Narrow strip fingerprint recognition methods, storage media, and electronic devices

Abstract

The present application provides a method for identifying narrow-strip fingerprints, the method comprising: processing multiple different training fingerprint images into multiple training fingerprint groups according to a preset first image processing rule; feeding the multiple training fingerprint groups into a multi-classification network to obtain a pre-trained model; processing multiple different registered fingerprint images into multiple registered fingerprint groups according to a preset second image processing rule; feeding the multiple registered fingerprint groups into a multi-classification network loaded with a pre-trained model to obtain a target model, the multi-classification network loaded with the target model can identify the registered finger ID and feature vector of each registered fingerprint image; inputting a group of fingerprint groups to be identified into a multi-classification network loaded with a target model to obtain the fingerprint ID to be identified and the feature vector of the fingerprint image to be identified; and obtaining the identification result of the fingerprint image to be identified according to the fingerprint ID to be identified and the corresponding feature vector and multiple registered finger IDs and the corresponding feature vectors. An electronic device is also provided.

Description

Technical Field

[0001] The present application relates to the field of consumer electronics, and in particular to a narrow-strip fingerprint recognition method, a storage medium, an electronic device, a narrow-strip fingerprint module, and a narrow-strip fingerprint sensor. Background Art

[0002] Fingerprint recognition technology is widely used in the field of consumer electronics, such as computers, smart phones, smart watches, etc. With the continuous development of science and technology, these electronic products are rapidly iterating towards higher integration and smaller size. Taking smart phones as an example, fingerprint recognition has gone through the stages of front fingerprint recognition scheme and back fingerprint recognition scheme, and has been continuously optimized. Later, some designers designed the fingerprint sensor on the side of the phone for the sake of the appearance of the phone. Traditional fingerprint recognition methods rely on details such as fingerprint ends and forks to achieve high fingerprint recognition accuracy. Since the fingerprint area obtained by narrow-strip fingerprint sensors is too small, there are few or even no details on each fingerprint image. As a result, it is impossible to directly use traditional fingerprint recognition methods to recognize fingerprint images obtained by narrow-strip fingerprint sensors, and the performance of the original excellent algorithm has been seriously reduced.

[0003] Therefore, it is an urgent problem to provide a narrow strip fingerprint recognition method suitable for recognizing narrow strip small area fingerprint images. Summary of the invention

[0004] The present application provides a narrow-strip fingerprint recognition method, a storage medium, an electronic device, a fingerprint recognition module and a narrow-strip fingerprint sensor, which can accurately recognize a narrow-strip fingerprint with a small area and find the registered finger corresponding to the narrow-strip fingerprint with a small area.

[0005] In a first aspect, an embodiment of the present application provides a method for recognizing a narrow strip fingerprint, and the method for recognizing a narrow strip fingerprint includes:

[0006] Processing a plurality of different training fingerprint images into a plurality of training fingerprint groups according to a preset first image processing rule, wherein each training fingerprint group includes a plurality of square sub-images and a label, wherein the label indicates a training finger ID to which the training fingerprint image corresponding to each training fingerprint group belongs;

[0007] Feeding the plurality of training fingerprint groups into a multi-classification network to obtain a pre-trained model, wherein the multi-classification network loaded with the pre-trained model can output the training finger ID and a feature vector for a plurality of square sub-images of each group of training fingerprint images;

[0008] Processing the plurality of different registered fingerprint images into a plurality of registered fingerprint groups according to a preset second image processing rule, wherein each registered fingerprint group includes a plurality of square sub-images and a label, and the label indicates the registered finger ID to which the registered fingerprint image corresponding to each registered fingerprint group belongs;

[0009] Feeding the plurality of registered fingerprint groups into a multi-classification network loaded with the pre-trained model to obtain a target model, wherein the multi-classification network loaded with the target model can output the registered finger ID and a feature vector of each registered fingerprint image;

[0010] Processing a fingerprint image to be identified into a group of fingerprints to be identified according to a preset third image processing rule, wherein the group of fingerprints to be identified includes a plurality of square sub-images;

[0011] Inputting the group of fingerprints to be identified into a multi-classification network loaded with the target model to obtain the ID of the finger to be identified and a feature vector of the fingerprint image to be identified; and

[0012] The recognition result of the fingerprint image to be recognized is obtained according to the ID of the finger to be recognized and the corresponding feature vector and multiple registered finger IDs and the corresponding feature vectors.

[0013] In a second aspect, an embodiment of the present application provides a storage medium, on which is stored program instructions of any one of the above-mentioned narrow-strip fingerprint recognition methods that can be loaded and executed by a processor.

[0014] In a third aspect, an embodiment of the present application provides an electronic device, the electronic device comprising:

[0015] A memory for storing program instructions;

[0016] The processor is used to execute program instructions to enable the electronic device to implement any one of the above-mentioned narrow strip fingerprint recognition methods.

[0017] The electronic device mentioned above further comprises a main body and a narrow strip fingerprint recognition sensor. The narrow strip fingerprint recognition sensor is arranged on the side of the main body. The side shape of the main body is adapted to the shape of the narrow strip fingerprint recognition sensor.

[0018] In a fourth aspect, an embodiment of the present application provides a fingerprint recognition module, the fingerprint recognition module comprising:

[0019] A memory for storing program instructions;

[0020] The processor is used to execute program instructions to enable the fingerprint recognition module to implement any one of the above-mentioned narrow-strip fingerprint recognition methods.

[0021] In a fifth aspect, an embodiment of the present application provides a narrow strip fingerprint sensor, which includes the above-mentioned fingerprint recognition module. Further, the narrow strip fingerprint sensor is a narrow strip curved fingerprint sensor.

[0022] In this embodiment, multiple training fingerprint images are processed into multiple training fingerprint groups according to the preset first image processing rule, and each training fingerprint group includes multiple square sub-images. Since the fingerprint area that can be obtained by the narrow strip fingerprint sensor is too small, there are few or even no detail points on each image, and the general multi-classification network cannot recognize the narrow strip fingerprint, so the narrow strip fingerprint is pre-processed in this application so that the multi-classification network can extract the fingerprint image features of the training fingerprint image and obtain the pre-trained model. The multi-classification network loaded with the pre-trained model can classify the training fingerprint image by the fingerprint image features, and fuse the feature information of multiple sub-images of each group, so that the multiple sub-images output an ID and a feature vector, and finally realize the preliminary fingerprint recognition function. Furthermore, in actual use, the multiple registered fingerprint groups obtained by screening and pre-processing the multiple registered fingerprint images are fed into the multi-classification network loaded with the pre-trained model to obtain the target model. The multiple registered fingerprint groups are fed into the multi-classification network loaded with the target model again for feature extraction, and each registered fingerprint group corresponds to a multi-dimensional feature. In order to save storage resources and facilitate fingerprint recognition later, KNN clustering is used to cluster these multi-dimensional features, and several registered fingerprint images are mapped to the feature space to generate a corresponding number of feature vectors. The ID and feature vector finally obtained constitute the registered fingerprint feature vector template library for fingerprint recognition. The fingerprint group to be recognized is input into the multi-classification network loaded with the target model to obtain the fingerprint ID and feature vector of the fingerprint image to be recognized, and the result of narrow strip fingerprint recognition is obtained according to the fingerprint ID and feature vector to be recognized, so as to realize the function of accurate recognition of narrow strip fingerprint images. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without creative work.

[0024] Figure 1 A flowchart of a method for recognizing narrow-strip fingerprints provided in an embodiment of the present application.

[0025] Figure 2 A schematic diagram of an electronic device provided in an embodiment of the present application.

[0026] Figure 3A flowchart of the sub-steps of step S101 provided in an embodiment of the present application.

[0027] Figure 4 A flowchart of the sub-steps of step S103 provided in an embodiment of the present application.

[0028] Figure 5 A flowchart of the sub-steps of step S105 provided in an embodiment of the present application.

[0029] Figure 6 A flowchart of the sub-steps of step S107 provided in an embodiment of the present application.

[0030] Figure 7 A schematic diagram of the internal structure of an electronic device provided in an embodiment of the present application.

[0031] Figure 8 A schematic diagram of a training fingerprint image and its invalid area and valid area provided in an embodiment of the present application.

[0032] Fig. 9 A schematic diagram of registered fingers provided in an embodiment of the present application.

[0033] Fig.10 A schematic diagram of the internal structure of a narrow strip fingerprint sensor provided in an embodiment of the present application.

[0034] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0036] The terms "first", "second", "third", "fourth", etc. (if any) 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 sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0037] It should be noted that the descriptions involving "first", "second", etc. in this application are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in this field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0038] The present invention provides a fingerprint recognition method that can recognize a narrow-shaped (such as a narrow strip, a narrow arc strip) fingerprint image. The fingerprint recognition method can be applied to electronic devices that are equipped with narrow-shaped fingerprint recognition sensors, for example, narrow-shaped fingerprint recognition sensors in mobile phones, tablet computers, etc.

[0039] Please see Figure 1 and Figure 2 , which is a flow chart of a method for recognizing a narrow strip fingerprint provided in an embodiment of the present application, Figure 2 Schematic diagram of an electronic device provided in an embodiment of the present application. The narrow-strip fingerprint recognition method is applied to a narrow-strip fingerprint recognition sensor 1 provided in an electronic device 100. The narrow-strip fingerprint recognition sensor 1 includes a sensing area 10, and the narrow-strip fingerprint sensor 1 is used to sense a fingerprint image when a user's finger is placed in the sensing area 10. The fingerprint recognition method includes the following steps.

[0040] Step S101, according to the preset first image processing rule, multiple different training fingerprint images are processed into multiple training fingerprint groups. Each training fingerprint group includes multiple square sub-images and a label, and the label indicates the training finger ID, identity document (ID) to which the training fingerprint image corresponding to each training fingerprint group belongs. The training finger ID is the finger ID corresponding to the training fingerprint image. In this embodiment, the training fingerprint image is a narrow strip fingerprint image. The first image processing rule is to first determine the mask using the threshold segmentation method to divide the training fingerprint image into a valid area and an invalid area. Different from the traditional fingerprint recognition method, all invalid image blocks on the fingerprint image can be ignored according to the mask. The deep learning scheme needs to ensure that the image input to the network is as free of invalid area interference as possible, and the invalid area needs to be cropped. According to experience, the invalid area of ​​the narrow strip fingerprint image is mainly distributed at both ends of the image. Secondly, the invalid area is removed using the minimum enclosing rectangle of the invalid area. How to process multiple different training fingerprint images into multiple training fingerprint groups according to the preset first image processing rule will be described in detail below.

[0041] Step S102, feed multiple sets of training fingerprint groups into a multi-classification network to obtain a pre-trained model. The multi-classification network loaded with the pre-trained model can output the training finger ID and a feature vector for each set of training fingerprint images. Specifically, multiple sets of training fingerprint groups constitute a training set, and the verification set is divided according to the proportion, and the multiple sets of training fingerprint groups are used to train the multi-classification network, wherein in the training stage, all sub-graphs of each group are shuffled in order and N are taken each time to be sent to the network, thereby increasing multiple possibilities and enhancing the performance of the multi-classification network; however, in the verification and testing stages, N sub-graphs from the same fingerprint image are directly sent to the network. The multi-classification network uses classic networks including but not limited to: VGG, ResNet, InceptionNet, MobileNe. A multi-graph feature fusion module is provided at the output end of the network to fuse the features of multiple square sub-graphs of each group so that multiple square sub-graphs output an ID and a feature vector.

[0042] Step S103, according to the preset second image processing rule, multiple different registered fingerprint images are processed into multiple registered fingerprint groups. Each registered fingerprint group includes multiple square sub-images and a label, and the label indicates the registered finger ID to which the registered fingerprint image corresponding to each registered fingerprint group belongs. How to process multiple different registered fingerprint images into multiple registered fingerprint groups according to the preset second image processing rule will be described in detail below.

[0043] Step S104, feed multiple groups of registered fingerprint groups into a multi-classification network loaded with a pre-trained model to obtain a target model. In this embodiment, each finger to be registered should register about 10 to 20 registered fingerprint images as templates, and set fingerprint image quality screening conditions, such as whether the area of ​​the registered fingerprint image recorded reaches a preset area value to ensure that the registered fingerprint image is valid. This step is to optimize the multi-classification network and enhance the recognition performance of the network. Fig. 9 Fingerprint 901, fingerprint 902 and fingerprint 903 are different positions of the same finger. When registering the fingerprint of a finger, the entire area of ​​the finger is collected as much as possible. The fingerprint collected in this embodiment is a narrow strip fingerprint sensor, and the collected fingerprint area is limited. Therefore, each registered finger needs to register several fingerprint images as templates.

[0044] Step S105, according to the preset third image processing rule, a fingerprint image to be identified is processed into a group of fingerprint groups to be identified. The multi-classification network loaded with the target model can output the registered finger ID and a feature vector of each registered fingerprint image. How to process a fingerprint image to be identified into a group of fingerprint groups to be identified according to the preset third image processing rule will be described in detail below.

[0045] Step S106, a group of fingerprints to be identified is input into a multi-classification network loaded with a target model to obtain the ID of the finger to be identified and a feature vector of the fingerprint image to be identified. Specifically, the fingerprint group to be identified is fed into a multi-classification network loaded with the target model to obtain the ID of the fingerprint to be identified and the corresponding original feature vector, wherein the original feature vector is a multi-dimensional feature vector, which is not conducive to storage and subsequent fingerprint matching. The original feature vector of each registered finger is clustered using KNN clustering to obtain a feature vector.

[0046] Step S107, obtaining the recognition result of the fingerprint image to be recognized based on the ID of the finger to be recognized and the corresponding feature vector and multiple registered finger IDs and the corresponding feature vectors. How to obtain the recognition result of the fingerprint image to be recognized based on the ID of the finger to be recognized and the corresponding feature vector and multiple registered finger IDs and the corresponding feature vectors will be described in detail below.

[0047] In this embodiment, multiple training fingerprint images are processed into multiple training fingerprint groups according to a preset first image processing rule, and each training fingerprint group includes multiple square sub-images. Since the fingerprint area that can be obtained by the narrow strip fingerprint sensor is too small, there are few or even no detail points on each image, and the general multi-classification network cannot recognize the narrow strip fingerprint, so the narrow strip fingerprint is pre-processed in this application so that the multi-classification network can extract the fingerprint image features of the training fingerprint image and obtain the pre-trained model. The multi-classification network loaded with the pre-trained model can classify the training fingerprint image by the fingerprint image features, and fuse the feature information of multiple sub-images of each group, so that the multiple sub-images output an ID and a feature vector, and finally realize the preliminary fingerprint recognition function. Furthermore, in actual use, the multiple registered fingerprint groups obtained by screening and pre-processing the multiple registered fingerprint images are fed into the multi-classification network loaded with the pre-trained model to obtain the target model. The multiple registered fingerprint groups are fed into the multi-classification network loaded with the target model again for feature extraction, and each registered fingerprint group corresponds to a multi-dimensional feature. In order to save storage resources and facilitate fingerprint recognition later, KNN clustering is used to cluster these multi-dimensional features, and several registered fingerprint images are mapped to the feature space to generate a corresponding number of feature vectors. The ID and feature vector finally obtained constitute the registered fingerprint feature vector template library for fingerprint recognition. The fingerprint group to be recognized is input into the multi-classification network loaded with the target model to obtain the fingerprint ID and feature vector of the fingerprint image to be recognized, and the result of narrow strip fingerprint recognition is obtained according to the fingerprint ID and feature vector to be recognized, so as to realize the function of accurate recognition of narrow strip fingerprint images.

[0048] Please refer to Figure 3, which is a sub-step flow chart of step S101 provided in an embodiment of the present application. Step S101 processes a plurality of different training fingerprint images into a plurality of training fingerprint groups according to a preset first image processing rule, wherein obtaining each training fingerprint group specifically includes the following steps.

[0049] Step S1011, calculate the invalid area of ​​the training fingerprint image according to a preset algorithm. Specifically, this embodiment uses a threshold segmentation method to determine the mask of the training fingerprint image and divide the training fingerprint image into a foreground (valid area) and a background (invalid area). Figure 8 According to experience, the invalid areas of the narrow strip fingerprint image are mainly distributed at both ends. The invalid area is removed by using the minimum enclosing rectangle of the invalid area, and the invalid area 811 of the training fingerprint image in the training fingerprint image 810 is shown.

[0050] Step S1012, cropping the invalid area of ​​the training fingerprint image to obtain the valid area of ​​the training fingerprint image, and obtaining the valid area of ​​each training fingerprint image. Figure 8 , the invalid area 811 of each training fingerprint image 810 is cropped to obtain the valid area 820 of the training fingerprint image. Removing the invalid area reduces the influence of the invalid area on fingerprint recognition and improves the efficiency of fingerprint recognition.

[0051] Step S1013, cropping the effective area of ​​the training fingerprint image into the multiple square sub-images to obtain the training fingerprint group. Specifically, in this embodiment, the width of the effective area of ​​the training fingerprint image is selected and used as the side length of the square to crop multiple squares.

[0052] Step S1014: adding a label of the training finger ID to which the corresponding training fingerprint image belongs to the training fingerprint group.

[0053] In this embodiment, the invalid area is removed, which reduces the influence of the invalid area on fingerprint recognition, improves the efficiency of fingerprint recognition, and enables the multi-classification network to learn and train the image features of each square sub-image in the fingerprint group more quickly.

[0054] Please refer to Figure 4 , which is a sub-step flowchart of step S103 provided in an embodiment of the present application.

[0055] Step S1031: Processing a plurality of different registered fingerprint images into a plurality of registered fingerprint groups according to the preset first image processing rule.

[0056] Step S1032, obtaining all tags in multiple groups of registered fingerprint groups.

[0057] Step S1033, obtaining all square sub-images corresponding to each label.

[0058] Step S1034: randomly selecting a plurality of square sub-images from all the square sub-images corresponding to each tag to form the registered fingerprint group.

[0059] Please refer to Figure 5 , which is a sub-step flow chart of step S105 provided in the embodiment of the present application. Step S105 processes a fingerprint image to be identified into a group of fingerprints to be identified according to a preset third image processing rule, and specifically includes the following steps.

[0060] Step S1051, calculating the invalid area of ​​the fingerprint image to be identified according to a preset algorithm.

[0061] Step S1052, cropping the invalid area of ​​the fingerprint image to be identified to obtain the valid area of ​​the fingerprint image to be identified.

[0062] Step S1053, cropping the effective area of ​​the fingerprint image to be identified into the plurality of square sub-images to obtain the fingerprint group to be identified.

[0063] Please refer to Figure 6 , which is a sub-step flowchart of step S107 provided in an embodiment of the present application.

[0064] Step S1071, construct a registered fingerprint feature vector template library using the multiple registered finger IDs and corresponding feature vectors. Specifically, the multiple registered fingers are fed into a multi-classification network loaded with the target model to obtain the ID of each registered finger and the corresponding original feature vector, wherein the original feature vector is a multi-dimensional feature vector, which is not conducive to storage and subsequent fingerprint matching. Use KNN clustering to cluster the original feature vector of each registered finger, map several registered finger images to the feature space to generate the feature vector of each registered finger, and use the ID of each registered finger and the corresponding feature vector as the registered fingerprint feature vector template library.

[0065] Step S1072, determining whether the to-be-identified finger ID matches the registered finger ID contained in the registered fingerprint feature vector template library.

[0066] Step S1073, when the ID of the finger to be identified matches the registered finger ID contained in the registered fingerprint feature vector template library, it is determined whether the distance between the feature vector corresponding to the finger to be identified and the feature vector corresponding to the matched registered finger is less than a preset threshold. Specifically, the distance between the feature vector of the finger to be identified and the feature vector in the registered fingerprint feature vector template library is calculated, and the registered fingerprint feature vector with the smallest distance is selected. When the ID of the finger to be identified matches the registered fingerprint ID library, the next step is performed.

[0067] Step S1074: when the distance between the feature vector corresponding to the finger to be identified and the feature vector corresponding to the matching registered finger is less than a preset threshold, output recognition success information.

[0068] In some other embodiments, when the ID of the finger to be identified does not match the registered finger ID contained in the registered fingerprint feature vector template library, information indicating that the identification has failed is output.

[0069] In some other embodiments, when the ID of the finger to be identified matches the registered finger ID contained in the registered fingerprint feature vector template library, and the distance between the feature vector corresponding to the finger to be identified and the feature vector corresponding to the matching registered finger is not less than a preset threshold, an identification failure message is output.

[0070] Alternatively, in some other embodiments, when the distance between the feature vector corresponding to the finger to be identified and the feature vector corresponding to the matching registered finger is less than a preset threshold, and the finger ID to be identified does not match the registered finger ID contained in the registered fingerprint feature vector template library, an identification failure message is output.

[0071] Please see Fig.10 , which is a schematic diagram of the internal structure of the narrow strip fingerprint sensor provided in an embodiment of the present application.

[0072] The narrow-strip fingerprint sensor 1 includes a fingerprint detection module 11 and a fingerprint recognition module 12. The fingerprint detection module 11 is used to output a fingerprint image when a finger is placed on the narrow-strip fingerprint sensor 1. The fingerprint recognition module 12 includes a memory 1201 and a processor 1202. The memory 1201 is used to store computer program instructions. The processor 1202 is used to execute the computer program instructions so that the fingerprint recognition module 12 implements the above-mentioned narrow-strip fingerprint recognition method.

[0073] The memory 1201 includes at least one type of readable storage medium, which includes flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 1201 may be an internal storage unit of the narrow-strip fingerprint sensor 1, such as a hard disk of the narrow-strip fingerprint sensor 1. In other embodiments, the memory 1201 may also be an external storage medium of the narrow-strip fingerprint sensor 1, such as a plug-in hard disk equipped on the narrow-strip fingerprint sensor 1, a smart memory card (Smart Media Card, SMC), a secure digital card (Secure Digital, SD), a flash card, etc. Further, the memory 1201 may also include both an internal storage unit and an external storage medium of the narrow-strip fingerprint sensor 1. The memory 1201 may not only be used to store application software and various types of data installed in the narrow-strip fingerprint sensor 1, such as program instructions of the narrow-strip fingerprint recognition method, etc., but may also be used to temporarily store data that has been output or is to be output, such as data generated by the execution of the narrow-strip fingerprint recognition method, etc.

[0074] In some embodiments, the processor 1202 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor or other data processing chip, and is used to run program instructions or process data stored in the memory 1201. Specifically, the processor 1202 executes program instructions of the narrow-strip fingerprint recognition method to control the fingerprint recognition module 12 to implement the narrow-strip fingerprint recognition method.

[0075] In the above embodiment, the fingerprint recognition is performed by the narrow strip fingerprint sensor 1. In other feasible embodiments, the fingerprint recognition method can also be performed by the processor of the electronic device 100.

[0076] Please refer to Figure 2 and Figure 7, the narrow strip fingerprint sensor 1 is applied to an electronic device 100. The electronic device 100 may be a mobile phone, a tablet computer, a laptop computer, etc. In this embodiment, the narrow strip fingerprint sensor 1 is described by taking the electronic device 100 as a mobile phone as an example. The electronic device 100 includes a main body 1001. The main body 1001 includes a front face 1002, a back face 1003, and a side face 1004 located between the front face 1002 and the back face 1003. The sensing area 10 of the narrow strip fingerprint sensor 1 is arranged on the side face 1004 of the main body 1001. In some feasible embodiments, the sensing area 10 may also be arranged at other positions of the electronic device 100, which is not limited here. It can be understood that when the electronic device is other electronic products, the position of the sensing area 10 may be changed according to the actual design. The narrow strip fingerprint sensor 1 is used to obtain a fingerprint image and input it to the electronic device 100. Further, the narrow strip fingerprint sensor 1 is a narrow strip curved surface fingerprint recognition sensor. Among them, the shape of the side face 1004 of the main body is adapted to the shape of the narrow strip fingerprint sensor 1.

[0077] The electronic device 100 at least includes a memory 101 and a processor 102. The memory 101 is used to store computer program instructions. The processor 102 is used to execute the program instructions to enable the electronic device to implement the above-mentioned narrow strip fingerprint recognition method.

[0078] Among them, the memory 101 includes at least one type of readable storage medium, which includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. The memory 101 can be an internal storage unit of the electronic device 100 in some embodiments, such as a hard disk of the electronic device 100. The memory 101 can also be an external storage medium of the electronic device 100 in other embodiments, such as a plug-in hard disk equipped on the electronic device 100, a smart memory card (Smart Media Card, SMC), a secure digital card (Secure Digital, SD), a flash card (Flash Card), etc. Further, the memory 101 can also include both an internal storage unit of the electronic device 100 and an external storage medium. The memory 101 can not only be used to store application software and various types of data installed in the electronic device 100, such as program instructions of the narrow strip fingerprint recognition method, etc., but also can be used to temporarily store data that has been output or is to be output, such as data generated by the execution of the narrow strip fingerprint recognition method, etc.

[0079] In some embodiments, the processor 102 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor or other data processing chip, and is used to run program instructions or process data stored in the memory 101. Specifically, the processor 102 executes program instructions of the narrow strip fingerprint recognition method to control the electronic device 100 to implement the narrow strip fingerprint recognition method.

[0080] Furthermore, the electronic device 100 may further include a bus 103 which may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0081] Furthermore, the electronic device 100 may also include a display component 104. The display component 104 may be an LED (Light Emitting Diode) display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch device, etc. The display component 104 may also be appropriately referred to as a display device or a display unit, which is used to display information processed in the electronic device 100 and to display a visual user interface.

[0082] Furthermore, the electronic device 100 may also include a communication component 105, which may optionally include a wired communication component and / or a wireless communication component (such as a WI-FI communication component, a Bluetooth communication component, etc.), which is generally used to establish a communication connection between the electronic device 100 and other electronic devices.

[0083] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0084] The identification method of the narrow strip fingerprint includes one or more program instructions. When the program instruction is loaded and executed on the device, the process or function according to the embodiment of the present application is generated in whole or in part. The device can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The program instruction can be stored in a computer-readable storage medium, or transmitted from a computer-readable storage medium to another computer-readable storage medium. For example, the program instruction can be transmitted from a website site, a computer, a server or a data center by wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can store or a data storage medium such as a server or a data center that includes one or more available media integration. The available medium can be a magnetic medium, (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid-state hard disk Solid State Disk (SSD)) etc.

[0085] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the above method embodiments and will not be repeated here.

[0086] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the above-described narrow-strip fingerprint recognition method embodiment is only schematic. For example, the division of the unit is only a logical function division. There may be other division methods in actual implementation, 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 an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0087] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0088] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0089] 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, 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 to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program instructions.

[0090] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

[0091] The above examples are only preferred embodiments of the present application, and certainly cannot be used to limit the scope of rights of the present application. Therefore, equivalent changes made according to the claims of the present application still fall within the scope covered by the present application.

Claims

1. A method for identifying a narrow strip fingerprint, characterized in that: The narrow strip fingerprint recognition method comprises: Processing a plurality of different training fingerprint images into a plurality of training fingerprint groups according to a preset first image processing rule, wherein each training fingerprint group includes a plurality of square sub-images and a label, wherein the plurality of square sub-images are cropped from each training fingerprint image with the width of the training fingerprint image being the side length of the square, and the label indicates the training finger ID to which the training fingerprint image corresponding to each training fingerprint group belongs; Feeding the multiple sets of training fingerprint groups into a multi-classification network to obtain a pre-trained model, wherein when feeding the multiple sets of training fingerprint groups into the multi-classification network, all sub-images of each group are shuffled in order and a preset number of sub-images are taken each time and fed into the multi-classification network, and the multi-classification network loaded with the pre-trained model can fuse the features of the multiple square sub-images of each set of training fingerprint images through a multi-image feature fusion module, so that the multiple square sub-images of each set of training fingerprint images output a training finger ID and a feature vector; Processing the plurality of different registered fingerprint images into a plurality of registered fingerprint groups according to a preset second image processing rule, wherein each registered fingerprint group includes a plurality of square sub-images and a label, and the label indicates the registered finger ID to which the registered fingerprint image corresponding to each registered fingerprint group belongs; Feeding the plurality of registered fingerprint groups into a multi-classification network loaded with the pre-trained model to obtain a target model, wherein the multi-classification network loaded with the target model can output the registered finger ID and a feature vector of each registered fingerprint image; Processing a fingerprint image to be identified into a group of fingerprints to be identified according to a preset third image processing rule, wherein the group of fingerprints to be identified includes a plurality of square sub-images; Inputting the group of fingerprints to be identified into a multi-classification network loaded with the target model to obtain the finger ID of the fingerprint image to be identified and a feature vector; and The recognition result of the fingerprint image to be recognized is obtained according to the ID of the finger to be recognized and the corresponding feature vector and multiple registered finger IDs and the corresponding feature vectors.

2. The method for recognizing a narrow strip fingerprint according to claim 1, characterized in that: Processing a plurality of different training fingerprint images into a plurality of training fingerprint groups according to a preset first image processing rule, wherein obtaining each of the training fingerprint groups specifically includes: Calculating the invalid area of ​​the training fingerprint image according to a preset algorithm; Cropping the invalid area of ​​the training fingerprint image to obtain the valid area of ​​the training fingerprint image; Cutting the effective area of ​​the training fingerprint image into the plurality of square sub-images to obtain the training fingerprint group; and A label of the training finger ID to which the corresponding training fingerprint image belongs is added to the training fingerprint group.

3. The method for recognizing a narrow strip fingerprint according to claim 1, characterized in that: Processing a plurality of different registered fingerprint images into a plurality of registered fingerprint groups according to the preset second image processing rule, wherein obtaining each of the registered fingerprint groups specifically includes: Processing a plurality of different registered fingerprint images into a plurality of registered fingerprint groups according to the preset first image processing rule; Obtaining all tags in the multiple groups of registered fingerprint groups; Get all the square sub-images corresponding to each label; A plurality of square sub-images are randomly selected from all the square sub-images corresponding to each label to form the registered fingerprint group.

4. The method for recognizing a narrow strip fingerprint according to claim 1, characterized in that: According to the preset third image processing rule, a fingerprint image to be identified is processed into a group of fingerprint groups to be identified, specifically including: Calculating the invalid area of ​​the fingerprint image to be identified according to the preset algorithm; Cropping the invalid area of ​​the fingerprint image to be identified to obtain the valid area of ​​the fingerprint image to be identified; The effective area of ​​the fingerprint image to be identified is cut into the multiple square sub-images to obtain the fingerprint group to be identified.

5. The method for recognizing a narrow strip fingerprint according to claim 1, characterized in that: The identification result of the fingerprint image to be identified is obtained according to the ID of the finger to be identified and the corresponding feature quantity and the IDs of multiple registered fingers and the corresponding feature quantities, specifically including: Constructing a registered fingerprint feature vector template library using the multiple registered finger IDs and corresponding feature quantities; Determine whether the finger ID to be identified matches the registered finger ID contained in the registered fingerprint feature vector template library; When the ID of the finger to be identified matches the registered finger ID contained in the registered fingerprint feature vector template library, determining whether the distance between the feature vector corresponding to the finger to be identified and the feature vector corresponding to the matched registered finger is less than a preset threshold; When the distance between the feature vector corresponding to the finger to be identified and the feature vector corresponding to the matching registered finger is less than a preset threshold, identification success information is output.

6. The method for recognizing a narrow strip fingerprint as claimed in claim 5, characterized in that: When the finger ID to be identified does not match the registered finger ID contained in the registered fingerprint feature vector template library, identification failure information is output.

7. The method for recognizing a narrow strip fingerprint as claimed in claim 5, characterized in that: Using the multiple registered finger IDs and the corresponding feature vectors to construct a registered fingerprint feature vector template library specifically includes: Feeding the multiple registered fingers into a multi-classification network loaded with the target model to obtain an ID of each registered finger and a corresponding original feature vector; Clustering the original feature vector of each registered finger using KNN clustering to generate a feature vector of each registered finger; The ID of each registered finger and the corresponding feature vector are used as the registered fingerprint feature vector template library.

8. A storage medium, characterized in that: The storage medium stores program instructions of the narrow strip fingerprint recognition method according to any one of claims 1 to 7 that can be loaded and executed by a processor.

9. An electronic device, characterized in that: The electronic device comprises: a memory for storing program instructions; and The processor is used to execute the program instructions to enable the electronic device to implement the narrow strip fingerprint recognition method according to any one of claims 1 to 7.

10. The electronic device according to claim 9, characterized in that: The electronic device further comprises a main body and a narrow strip-shaped fingerprint recognition sensor, wherein the narrow strip-shaped fingerprint recognition sensor is arranged on a side surface of the main body, and the side surface shape of the main body is matched with the shape of the narrow strip-shaped fingerprint recognition sensor.

11. A fingerprint recognition module, characterized in that: The fingerprint recognition module comprises: a memory for storing program instructions; and The processor is used to execute the program instructions to enable the fingerprint recognition module to implement the narrow strip fingerprint recognition method according to any one of claims 1 to 7.

12. A narrow strip fingerprint sensor, characterized in that: The narrow strip fingerprint sensor comprises the fingerprint recognition module as claimed in claim 11.

13. The narrow strip fingerprint sensor as claimed in claim 12, characterized in that: The narrow strip fingerprint sensor is a narrow strip curved fingerprint sensor.

14. The narrow strip fingerprint sensor according to claim 12, characterized in that: The narrow strip fingerprint sensor is a narrow strip capacitive curved fingerprint sensor.

Images