiment 1:

[0028] This embodiment provides a biometric identification method based on local coding. It can be understood that a scene can be set up in this embodiment, for example: a scene for identifying the identity of a target object.

[0029] See also Figure 1 , the figure shows that the method includes step S1, step S2, step S3 and step S4.

[0030] Step S1, obtaining first information and second information, wherein the first information includes a finger vein image of a target object, and the second information includes a palm print image of the target object;

[0031] In this step, a dedicated biometric feature acquisition device is used to acquire a finger vein image and a palm print image of the target object.

[0032] Step S2, preprocessing the first information and the second information respectively to obtain first image information and second image information;

[0033] The step S2 also includes step S21, step S22 and step S23, which specifically include:

[0034] Step S21, filtering the finger vein image of the target object using a Gaussian filter to obtain filtered image information;

[0035] In this step, the finger vein image of the target object is processed using a Gaussian filter to reduce image noise and smooth the image.

[0036] Step S22, extracting the region of interest from the filtered image information to obtain image information of the region of interest;

[0037] In this step, the region of interest in the filtered image information is extracted to remove redundant background, reduce the amount of calculation, and improve recognition efficiency.

[0038] The step S22 also includes step S221, step S222, step S223 and step S224, which specifically include:

[0039] Step S221, segmenting the image using a linear iterative clustering method, extracting the superpixel boundary and the boundary detected by the Sobel operator respectively, and obtaining a finger boundary image;

[0040] In this step, the finger boundary image is obtained to provide a data basis for finger tilt detection and correction.

[0041] Step S222, calculating the finger midline in the finger boundary image;

[0042] In this step, in the finger boundary image, for the detected finger boundary, the column mean of the two boundary points in the same row is the center point of the finger boundary in that row, and a linear fitting method is used to fit all the calculated center points into a straight line, which is the finger midline.

[0043] Step S223, calculating the inclination angle of the finger boundary image according to the finger midline, and correcting the finger boundary image according to the inclination angle to obtain corrected image information;

[0044] In this step, when the difference between the maximum number of columns and the minimum number of columns corresponding to the points on the midline of the finger is less than 15 pixels, there is no need to correct the finger boundary image.

[0045] Step S224: determine the width of the region of interest in the corrected image information according to the inward tangent line of the finger boundary, and obtain image information of the region of interest.

[0046] Step S23: Enhance the image information of the region of interest to obtain first image information.

[0047] It should be noted that in this step, the method for enhancing the image information of the region of interest is not limited.

[0048] Step S3, using a local coding method to extract features from the first image information and the second image information respectively, to obtain a first feature vector and a second feature vector, wherein the first feature vector includes a finger vein local coding feature, and the second feature vector includes a palm print image local coding feature;

[0049] The step S3 also includes step S31, step S32, step S33 and step S34, which specifically include:

[0050] Step S31, filling the first image information to obtain filled image information;

[0051] The step S31 also includes step S311, step S312 and step S313, which specifically include:

[0052] Step S311, traverse each row and each column in the first image information to obtain row number information and column number information of the first image information;

[0053] Step S312, determining whether the row number information or column number information of the first image information is a multiple of 2, and obtaining a determination result;

[0054] Step S313: When the judgment result is that the row number information or column number information of the first image information is not a multiple of 2, the bottom or rightmost side of the first image information is filled with zeros.

[0055] In this embodiment, the first image information is recorded as an M×N matrix, where M and N are the number of rows and columns of the matrix respectively. Since the image needs to be divided into sub-images of size 2×2, in order to ensure that all blocks are of the same size and the edge of the image is not missed, the sizes of M and N are adjusted to multiples of 2 so that the entire image can be evenly divided and processed, thereby avoiding missing texture features at the boundary and improving detection accuracy.

[0056] Step S32: Slide the first sliding window on the filled image information, calculate the average value under each first sliding window, and obtain the third image information;

[0057] Step S33, dividing the third image information to obtain fourth image information;

[0058] Step S34: Calculate feature information of the finger vein image based on the fourth image information.

[0059] The step S34 also includes step S341, step S342 and step S343, which specifically include:

[0060] Step S341, obtaining a preset second sliding window;

[0061] In this step, the preset second sliding window size is 5×5.

[0062] Step S342: traverse the preset second sliding window on the fourth image information, and calculate the directional feature information under each second sliding window, wherein the directional feature information includes horizontal, vertical, diagonal, anti-diagonal and peripheral directional features;

[0063] In this step, the directional feature information under each second sliding window is calculated as follows:

[0064]

[0065] In the above formula, F l (j) represents the feature of the lth sub-graph in direction j, s represents the sign function, g l,j (i) represents the i-th pixel in the direction j of the l-th sub-image, g l,j (c) represents the pixel value of the center point of the lth sub-image in direction j, i represents the i-th pixel point in direction j, M s Indicates the pixel length in the peripheral direction, and its value is 8.

[0066] Step S343: Connect the directional features included in the directional feature information to obtain a first feature vector.

[0067] In this step, the directional feature information is finally expressed as F = [Fl (1), F l (2), F l (3), F l (4), F l (5)], further, the features of all subgraphs are concatenated into a long vector as the local encoding feature to obtain the first feature vector.

[0068] Step S4: Identify the target object according to the first feature vector and the second feature vector.

[0069] In this step, the first feature vector and the second feature vector are concatenated into one feature vector, and then the KNN algorithm (K nearest neighbor classification algorithm) is used for identification prediction, so as to identify the identity of the target object.

[0070] It should be noted that the present invention has better accuracy, lower error rate and higher recognition efficiency than the recognition algorithm disclosed in the prior art, as shown in Table 1:

[0071] method Recognition accuracy EER Time (ms) FPV-Net 91.67％ 3.90 482.87 LC-CNN 93.10％ 1.50 135.24+33.84 Method of the present invention 99.76％ 0.24 106.28

[0072] The present invention consumes little time for single feature extraction, is simple to calculate, does not require high-performance equipment to train the neural network model, effectively simplifies the implementation process of multimodal biometrics, and improves recognition efficiency while ensuring recognition accuracy.

[0073] Embodiment 2:

[0074] like Figure 2 As shown, this embodiment provides a biometric identification device based on local coding, the device includes an acquisition module 901, a preprocessing module 902, a feature extraction module 903 and a recognition module 904, which specifically include:

[0075] An acquisition module 901 is used to acquire first information and second information, wherein the first information includes a finger vein image of a target object, and the second information includes a palm print image of the target object;

[0076] A preprocessing module 902, configured to preprocess the first information and the second information respectively to obtain first image information and second image information;

[0077] A feature extraction module 903 is used to extract features from the first image information and the second image information respectively by using a local coding method to obtain a first feature vector and a second feature vector, wherein the first feature vector includes a finger vein local coding feature, and the second feature vector includes a palm print image local coding feature;

[0078] The identification module 904 is configured to identify the target object according to the first feature vector and the second feature vector.

[0079] In a specific implementation of the present disclosure, the preprocessing module 902 further includes a first processing unit 9021, a second processing unit 9022 and an enhancement unit 9023, which specifically include:

[0080] The first processing unit 9021 is used to filter the finger vein image of the target object using a Gaussian filter to obtain filtered image information;

[0081] The second processing unit 9022 is used to extract the region of interest from the filtered image information to obtain image information of the region of interest;

[0082] The enhancement unit 9023 is used to enhance the image information of the region of interest to obtain first image information.

[0083] In a specific embodiment of the present disclosure, the second processing unit 9022 further includes a third processing unit 90221, a fourth processing unit 90222, a fifth processing unit 90223 and a sixth processing unit 90224, which specifically include:

[0084] The third processing unit 90221 is used to segment the image by using a linear iterative clustering method, and extract the superpixel boundary and the boundary detected by the Sobel operator to obtain a finger boundary image;

[0085] The fourth processing unit 90222 is used to calculate the finger midline in the finger boundary image;

[0086] a fifth processing unit 90223, configured to calculate a tilt angle of the finger boundary image according to the finger midline, and correct the finger boundary image according to the tilt angle to obtain corrected image information;

[0087] The sixth processing unit 90224 is used to determine the width of the region of interest in the corrected image information according to the tangent line of the finger boundary, and obtain the image information of the region of interest.

[0088] In a specific implementation of the present disclosure, the feature extraction module 903 further includes a filling unit 9031, a seventh processing unit 9032, an eighth processing unit 9033 and a ninth processing unit 9034, which specifically include:

[0089] A filling unit 9031 is used to fill the first image information to obtain filled image information;

[0090] A seventh processing unit 9032 is configured to slide the first sliding window on the padded image information, calculate an average value under each first sliding window, and obtain third image information;

[0091] an eighth processing unit 9033, configured to divide the third image information to obtain fourth image information;

[0092] The ninth processing unit 9034 is used to calculate feature information of the finger vein image according to the fourth image information.

[0093] In a specific implementation of the present disclosure, the ninth processing unit 9034 further includes an acquisition unit 90341, a tenth processing unit 90342 and an eleventh processing unit 90343, which specifically include:

[0094] An acquiring unit 90341 is used to acquire a preset second sliding window;

[0095] a tenth processing unit 90342, configured to traverse the preset second sliding window on the fourth image information, and calculate directional feature information under each second sliding window, wherein the directional feature information includes horizontal, vertical, diagonal, anti-diagonal and peripheral directional features;

[0096] The eleventh processing unit 90343 is used to connect the various directional features included in the directional feature information to obtain a first feature vector.

[0097] In a specific implementation of the present disclosure, the filling unit 9031 further includes a judgment unit 90311, a first sub-judgment unit 90312 and a second sub-judgment unit 90313, which specifically include:

[0098] A traversal unit 90311 is used to traverse each row and each column in the first image information to obtain row number information and column number information of the first image information;

[0099] A judging unit 90312 is used to judge whether the row number information or the column number information of the first image information is a multiple of 2, and obtain a judgment result;

[0100] The sub-judgment unit 90313 is used to fill the bottom or rightmost side of the first image information with zeros when the judgment result is that the row number information or column number information of the first image information is not a multiple of 2.

[0101] It should be noted that, regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0102] Embodiment 3:

[0103] Corresponding to the above method embodiment, this embodiment also provides a biometric identification device based on local coding. The biometric identification device based on local coding described below and the biometric identification method based on local coding described above can refer to each other.

[0104] Figure 3 8 is a block diagram of a biometric identification device 800 based on local coding according to an exemplary embodiment. Figure 3 As shown, the local coding-based biometric recognition device 800 may include: a processor 801 and a memory 802. The local coding-based biometric recognition device 800 may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0105] The processor 801 is used to control the overall operation of the local coding-based biometric recognition device 800 to complete all or part of the steps in the local coding-based biometric recognition method. The memory 802 is used to store various types of data to support the operation of the local coding-based biometric recognition device 800, and these data may include, for example, instructions for any application or method operating on the local coding-based biometric recognition device 800, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone, which is used to receive external audio signals. The received audio signal may be further stored in the memory 802 or sent via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the local coding-based biometric device 800 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: Wi-Fi module, Bluetooth module, NFC module.

[0106] In an exemplary embodiment, the local coding based biometric device 800 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned local coding based biometric method.

[0107] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned local coding-based biometric recognition method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions can be executed by the processor 801 of the local coding-based biometric recognition device 800 to complete the above-mentioned local coding-based biometric recognition method.

[0108] Embodiment 4:

[0109] Corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment. The readable storage medium described below and the biometric recognition method based on local coding described above can refer to each other.

[0110] A readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the biometric identification method based on local coding in the above method embodiment are implemented.

[0111] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

[0112] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0113] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A biometric identification method based on local coding, characterized in that: include: Acquire first information and second information, wherein the first information includes a finger vein image of the target object, and the second information includes a palm print image of the target object; Preprocessing the first information and the second information respectively to obtain first image information and second image information; Using a local coding method to extract features from the first image information and the second image information respectively, to obtain a first feature vector and a second feature vector, wherein the first feature vector includes a finger vein local coding feature, and the second feature vector includes a palm print image local coding feature; The target object is identified according to the first feature vector and the second feature vector.

2. The biometric identification method based on local coding according to claim 1, characterized in that: Preprocessing the first information and the second information respectively to obtain first image information and second image information includes: Filtering the finger vein image of the target object using a Gaussian filter to obtain filtered image information; Extracting a region of interest from the filtered image information to obtain image information of the region of interest; The image information of the region of interest is enhanced to obtain first image information.

3. The biometric identification method based on local coding according to claim 1, characterized in that: The method of extracting features from the first image information and the second image information respectively by using a local coding method includes: Filling the first image information to obtain filled image information; Slide the first sliding window on the padded image information, calculate the average value under each first sliding window, and obtain the third image information; dividing the third image information to obtain fourth image information; The characteristic information of the finger vein image is calculated according to the fourth image information.

4. The biometric identification method based on local coding according to claim 3 is characterized in that: Calculating feature information of the finger vein image according to the fourth image information includes: Obtain a preset second sliding window; Traversing the preset second sliding window on the fourth image information, calculating directional feature information under each second sliding window, the directional feature information including horizontal, vertical, diagonal, anti-diagonal and peripheral directional features; The directional features included in the directional feature information are connected to obtain a first feature vector.

5. A biometric identification device based on local coding, characterized in that: include: An acquisition module, configured to acquire first information and second information, wherein the first information includes a finger vein image of a target object, and the second information includes a palm print image of the target object; A preprocessing module, used to preprocess the first information and the second information respectively to obtain first image information and second image information; A feature extraction module, configured to extract features from the first image information and the second image information respectively by using a local coding method to obtain a first feature vector and a second feature vector, wherein the first feature vector includes a finger vein local coding feature, and the second feature vector includes a palm print image local coding feature; A recognition module is used to recognize a target object according to the first feature vector and the second feature vector.

6. The biometric identification device based on local coding according to claim 5, characterized in that: The preprocessing module comprises: A first processing unit, configured to filter the finger vein image of the target object using a Gaussian filter to obtain filtered image information; A second processing unit is used to extract the region of interest from the filtered image information to obtain image information of the region of interest; The enhancement unit is used to enhance the image information of the region of interest to obtain first image information.

7. The biometric identification device based on local coding according to claim 5, characterized in that: The feature extraction module comprises: A filling unit, used for filling the first image information to obtain filled image information; A seventh processing unit, configured to slide the first sliding window on the padded image information, calculate an average value under each first sliding window, and obtain third image information; an eighth processing unit, configured to divide the third image information to obtain fourth image information; A ninth processing unit is used to calculate feature information of the finger vein image according to the fourth image information.

8. The biometric identification device based on local coding according to claim 7, characterized in that: The ninth processing unit comprises: An acquiring unit, used for acquiring a preset second sliding window; a tenth processing unit, configured to traverse the preset second sliding window on the fourth image information, and calculate directional feature information under each second sliding window, wherein the directional feature information includes horizontal, vertical, diagonal, anti-diagonal and peripheral directional features; The eleventh processing unit is used to connect the directional features included in the directional feature information to obtain a first feature vector.

9. A biometric identification device based on local coding, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the local coding-based biometric recognition method as claimed in any one of claims 1 to 4 when executing the computer program.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the local coding-based biometric identification method according to any one of claims 1 to 4 are implemented.

Images