Fingerprint input and recognition method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application provide a fingerprint entry and identification method and device, electronic equipment and storage medium. The fingerprint entry method comprises: first, obtaining fingerprint template pictures of at least two sub-regions of a fingerprint identification region, then, determining at least two fingerprint feature pictures according to the fingerprint template pictures to form a fingerprint feature picture library, wherein the size of the fingerprint identification region, the size of the fingerprint region of the first segment of the finger, the size of the fingerprint template picture, and the size of the fingerprint feature picture decrease in turn. Embodiments of the present application can reduce the degree of complexity of the fingerprint entry process, reduce the time consumption of fingerprint entry, and improve the convenience of fingerprint entry.

Description

Technical Field

[0001] This application relates to the field of computer information acquisition technology, and more specifically, to a fingerprint input and recognition method, device, electronic device and storage medium. Background Technology

[0002] Biometric systems in electronic devices are widely used in scenarios such as device unlocking, encryption, and payment, and have become an indispensable part of daily life. Common biometric systems include fingerprint recognition, facial recognition, and iris recognition. Among them, fingerprint recognition systems have the advantages of convenience and speed, and are more commonly used in electronic devices. Today, fingerprint recognition has become the most mature and widely used biometric technology.

[0003] Because the fingerprint recognition system typically has a small fingerprint enrollment area, it requires lifting the finger multiple times and repeating the enrollment process to capture complete fingerprint features in order to complete the fingerprint comparison template enrollment process. The entire fingerprint enrollment process is cumbersome, time-consuming, and not very convenient. Summary of the Invention

[0004] This application addresses the shortcomings of existing methods by proposing a fingerprint enrollment and recognition method, device, electronic device, and storage medium that reduces the complexity of the fingerprint enrollment process, decreases the time required for fingerprint enrollment, and improves the convenience of fingerprint enrollment.

[0005] In a first aspect, embodiments of this application provide a fingerprint enrollment method, comprising: acquiring fingerprint template images of at least two sub-regions of a fingerprint recognition area; determining at least two fingerprint feature images based on each of the fingerprint template images to form a fingerprint feature image library; wherein the size of the fingerprint recognition area, the size of the fingerprint area of ​​the first segment of the finger, the size of the fingerprint template image, and the size of the fingerprint feature image decrease sequentially.

[0006] Secondly, embodiments of this application provide a fingerprint recognition method, including: acquiring a real-time fingerprint image; and recognizing the real-time fingerprint image based on a fingerprint feature library obtained by the fingerprint enrollment method described above.

[0007] Thirdly, embodiments of this application provide a fingerprint enrollment device, comprising: an acquisition module for acquiring fingerprint template images of at least two sub-regions of a fingerprint recognition area; and a processing module for determining at least two fingerprint feature images based on each of the fingerprint template images to form a fingerprint feature image library; wherein the size of the fingerprint recognition area, the size of the fingerprint area of ​​the first segment of the finger, the size of the fingerprint template image, and the size of the fingerprint feature image decrease sequentially.

[0008] Fourthly, embodiments of this application provide a fingerprint recognition device, comprising: a data acquisition module for acquiring real-time fingerprint images; and a recognition module for recognizing the real-time fingerprint images based on a fingerprint feature library obtained by the fingerprint entry method described above.

[0009] Fifthly, embodiments of this application provide an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the fingerprint enrollment method provided in the first aspect of this application, and / or the fingerprint recognition method provided in the second aspect of this application.

[0010] In a sixth aspect, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by an electronic device, implements the fingerprint enrollment method provided in the first aspect of this application and / or the fingerprint recognition method provided in the second aspect of this application.

[0011] The beneficial technical effects of the technical solutions provided in this application include:

[0012] Because the size of the fingerprint recognition area is larger than the size of the fingerprint area of ​​the first segment of the finger, the fingerprint area of ​​the first segment of the finger can be completely placed in the fingerprint recognition area to sense the complete fingerprint features of the first segment of the finger. Thus, a relatively complete fingerprint feature of the fingerprint area of ​​the first segment of the finger can be obtained without lifting the finger.

[0013] Because the size of the fingerprint area on the first segment of the finger is larger than the size of the fingerprint template image (the maximum fingerprint area that the system can collect in a single transaction), the maximum fingerprint area that the system can collect in a single transaction is smaller, resulting in lower hardware costs for the input device.

[0014] By using the above settings and combining the fingerprint template images of at least two sub-regions of the fingerprint recognition area, that is, the fingerprint template images of each sub-region contain fingerprint features from different positions of the first segment of the finger, the obtained fingerprint features are relatively complete. Thus, fingerprint information can be entered without lifting the finger while keeping costs low, reducing the complexity of the fingerprint entry process, reducing the time spent on fingerprint entry, and improving the convenience of fingerprint entry.

[0015] Furthermore, by determining at least two fingerprint feature images based on each of the fingerprint template images to form a fingerprint feature library, the size of the fingerprint template images is smaller than the size of the fingerprint feature images. That is, by using each of the fingerprint template images to obtain smaller fingerprint feature images, the size of the images in the fingerprint feature library used for comparison and matching during subsequent fingerprint recognition is reduced, thereby reducing the computational load of subsequent fingerprint recognition and improving the efficiency of fingerprint recognition.

[0016] Additional aspects and advantages of this application will be set forth in part in the description which follows, and will become apparent from the description or may be learned by practice of this application. Attached Figure Description

[0017] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0018] Figure 1 This is a schematic diagram of the module structure of the fingerprint recognition device in an electronic device according to an embodiment of this application;

[0019] Figure 2 This is a schematic diagram illustrating the process of collecting a fingerprint template image when the area of ​​the largest fingerprint region that can be collected in a single transaction is greater than the area of ​​the fingerprint region of the first segment of the finger.

[0020] Figure 3 A schematic flowchart illustrating a fingerprint enrollment method provided in an embodiment of this application;

[0021] Figure 4 A schematic diagram illustrating a specific example of a fingerprint enrollment method provided in this application embodiment;

[0022] Figure 5a This is a schematic diagram of the first fingerprint template image collected during fingerprint enrollment in an embodiment of this application;

[0023] Figure 5b This is a schematic diagram of the second fingerprint template image collected during fingerprint enrollment in an embodiment of this application;

[0024] Figure 5c This is a schematic diagram of the third fingerprint template image collected during fingerprint enrollment in an embodiment of this application;

[0025] Figure 5d This is a schematic diagram of the fourth fingerprint template image collected during fingerprint enrollment in an embodiment of this application;

[0026] Figure 6 This is a schematic diagram illustrating the addition of a central template image to the fingerprint center area according to an embodiment of this application;

[0027] Figure 7 This is a schematic diagram illustrating how the first fingerprint template image is cropped to generate three fingerprint feature images according to an embodiment of this application;

[0028] Figure 8 This is a schematic diagram of the structure of a fingerprint enrollment device provided in an embodiment of this application;

[0029] Figure 9 A schematic diagram illustrating a specific example of a fingerprint recognition device provided in this application embodiment;

[0030] Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Attached image description:

[0032] A - Fingerprint recognition area; B - Maximum fingerprint area that can be collected in a single scan; C - Fingerprint recognition acquisition area; D - Fingerprint area of ​​the first segment of the finger; O - Overlapping area;

[0033] 11-First fingerprint template image; 111-First fingerprint feature image; 112-Second fingerprint feature image; 113-Third fingerprint feature image; 12-Second fingerprint template image; 13-Third fingerprint template image; 14-Fourth fingerprint template image; 15-Center template image. Detailed Implementation

[0034] The embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the embodiments described below with reference to the accompanying drawings are exemplary descriptions for explaining the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions of the embodiments of this application.

[0035] Those skilled in the art will understand that, unless specifically stated otherwise, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be further understood that the term “comprising” as used in this application means the presence of the stated features, integers, steps, operations, elements, and / or components, but does not exclude implementations of other features, information, data, steps, operations, elements, components, and / or combinations thereof supported by this art. It should be understood that when we say an element is “connected” or “coupled” to another element, the element may be directly connected or coupled to the other element, or it may mean that the element and the other element are connected through an intermediate element. Furthermore, “connected” or “coupled” as used herein may include wireless connection or wireless coupling. The term “and / or” as used herein means at least one of the items defined by the term; for example, “A and / or B” may be implemented as “A,” or as “B,” or as “A and B.”

[0036] The inventors discovered that since large-area fingerprint recognition systems can collect fingerprints over a large area, they proposed a new method for inputting fingerprint comparison templates based on large-area fingerprint recognition systems. This method can solve the problem of repeated and multiple fingerprint inputs required in single-point fingerprint recognition systems, greatly optimize the method and process of inputting fingerprint comparison templates, and improve the input experience.

[0037] Figure 1The diagram shows a schematic of the module structure of a fingerprint recognition device in an electronic device according to an embodiment of this application. In a large-area fingerprint recognition system, the area of ​​the fingerprint recognition region A is usually large, typically 30mm*40mm (i.e., a rectangular area of ​​30mm*40mm). Due to limitations in module hardware cost and module size, the area of ​​the largest fingerprint region B that can be collected in a single transaction (equal to the size of the fingerprint template image) is usually smaller than the area of ​​the fingerprint recognition region A, typically 12mm*12mm (i.e., a rectangular area of ​​12mm*12mm). Typically, the collection area for fingerprint recognition does not need to reach the area of ​​the largest fingerprint region B that can be collected in a single transaction; a smaller size is sufficient to contain enough fingerprint feature information for fingerprint recognition. Therefore, the area of ​​the collection region C used for fingerprint recognition (equal to the size of the fingerprint feature image) is generally set to be smaller than the area of ​​the largest fingerprint region B that can be collected in a single transaction, typically 8mm*8mm (i.e., a square area of ​​8mm*8mm). Figure 1 The image shows the fingerprint recognition area A, the maximum fingerprint area that can be collected in a single scan B, and the fingerprint collection area C.

[0038] When a fingerprint recognition system is working, a fingerprint template must first be entered before fingerprint matching and recognition can proceed. The number of fingerprint template images captured is related to the area of ​​the largest fingerprint region B that can be captured in a single attempt. If the area of ​​the largest fingerprint region B that can be captured in a single attempt is larger than the area of ​​the fingerprint region D of the first segment of the finger, then only one high-quality fingerprint template image needs to be captured during fingerprint template entry. Figure 2 As shown.

[0039] However, due to factors such as cost, the second sensing area is usually smaller than the area of ​​a human fingerprint. This means that a single fingerprint comparison template image cannot contain all the fingerprint features of a finger. Therefore, multiple images need to be collected to record all fingerprint information in order to achieve better fingerprint recognition results.

[0040] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0041] One embodiment of this application provides a fingerprint enrollment method, such as... Figure 3 As shown, it may include:

[0042] S101: Obtain fingerprint template images of at least two sub-regions of the fingerprint recognition area.

[0043] The fingerprint recognition area is larger than the fingerprint area of ​​the first segment of the finger, and the fingerprint area of ​​the first segment of the finger is larger than the fingerprint template image. In other words, multiple fingerprint template images are obtained by collecting images of different areas on the fingerprint recognition area using the second sensing area.

[0044] Because the fingerprint recognition area is larger than the fingerprint area of ​​the first segment of the finger, the fingerprint area of ​​the first segment of the finger can be completely placed in the fingerprint recognition area to sense the complete fingerprint features of the first segment of the finger. Therefore, a relatively complete fingerprint feature of the fingerprint area of ​​the first segment of the finger can be obtained without lifting the finger.

[0045] Because the size of the fingerprint area on the first segment of the finger is larger than the size of the fingerprint template image (the maximum fingerprint area that the system can collect in a single transaction), the maximum fingerprint area that the system can collect in a single transaction is smaller, resulting in lower hardware costs for the input device.

[0046] By using the above settings and combining the fingerprint template images of at least two sub-regions of the fingerprint recognition area, that is, the fingerprint template images of each sub-region contain fingerprint features from different positions of the first segment of the finger, the obtained fingerprint features are relatively complete. Thus, fingerprint information can be entered without lifting the finger while keeping costs low, reducing the complexity of the fingerprint entry process, reducing the time spent on fingerprint entry, and improving the convenience of fingerprint entry.

[0047] S102: Based on each fingerprint template image, determine at least two fingerprint feature images to form a fingerprint feature image library.

[0048] The size of the fingerprint recognition area, the size of the fingerprint area on the first segment of the finger, the size of the fingerprint template image, and the size of the fingerprint feature image can be decreased sequentially.

[0049] By determining at least two fingerprint feature images based on each fingerprint template image, a fingerprint feature library is formed. The size of the fingerprint template image is smaller than the size of the fingerprint feature image. That is, a smaller fingerprint feature image is obtained by using each fingerprint template image. This reduces the size of the images in the fingerprint feature library used for comparison and matching during subsequent fingerprint recognition, thereby reducing the computational load of subsequent fingerprint recognition and improving the efficiency of fingerprint recognition.

[0050] In other words, the image size (third sensing area) required for fingerprint recognition and comparison is usually smaller than the fingerprint template image size (second sensing area). After the fingerprint template image is acquired, it needs to be cropped into an image of the third sensing area size (i.e., a fingerprint feature image) to facilitate fingerprint comparison and recognition, thereby generating a fingerprint feature library. The fingerprint feature library typically contains dozens of fingerprint images. During fingerprint recognition, the fingerprint image acquired by the device is compared with all the fingerprint feature images in the feature library. When the fingerprint image acquired by the device matches any fingerprint feature image in the feature library, the fingerprint recognition is considered successful.

[0051] In some embodiments, step S102 may include: cropping each fingerprint template image to generate at least two fingerprint feature images, thereby obtaining a fingerprint feature library. Compared to the method of first stitching fingerprint template images into a complete fingerprint image and then cropping the stitched image into a fingerprint feature library, this avoids the problem of abrupt changes at the stitching seams that could adversely affect fingerprint recognition, thus improving the accuracy of subsequent fingerprint recognition.

[0052] In some feasible embodiments, at least some fingerprint template images may include the fingerprint center area of ​​the fingerprint region of the first segment of the finger, and multiple fingerprint feature images may include at least one fingerprint feature image that contains the fingerprint center area of ​​the fingerprint region of the first segment of the finger. That is, at least one fingerprint feature image in the fingerprint feature image library contains the fingerprint center area of ​​the fingerprint region of the first segment of the finger, and the fingerprint center area of ​​the fingerprint region of the first segment of the finger has a high probability of being collected during fingerprint recognition, thereby improving the problem of fingerprint recognition misjudgment caused by incomplete fingerprint feature information in the fingerprint center area.

[0053] In some embodiments, the fingerprint template image may contain the same overlapping region, which may include the fingerprint center area of ​​the fingerprint region of the first segment of the finger. Step S102 may specifically include: first, taking the position containing the overlapping region as the initial position of the cropping window to obtain a first fingerprint feature image; then, translating the cropping window along a first direction to obtain at least one second fingerprint feature image. The resulting fingerprint feature image library includes the first fingerprint feature image and each second fingerprint feature image. That is, translating the cropping window along the first direction to crop multiple fingerprint feature images, wherein the first direction may be the length direction of the first segment of the finger, the width direction (perpendicular to the length direction), the direction at a 45-degree angle to the length direction, etc., and is not limited here.

[0054] Optionally, after translating the cropping window along the first direction to obtain at least one second fingerprint feature image, the step may further include: translating the cropping window along the second direction to obtain at least one third fingerprint feature image, wherein there is a designed angle between the second direction and the first direction. In this case, the fingerprint feature image library includes the first fingerprint feature image, each of the second fingerprint feature images, and each of the third fingerprint feature images. That is, multiple fingerprint feature images are cropped by translating the cropping window along the first direction and the second direction respectively.

[0055] The angle between the second direction and the first direction can be 90 degrees, or it can be 30 degrees, 45 degrees, 60 degrees, etc. When the angle between the second direction and the first direction is 90 degrees, the overlap area between the captured second fingerprint feature image and the third fingerprint feature image is small, thus enabling the acquisition of more comprehensive fingerprint information without changing the total number of fingerprint feature images.

[0056] In some other feasible embodiments, after translating the cropping window along the second direction to obtain at least one third fingerprint feature image, the step may further include: translating the cropping window along the third direction to obtain at least one fourth fingerprint feature image. In this case, the fingerprint feature image library includes the first fingerprint feature image, the second fingerprint feature image, the third fingerprint feature image, and the fourth fingerprint feature image.

[0057] Among them, the design angle between the third direction and the first direction and the second direction can both be less than 90 degrees. For example, the design angle between the second direction and the first direction can be equal to 90 degrees, and the design angle between the third direction and the first direction and the second direction can be 30 degrees and 60 degrees respectively, or both can be 45 degrees, etc.

[0058] Optionally, the first direction is parallel to the length direction of the fingerprint region of the first segment of the finger, and the number of second fingerprint feature images is greater than the number of third fingerprint feature images. Since the length of the fingerprint region of the first segment of the finger is greater than its width, by capturing more fingerprint feature images along the length of the finger than along its width, more fingerprint information from the first segment of the finger can be collected while maintaining the same number of fingerprint feature images, thus improving the success rate of subsequent fingerprint matching and recognition.

[0059] In some embodiments, the fingerprint template image may include at least one central template image, the center of which coincides with the center of the fingerprint region of the first segment of the finger. Considering that the fingerprint center region has a higher probability of being matched during recognition compared to the surrounding areas, adding a fingerprint template image to the fingerprint center region can further enrich the features of the fingerprint center region and improve the success rate of subsequent fingerprint matching and recognition.

[0060] In practical applications, by adjusting the acquisition method and cropping method of the template images, many sets of fingerprint feature image libraries can be obtained. The generated multiple sets of feature image libraries can be used to conduct fingerprint recognition experiments to verify the system. Machine learning can be used to obtain the optimal fingerprint template image entry method and image cropping method for the system, which can then be used as the final implementation plan for fingerprint entry in the system.

[0061] During the fingerprint template enrollment stage, the finger to be enrolled is first pressed onto the device's acquisition area. The system sequentially and continuously acquires multiple high-quality fingerprint images. Then, the system internally crops these images and generates a fingerprint feature image library, which is stored within the device. The entire fingerprint enrollment process requires no lifting of the finger or repeated pressing. Typically, the fingerprint feature image library contains dozens of fingerprint images. During the fingerprint recognition stage, the system compares the acquired fingerprint image with the fingerprint feature images in the library to complete the fingerprint recognition process.

[0062] Specifically, such as Figure 4 As shown, Figure 4 This is a schematic diagram illustrating a specific example of a fingerprint enrollment method. Specifically, the electronic device first receives a request to enroll a fingerprint template, then acquires a fingerprint template image, and performs image quality checks (i.e., image quality control). Specifically, it checks whether the image's clarity meets requirements, whether there are ghostings, blemishes, etc. If the image quality check fails, a new fingerprint template image of that sub-region within the fingerprint recognition area is enrolled. If the image quality check passes, the next fingerprint template image (of another sub-region within the fingerprint recognition area) is acquired. Multiple fingerprint template images are acquired continuously to complete the fingerprint template image acquisition process. Finally, the template image is cropped according to a predetermined cropping method to generate a fingerprint feature library, which is then stored internally to complete the entire fingerprint enrollment process.

[0063] To make it easier to understand, the following example will illustrate the point:

[0064] See Figure 5a , Figure 5b , Figure 5c , Figure 5d , Figure 5a , Figure 5b , Figure 5c , Figure 5dThese represent the four fingerprint template images collected sequentially during fingerprint enrollment (first fingerprint template image 11, second fingerprint template image 12, third fingerprint template image 13, and fourth fingerprint template image 14). Since the fingerprint center area of ​​the first segment of the finger is more likely to be captured during fingerprint comparison, these four fingerprint template images can include the same overlapping area O. The overlapping area O can include the fingerprint center area of ​​the first segment of the finger, and the area of ​​the overlapping area O can be adjusted appropriately according to the actual situation of the module. It should be noted that the entire fingerprint enrollment process does not require the finger to be lifted; simply collecting fingerprint template images from different areas sequentially greatly reduces the difficulty of fingerprint information collection and optimizes the fingerprint enrollment experience.

[0065] like Figure 6 As shown, Figure 6 This indicates that a central template image 15 is added to the central area of ​​the fingerprint. The center of the acquisition area of ​​the central template image 15 coincides with the center of the fingerprint area of ​​the first segment of the finger. As an example, the center position of the central template image 15 can be the overlapping area O. It should be noted that the number of fingerprint template images can be adjusted according to the actual situation. It is not necessarily required to be only 4 or 5 images. As long as the images contain enough fingerprint feature information, it is sufficient for fingerprint recognition. This is just an example to illustrate the fingerprint template image acquisition method.

[0066] like Figure 7 As shown, Figure 7 This means that the first fingerprint template image 11 is cropped to generate three fingerprint feature images (namely, the first fingerprint feature image 111, the second fingerprint feature image 112, and the third fingerprint feature image 113). Cropping all the collected fingerprint template images can yield dozens of images, which together form a fingerprint feature image library.

[0067] The fingerprint enrollment method provided in this application is applicable to the fingerprint comparison template enrollment method and fingerprint feature image library generation method in large-area fingerprint recognition systems such as optical and ultrasonic fingerprint recognition systems. During the fingerprint template enrollment process, the finger does not need to be lifted, which can effectively reduce the fingerprint template enrollment time and optimize the enrollment experience. Furthermore, this method does not require additional system hardware components or additional module costs, which is of great significance for promoting the widespread adoption of large-area fingerprint recognition systems. In other words, the entire fingerprint template enrollment process is simple and fast; the finger does not need to be lifted or rotated during the enrollment process, effectively optimizing the fingerprint enrollment experience. This solution can be implemented based on existing large-area fingerprint recognition systems without requiring additional system hardware components, thus balancing the advantages of performance and cost. That is, without increasing the manufacturing cost of the fingerprint recognition terminal, it can reduce fingerprint enrollment time and improve the convenience of fingerprint enrollment by eliminating the need to lift or rotate the finger.

[0068] Based on the same inventive concept, this application provides a fingerprint enrollment device 20, the structural framework of which is shown in the schematic diagram below. Figure 8 As shown, it may include: an acquisition module 201 and a processing module 202.

[0069] The acquisition module 201 is used to acquire fingerprint template images of at least two sub-regions of the fingerprint recognition area.

[0070] The processing module 202 is used to determine at least two fingerprint feature images based on each fingerprint template image to form a fingerprint feature image library.

[0071] Among them, the size of the fingerprint recognition area, the size of the fingerprint area of ​​the first segment of the finger, the size of the fingerprint template image, and the size of the fingerprint feature image decrease in that order.

[0072] In some embodiments, such as Figure 9 As shown, the processing module 202 may include a cropping unit 2021 and an output unit 2022. The cropping unit 2021 is used to crop each fingerprint template image to generate multiple fingerprint feature images. The output unit 2022 is used to store the multiple fingerprint feature images to form a fingerprint feature library.

[0073] Optionally, at least a portion of the fingerprint template image may include the fingerprint center region of the fingerprint region of the first segment of the finger, and multiple fingerprint feature images may include at least one fingerprint feature image that includes the fingerprint center region of the fingerprint region of the first segment of the finger.

[0074] Optionally, the fingerprint template image may contain the same overlapping region, which may include the fingerprint center area of ​​the fingerprint region of the first segment of the finger. The cropping unit 2021 is specifically used to obtain a first fingerprint feature image by using the position containing the overlapping region as the initial position of the cropping window; and to translate the cropping window along a first direction to obtain at least one second fingerprint feature image. The output unit 2022 is specifically used to store the first fingerprint feature image and each of the second fingerprint feature images to form a fingerprint feature library.

[0075] Optionally, the cropping unit 2021 can also be used to translate the cropping window along the second direction to obtain at least one third fingerprint feature image. There is a design angle between the second direction and the first direction. In this case, the output unit 2022 is specifically used to store the first fingerprint feature image, each second fingerprint feature image and each third fingerprint feature image to form a fingerprint feature library.

[0076] The angle between the second direction and the first direction can be 90 degrees, or it can be 30 degrees, 45 degrees, 60 degrees, etc. When the angle between the second direction and the first direction is 90 degrees, the overlap area between the captured second fingerprint feature image and the third fingerprint feature image is small, thus enabling the acquisition of more comprehensive fingerprint information without changing the total number of fingerprint feature images.

[0077] Optionally, the first direction is parallel to the length direction of the fingerprint region of the first segment of the finger, and the number of second fingerprint feature images can be greater than the number of third fingerprint feature images. This allows for the collection of more fingerprint information from the first segment of the finger while maintaining the same number of fingerprint feature images, thereby improving the success rate of subsequent fingerprint matching and recognition.

[0078] Optionally, the fingerprint template image may include at least one central template image, the center of which coincides with the center of the fingerprint region of the first segment of the finger. By adding a fingerprint template image to the central fingerprint region, the features of the central fingerprint region can be further enriched, improving the success rate of subsequent fingerprint matching and recognition.

[0079] The fingerprint enrollment device in this embodiment can execute any of the fingerprint enrollment methods provided in the embodiments of this application. Their implementation principles are similar and will not be described in detail here.

[0080] Based on the same inventive concept, this application provides a fingerprint recognition method comprising the following steps: first, acquiring a real-time fingerprint image; then, recognizing the real-time fingerprint image based on a fingerprint feature library obtained using any of the fingerprint entry methods provided in this application. The implementation principles are similar, and the achieved technical effects are also similar, so they will not be elaborated upon here.

[0081] Based on the same inventive concept, the fingerprint recognition device provided in this application may include: a collection module and a recognition module. The collection module is used to acquire real-time fingerprint images, and the recognition module is used to recognize the real-time fingerprint images based on a fingerprint feature library obtained by any of the fingerprint enrollment methods provided in this application. Their implementation principles are similar, and the achieved technical effects are also similar, so they will not be described in detail here.

[0082] Based on the same inventive concept, embodiments of this application provide an electronic device 30, such as... Figure 10 As shown, the electronic device 30 includes a memory 303 and a processor 301. The memory 303 is communicatively connected to the processor 301, such as via a bus 302. At least one computer program is stored in the memory 303. The processor 301 executes the computer program to implement any fingerprint enrollment method and / or any fingerprint recognition method provided in the embodiments of this application.

[0083] The processor 301 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. The processor 301 can also be a combination that implements computational functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0084] Bus 302 may include a pathway for transmitting information between the aforementioned components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. Bus 302 can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 9 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0085] The memory 303 may be a ROM (Read-Only Memory) or other type of static storage device capable of storing static information and instructions, RAM (Random Access Memory) or other type of dynamic storage device capable of storing information and instructions, or it may be an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read-Only Memory) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto.

[0086] Optionally, the electronic device 30 may also include a communication unit 304. The communication unit 304 can be used for receiving and transmitting signals. The communication unit 304 allows the electronic device 30 to communicate wirelessly or wiredly with other devices to exchange data. It should be noted that in practical applications, the communication unit 304 is not limited to one.

[0087] Optionally, the electronic device 30 may further include an input unit 305. The input unit 305 can be used to receive input numbers, characters, images, and / or sound information, or to generate key signal inputs related to user settings and function control of the electronic device 30. The input unit 305 may include, but is not limited to, one or more of a touchscreen, a camera, etc.

[0088] Optionally, the electronic device 30 may also include an output unit 306. The output unit 306 can be used to output or display information processed by the processor 301. The output unit 306 may include, but is not limited to, one or more of a display device, a speaker, a vibration device, etc.

[0089] Although Figure 10 An electronic device 30 with various devices is shown; however, it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed alternatively.

[0090] Optionally, the memory 303 is used to store application code that executes the scheme of this application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement any fingerprint enrollment method and / or any fingerprint recognition method provided in the embodiments of this application.

[0091] Those skilled in the art will understand that the electronic devices provided in the embodiments of this application can be specifically designed and manufactured for the desired purpose, or may include known devices in general-purpose computers. These devices have computer programs stored therein that are selectively activated or reconfigured. Such computer programs can be stored in a device (e.g., computer) readable medium or in any type of medium suitable for storing electronic instructions and respectively coupled to a bus.

[0092] Compared with existing technologies, it can achieve the following: reduce fingerprint enrollment time without increasing the manufacturing cost of fingerprint recognition terminals, and improve the convenience of fingerprint enrollment without lifting or rotating the finger.

[0093] Based on the same inventive concept, embodiments of this application provide a computer-readable storage medium storing a computer program. When executed by an electronic device, the program enables any of the fingerprint enrollment methods and / or fingerprint recognition methods provided in the embodiments of this application. The implementation principles are similar, and the achieved technical effects are also similar, so further details are omitted here.

[0094] By applying the embodiments of this application, at least the following beneficial effects can be achieved:

[0095] 1. The entire fingerprint template enrollment process is simple and quick. During the enrollment process, there is no need to lift the finger or rotate the finger angle to complete the fingerprint enrollment, which can effectively optimize the fingerprint enrollment experience.

[0096] 2. This solution can be implemented based on existing large-area fingerprint recognition systems without the need for additional system hardware components, thus balancing the advantages of performance and cost.

[0097] Those skilled in the art will understand that the steps, measures, and solutions in the various operations, methods, and processes discussed in this application can be alternated, modified, combined, or deleted. Furthermore, other steps, measures, and solutions in the various operations, methods, and processes discussed in this application can also be alternated, modified, rearranged, decomposed, combined, or deleted. Furthermore, steps, measures, and solutions in the prior art that are similar to those disclosed in this application can also be alternated, modified, rearranged, decomposed, combined, or deleted.

[0098] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0099] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown sequentially according to the arrows, the order in which these steps are implemented is not limited to the order indicated by the arrows. Unless explicitly stated herein, in some implementation scenarios of this application, the steps in each process can be executed in other orders as needed. Moreover, some or all of the steps in each flowchart may include multiple sub-steps or multiple stages based on the actual implementation scenario. Some or all of these sub-steps or stages may be executed at the same time or at different times. In scenarios where the execution times are different, the execution order of these sub-steps or stages can be flexibly configured according to needs, and this application does not limit this.

[0100] The above description is only a partial implementation of this application. It should be noted that for those skilled in the art, other similar implementation methods based on the technical concept of this application, without departing from the technical concept of this application, also fall within the protection scope of the embodiments of this application.

Claims

1. A fingerprint enrollment method, characterized in that, include: Obtain fingerprint template images of at least two sub-regions of the fingerprint recognition area; Based on each of the fingerprint template images, at least two fingerprint feature images are determined to form a fingerprint feature library, including: cropping each of the fingerprint template images to generate at least two fingerprint feature images to obtain the fingerprint feature library, wherein the fingerprint feature library contains dozens of fingerprint feature images; The size of the fingerprint recognition area, the size of the fingerprint area of ​​the first segment of the finger, the size of the fingerprint template image, and the size of the fingerprint feature image decrease sequentially. The size of the fingerprint feature image is the image size required for fingerprint recognition and comparison. At least a portion of the fingerprint template image includes the fingerprint center area of ​​the fingerprint region of the first segment of the finger; at least one of the multiple fingerprint feature images includes a fingerprint feature image that includes the fingerprint center area of ​​the fingerprint region of the first segment of the finger; The fingerprint template images contain the same overlapping region, which includes the fingerprint center area of ​​the fingerprint region of the first segment of the finger. The step of cropping each fingerprint template image to generate at least two fingerprint feature images, thus obtaining the fingerprint feature library, includes: Using the location containing the overlapping area as the initial position of the cropping window, a first fingerprint feature image is obtained; The cropping window is translated along the first direction to obtain at least one second fingerprint feature image; After translating the cropping window along the first direction to obtain at least one second fingerprint feature image, the method further includes: The cropping window is translated along the second direction to obtain at least one third fingerprint feature image; After translating the cropping window along the second direction to obtain at least one third fingerprint feature image, the method further includes: translating the cropping window along the third direction to obtain at least one fourth fingerprint feature image. The fingerprint feature image library includes the first fingerprint feature image, each of the second fingerprint feature images, each of the third fingerprint feature images, and each of the fourth fingerprint feature images; The design angle between the third direction and the first and second directions is less than 90 degrees.

2. The fingerprint enrollment method according to claim 1, characterized in that... There is a design angle between the second direction and the first direction.

3. The fingerprint enrollment method according to claim 2, characterized in that, The design angle between the second direction and the first direction is 90 degrees.

4. The fingerprint entry method according to claim 2 or 3, characterized in that, The first direction is parallel to the length direction of the fingerprint region of the first segment of the finger, and the number of the second fingerprint feature images is greater than the number of the third fingerprint feature images.

5. The fingerprint enrollment method according to claim 1, characterized in that, The fingerprint template image includes at least one central template image, and the center of the acquisition area of ​​the central template image coincides with the center of the fingerprint area of ​​the first segment of the finger.

6. A fingerprint recognition method, characterized in that, include: Obtain real-time fingerprint images; The real-time fingerprint image is identified based on the fingerprint feature library obtained by any one of the fingerprint enrollment methods described in claims 1-5.

7. A fingerprint enrollment device for performing the fingerprint enrollment method as described in any one of claims 1-5, characterized in that, include: The acquisition module is used to acquire fingerprint template images of at least two sub-regions of the fingerprint recognition area; The processing module is used to determine at least two fingerprint feature images based on each of the fingerprint template images to form a fingerprint feature image library; The size of the fingerprint recognition area, the size of the fingerprint area of ​​the first segment of the finger, the size of the fingerprint template image, and the size of the fingerprint feature image decrease sequentially.

8. A fingerprint recognition device, characterized in that, include: The acquisition module is used to acquire real-time fingerprint images; The recognition module is used to recognize the real-time fingerprint image based on the fingerprint feature library obtained by any one of the fingerprint enrollment methods as described in claims 1-5.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory, characterized in that the processor executes the computer program to implement the fingerprint enrollment method as described in any one of claims 1-5, and / or the fingerprint recognition method as described in claim 6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, when executed by an electronic device, the computer program implements the fingerprint enrollment method as described in any one of claims 1-5, and / or the fingerprint recognition method as described in claim 6.

Images