Fingerprint recognition method and device
Through contactless image acquisition and image processing technology, the problem of low accuracy of contact fingerprint recognition is solved, and a more accurate fingerprint recognition effect is achieved.
Patent Information
- Application Number
- CN202010716973.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2020-07-23
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2040-07-23
AI Technical Summary
The existing contact fingerprint recognition technology is greatly affected by factors such as pressing pressure, pressing area, pressing angle, stains and sweat stains, resulting in low recognition accuracy.
Fingerprint images are collected by non-contact image acquisition equipment, and fingerprint features are extracted for identification through image processing technologies such as filtering, grayscale processing and contrast enhancement.
It improves the accuracy of fingerprint recognition, reduces the recognition error caused by changes in the pressing method, obtains an approximate distortion-free fingerprint image, significantly improves the contrast between the ridge and valley lines, thereby achieving more accurate fingerprint recognition.
Smart Images

Figure CN111898512B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of Internet, and in particular to a fingerprint recognition method and device. Background Art
[0002] Identity authentication based on biometrics is widely used in various fields, and fingerprint recognition is one of the most widely used biometrics.
[0003] Currently, the more popular fingerprint recognition is contact fingerprint recognition, such as pressing a finger into the fingerprint sensor to obtain fingerprint information and use it for identity authentication. However, in actual applications, it is found that this fingerprint recognition method is greatly affected by factors such as pressing force, pressing area, pressing angle, stains, sweat stains, etc., which affects the recognition accuracy. Therefore, a solution is urgently needed to improve the accuracy of fingerprint recognition. Summary of the invention
[0004] The embodiment of the present application provides a fingerprint recognition method, which can perform fingerprint recognition more accurately.
[0005] The embodiment of the present application provides a fingerprint recognition device that can perform fingerprint recognition more accurately.
[0006] To solve the above technical problems, the embodiments of the present application are implemented as follows:
[0007] The present application embodiment adopts the following technical solutions:
[0008] A fingerprint recognition method, characterized by comprising:
[0009] Acquiring a fingerprint image collected by a non-contact image acquisition device;
[0010] Performing filtering and grayscale processing on the fingerprint image to obtain a grayscale image;
[0011] Performing contrast enhancement on the grayscale image to obtain a contrast-enhanced image;
[0012] Fingerprint features are extracted from the contrast-enhanced image, and fingerprint recognition is performed based on the extraction result.
[0013] A fingerprint recognition device, characterized in that it comprises: an image acquisition unit, an image processing unit, and a fingerprint recognition unit, wherein:
[0014] The image acquisition unit is used to acquire the fingerprint image acquired by the non-contact image acquisition device;
[0015] The image processing unit is used to perform filtering and grayscale processing on the fingerprint image to obtain a grayscale image;
[0016] The image processing unit is used to perform contrast enhancement on the grayscale image to obtain a contrast-enhanced image;
[0017] The fingerprint recognition unit is used to extract fingerprint features from the contrast-enhanced image and perform fingerprint recognition based on the extraction result.
[0018] It can be seen from the technical solutions provided by the above embodiments that a fingerprint image collected by a non-contact image acquisition device can be first obtained, and then filtering and grayscale processing can be performed based on the fingerprint image, and then the grayscale image can be contrast enhanced, so as to extract fingerprint features based on the contrast enhanced image, and perform fingerprint recognition based on the extraction result.
[0019] That is, a non-contact image acquisition device can be used to collect fingerprint images that are nearly distortion-free, and through image processing methods such as filtering, grayscale, and contrast enhancement, the contrast between the ridges and valleys in the fingerprint can be improved, thereby enabling more accurate fingerprint recognition. BRIEF DESCRIPTION OF THE DRAWINGS
[0020] In order to more clearly illustrate the embodiments of the present application or the existing technical solutions, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0021] Figure 1 A schematic diagram of the fingerprint recognition method provided in the embodiment of the present application;
[0022] Figure 2 A schematic diagram of a fingerprint image collected according to an embodiment of the present application;
[0023] Figure 3 A schematic diagram of contrast enhancement of a fingerprint image provided in an embodiment of the present application;
[0024] Figure 4 A schematic diagram of image denoising for a fingerprint image provided in an embodiment of the present application;
[0025] Figure 5 A schematic diagram of feature extraction of a fingerprint image provided in an embodiment of the present application;
[0026] Figure 6 A schematic diagram of a fingerprint recognition method provided in an embodiment of the present application;
[0027] Figure 7 A schematic diagram of the structure of a fingerprint recognition device provided in an embodiment of the present application;
[0028] Figure 8 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0029] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.
[0030] The technical solutions provided by each embodiment of the present application are described in detail below in conjunction with the accompanying drawings.
[0031] Example 1
[0032] This embodiment provides a fingerprint recognition method that can perform fingerprint recognition more accurately. It is assumed that the execution subject can be a fingerprint recognition device or a processor in an identity authentication device. The specific flow diagram of this embodiment is as follows Figure 1 As shown, including:
[0033] Step 102: Acquire a fingerprint image collected by a non-contact image acquisition device.
[0034] As mentioned above, the more popular fingerprint recognition is usually the pressing type, that is, the finger contacts the fingerprint sensor, which may affect the accuracy of fingerprint recognition due to the pressing force, pressing area, pressing angle, stains, and sweat stains. Therefore, in this step, the fingerprint image can be collected by a non-contact image acquisition device.
[0035] Specifically, the contactless image acquisition device can be an optical camera, such as a front or rear camera installed on a mobile phone, a surveillance camera installed on an access control, etc. The user can point his finger at the image acquisition device without touching it, so that the device can collect the fingerprint image. For example, when the user needs to perform access control authentication, the finger to be authenticated can be placed in front of the access control camera without touching it.
[0036] In this step, the execution subject may directly obtain the fingerprint image collected and saved by the non-contact image acquisition device, or may obtain the fingerprint image collected in real time by the non-contact image acquisition device.
[0037] The fingerprints collected by non-contact image acquisition equipment are closer to real biological fingerprints because they avoid fingerprint distortion caused by pressing.
[0038] In practical applications, the acquired image may contain other non-fingerprint images, such as faces, backgrounds, etc. Therefore, in order to acquire fingerprint images more accurately, in one embodiment, acquiring fingerprint images acquired by a non-contact image acquisition device may include: acquiring images acquired by a non-contact image acquisition device; performing image recognition on the images; and based on the image recognition results, extracting the fingerprint image containing the fingerprint from the acquired images.
[0039] Specifically, an image captured by a non-contact image acquisition device can be obtained first. Since the image may or may not contain fingerprints, and the area containing the fingerprints may be larger or smaller, image recognition can be performed on the image to obtain a recognition result. Based on the image recognition result, it can be determined whether the image contains fingerprints. If so, a fingerprint image containing the fingerprint can be captured from the captured image based on the image recognition result.
[0040] Image recognition here refers to the technology of using computers to process, analyze and understand images to identify targets and objects of various different patterns. It is a practical application of deep learning algorithms. For example, image features such as text and patterns can be recognized, as well as biological features such as faces and fingerprints. Therefore, in order to more accurately obtain fingerprint images containing fingerprints, the fingerprint image can be intercepted from the acquired image through image recognition, so that fingerprint recognition can be more accurately performed in subsequent steps.
[0041] In practical applications, even if a fingerprint image is collected by a non-contact image acquisition device, the accuracy of fingerprint recognition may be affected by factors such as distance and angle. Therefore, in order to further improve the accuracy of fingerprint recognition, in one embodiment, obtaining a fingerprint image collected by a non-contact image acquisition device may include: obtaining multiple fingerprint images continuously collected by the non-contact image acquisition device.
[0042] Specifically, a non-contact image acquisition device can be used to continuously acquire multiple fingerprint images, such as prompting the user to move in space, or continuously taking pictures at the same spatial position, etc. Thus, multiple fingerprint images can be acquired. It is also possible to combine the image recognition described above and obtain multiple fingerprint images by intercepting them separately from multiple original images.
[0043] In this step, the fingerprint image collected by the image acquisition device can be an image of the three primary color light model (RGB color model), or an image of the RGB color model (hereinafter referred to as RGB image). Figure 2As shown, it can be seen that the collected RGB image has almost no distortion after pressing.
[0044] Step 104: Filter and grayscale process the fingerprint image to obtain a grayscale image.
[0045] In fingerprint recognition, feature extraction is usually performed based on grayscale images, and recognition and authentication are performed based on the feature extraction results. Therefore, in this step, filtering and grayscale processing can be performed on the fingerprint image collected in the previous step.
[0046] Specifically, image filtering can suppress the noise of an image while preserving the image details as much as possible. The quality of the processing will directly affect the effectiveness and reliability of subsequent image processing and analysis.
[0047] In this step, median filtering can be performed first. Median filtering can replace the original pixel with the median of the neighborhood pixel set around the test pixel. The effect of median filtering is more obvious when removing noise. For example, the image can be split into several 3×3 pixel sets, then in each pixel set, the middle pixel block can be used to replace the surrounding pixel blocks. Of course, in actual use, mean filtering, Gaussian filtering, etc. can also be performed on the image. For example, in each 3×3 pixel set, the mean of the pixels can be used to replace all pixel blocks.
[0048] In the field of image processing, a grayscale digital image is an image with only one sampled color per pixel. Such images are usually displayed as grayscales from the darkest black to the brightest white. That is, different RGB colors can be mapped to different grayscales through a specific mapping method to obtain a grayscale image.
[0049] Step 106: performing contrast enhancement on the grayscale image to obtain a contrast enhanced image.
[0050] Since the fingerprint includes ridges and valleys, after grayscale processing, certain differences between ridges and valleys can be reflected. In this step, in order to highlight the difference between ridges and valleys, the grayscale image can be subjected to contrast enhancement (also known as contrast enhancement), so that the contrast-enhanced image can more clearly reflect the difference between ridges and valleys.
[0051] Specifically, there may be a variety of contrast enhancement algorithms, such as Automatic Color Equalization (ACE), Adaptive Contrast Enhancement (ACE), Adaptive Histgram Equalization (AHE), Contrast Limited Adaptive Histgram Equalization (CLAHE), etc.
[0052] Furthermore, the automatic color equalization algorithm takes into account the spatial position relationship between color and brightness in the image, performs adaptive filtering of local characteristics, and realizes image brightness and color adjustment and contrast adjustment with local and nonlinear characteristics, while satisfying the gray world theory hypothesis and the white spot hypothesis.
[0053] The adaptive contrast enhancement algorithm can divide an image into two parts: one is the low-frequency part, which can be obtained by filtering the image; the other is the high-frequency part, which can be obtained by subtracting the low-frequency part from the original image. The goal of the algorithm is to enhance the high-frequency part representing the details, that is, to gain the high-frequency part and then reconstruct the enhanced image.
[0054] In practical applications, since the adaptive contrast enhancement algorithm can better distinguish the ridges and valleys in the fingerprint, in one implementation, contrast enhancement is performed on the grayscale image to obtain a contrast enhanced image, which may include: using an adaptive contrast enhancement algorithm to contrast enhance the grayscale image to obtain a contrast enhanced image.
[0055] Specifically, contrast enhancement can be performed through the following steps:
[0056] First, obtain the low-frequency unsharp mask part. For grayscale images, mean filtering can be performed on the local area centered on the pixel to obtain a relatively smooth and blurred low-frequency image.
[0057] Secondly, the high-frequency components of the image can be obtained by subtracting the low-frequency image from the original grayscale image.
[0058] Thirdly, the contrast gain (CG) can be used to amplify the high-frequency components and add them to the low-frequency image. The contrast gain (CG) can be calculated by dividing the grayscale average by the local variance of each pixel. Therefore, at the edge of the image, the local variance is relatively large and the CG is relatively small, which plays a suppressive role. In the smooth area, the local variance is relatively small and the CG is relatively large. By placing certain restrictions on the maximum value of the CG, noise can be effectively suppressed.
[0059] After the image is processed by the adaptive contrast enhancement algorithm, the ridge information can be significantly deepened and the valley information can be weakened, so that the ridges and valleys can be distinguished more clearly, and then the fingerprint features can be extracted more accurately in the subsequent feature extraction. Therefore, this method is very suitable for contrast enhancement processing of fingerprint images.
[0060] like Figure 3 As shown, this is a fingerprint image obtained by an adaptive contrast enhancement algorithm. It can be clearly seen that the ridges and valleys are quite obvious.
[0061] In practical applications, in order to make the features in the fingerprint image more obvious, the image may be subjected to noise reduction. Therefore, in one embodiment, the method may further include: performing image noise reduction on the contrast-enhanced image to obtain a noise-reduced image.
[0062] Image Denoising: Digital images are often affected by the noise interference of imaging devices and external environment during digitization and transmission, which are called noisy images or noisy images. The process of reducing noise in digital images is called image denoising, sometimes also called image denoising.
[0063] There are many types of image denoising, such as spatial domain methods, frequency domain methods, spatial and frequency domain methods, methods based on partial differential equations, etc.
[0064] Specifically, among the spatial domain and frequency domain methods, there is a three-dimensional block matching filter (BM3D), which finds two-dimensional image blocks similar to the reference block through similarity judgment, and combines similar blocks into three-dimensional groups, performs collaborative filtering on the three-dimensional groups, and then aggregates the processing results to the position of the original image block. Since there are many similar image areas in the fingerprint image, this algorithm can better reduce the noise of the fingerprint image.
[0065] Therefore, in one implementation, performing image noise reduction on the contrast enhanced image to obtain a noise-reduced image may include: performing image noise reduction on the contrast enhanced image using a three-dimensional block matching algorithm to obtain a noise-reduced image.
[0066] Specifically, noise reduction can be achieved through the following steps:
[0067] First, similar blocks of the image can be estimated. Several blocks with the smallest difference are found in the surrounding area of the reference block, that is, the Euclidean distance is used to judge the difference between image blocks. If the difference is less than a certain threshold, the two image blocks are considered similar, and these similar blocks are combined into a three-dimensional matrix.
[0068] Secondly, a DCT transform is performed on the array of pixels at the same position of each similar three-dimensional image group, and the components smaller than the threshold value can be set to 0, and then an inverse transform is performed.
[0069] Again, these blocks can be inversely transformed and put back in place, and the weights can be superimposed using the number of non-zero components. Finally, the superimposed image can be divided by the weight of each point to obtain the basic estimated image. At this time, the noise points of the image are largely removed.
[0070] like Figure 4 As shown, for Figure 3 , that is, the image after BM3D denoising after contrast enhancement, it can be seen that the image is relatively smooth and the larger noise is removed. For fingerprint images, this denoising method is very suitable.
[0071] Step 108: Extract fingerprint features from the contrast-enhanced image, and perform fingerprint recognition based on the extraction result.
[0072] After the above steps, a contrast-enhanced fingerprint image is obtained. In this step, fingerprint features can be extracted from the image, and fingerprint recognition can be performed based on the extracted results. Specifically, the arrangement features of the ridges and valleys in the fingerprint can be extracted.
[0073] As mentioned above, the image can be denoised. In order to extract fingerprint features more accurately, in one embodiment, fingerprint features are extracted from the contrast-enhanced image, and fingerprint recognition is performed based on the extraction results. This may include: fingerprint features are extracted from the denoised image, and fingerprint recognition is performed based on the extraction results.
[0074] like Figure 5 , which is a schematic diagram of extracting fingerprint features from a denoised image, in which the arrangement features of ridges and valleys may be included.
[0075] According to the above introduction, multiple fingerprint images continuously collected by the non-contact image acquisition device can be obtained. Then in this step, in order to be able to perform fingerprint recognition more accurately, in one embodiment, fingerprint recognition is performed based on the extraction results, which may include: fingerprint recognition based on multiple extraction results.
[0076] Specifically, the filtering, grayscale, contrast enhancement, and noise reduction processes in the above steps may be performed on each acquired fingerprint image, and fingerprint feature extraction may be performed, thereby obtaining multiple groups of extraction results corresponding to each fingerprint image.
[0077] When performing fingerprint recognition, based on different recognition strategies, multiple groups of results can be used for recognition at the same time, and the recognition result can be determined based on the probability of successful recognition; or as long as one group of recognition is successful, it can be determined that the recognition is successful, etc.
[0078] like Figure 6 As shown, it is a schematic diagram of the fingerprint recognition method. At the beginning, the RGB image can be obtained first, and then the image can be filtered and grayscale processed, and then ACE contrast enhancement and BM3D image denoising can be performed, and finally the feature extraction of the denoised image can be performed, and fingerprint recognition can be performed based on the extraction result.
[0079] It can be seen from the method provided in the above embodiment that a fingerprint image collected by a non-contact image acquisition device can be first obtained, and then filtering and grayscale processing can be performed based on the fingerprint image, and then the grayscale image can be contrast enhanced, so as to extract fingerprint features based on the contrast enhanced image, and fingerprint recognition can be performed based on the extraction result.
[0080] That is, a non-contact image acquisition device can be used to collect fingerprint images that are nearly distortion-free, and through image processing methods such as filtering, grayscale, and contrast enhancement, the contrast between the ridges and valleys in the fingerprint can be improved, thereby enabling more accurate fingerprint recognition.
[0081] In actual scenarios, it can be applied to access control authentication. For example, a camera can be installed on the access control device. When fingerprint recognition is required, the user can lift the finger to a certain distance from the camera so that the camera can collect the fingerprint image, thereby performing fingerprint recognition and achieving access control authentication. Of course, in actual applications, the fingerprint images of five fingers can be recognized at the same time, and fingerprint recognition and authentication can be performed using five fingers.
[0082] Example 2
[0083] Based on the same concept, the second embodiment of the present application provides a fingerprint recognition device that can perform fingerprint recognition more accurately. The structural diagram of the device is shown in FIG. Figure 7 As shown, it includes: an image acquisition unit 202, an image processing unit 204, and a fingerprint recognition unit 206, wherein:
[0084] The image acquisition unit 202 may be used to acquire a fingerprint image acquired by a non-contact image acquisition device;
[0085] The image processing unit 204 may be used to perform filtering and grayscale processing on the fingerprint image to obtain a grayscale image;
[0086] The image processing unit 204 may be used to perform contrast enhancement on the grayscale image to obtain a contrast enhanced image;
[0087] The fingerprint recognition unit 206 may be used to extract fingerprint features from the contrast-enhanced image and perform fingerprint recognition based on the extraction result.
[0088] In one embodiment, the image processing unit 204 may also be used to: extract fingerprint features from the contrast-enhanced image, and before performing fingerprint recognition based on the extracted results,
[0089] Performing image denoising on the contrast-enhanced image to obtain a denoised image;
[0090] The fingerprint recognition unit 206 may be used to:
[0091] The fingerprint features are extracted from the denoised image, and fingerprint recognition is performed based on the extraction results.
[0092] In one implementation, the image processing unit 204 may be configured to:
[0093] The contrast of the grayscale image is enhanced by using an adaptive contrast enhancement algorithm to obtain a contrast enhanced image.
[0094] In one implementation, the image processing unit 204 may be configured to:
[0095] The image after contrast enhancement is subjected to image denoising by using a three-dimensional block matching algorithm to obtain a denoised image.
[0096] In one implementation, the image acquisition unit 202 may be used to:
[0097] acquiring an image acquired by a non-contact image acquisition device;
[0098] Perform image recognition on the image;
[0099] Based on the image recognition result, a fingerprint image containing the fingerprint is cut out from the collected image.
[0100] In one implementation, the image acquisition unit 202 may be used to:
[0101] Acquire multiple fingerprint images continuously collected by a non-contact image acquisition device;
[0102] Fingerprint recognition is performed based on the extraction results, including:
[0103] Fingerprint recognition is performed based on multiple extraction results.
[0104] It can be seen from the method provided in the above embodiment that a fingerprint image collected by a non-contact image acquisition device can be first obtained, and then filtering and grayscale processing can be performed based on the fingerprint image, and then the grayscale image can be contrast enhanced, so as to extract fingerprint features based on the contrast enhanced image, and fingerprint recognition can be performed based on the extraction result.
[0105] That is, a non-contact image acquisition device can be used to collect fingerprint images that are nearly distortion-free, and through image processing methods such as filtering, grayscale, and contrast enhancement, the contrast between the ridges and valleys in the fingerprint can be improved, thereby enabling more accurate fingerprint recognition.
[0106] Figure 8 It is a schematic diagram of the structure of an electronic device of an embodiment of the present application. At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. Among them, the memory may include a memory, such as a high-speed random access memory (Random-Access Memory, RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage, etc. Of course, the electronic device may also include hardware required for other services.
[0107] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0108] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.
[0109] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a fingerprint recognition device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:
[0110] Acquiring a fingerprint image collected by a non-contact image acquisition device;
[0111] Performing filtering and grayscale processing on the fingerprint image to obtain a grayscale image;
[0112] Performing contrast enhancement on the grayscale image to obtain a contrast-enhanced image;
[0113] Fingerprint features are extracted from the contrast-enhanced image, and fingerprint recognition is performed based on the extraction result.
[0114] The above application Figure 7 The method performed by the fingerprint recognition device provided in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or instructions in the form of software. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The various methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.
[0115] The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.
[0116] The electronic device may also perform Figure 7 The fingerprint recognition device provided by the embodiment shown in the figure is Figure 8 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.
[0117] The present application also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, enable the electronic device to execute Figure 7 The method performed by the fingerprint recognition device in the illustrated embodiment is specifically used to perform:
[0118] Acquiring a fingerprint image collected by a non-contact image acquisition device;
[0119] Performing filtering and grayscale processing on the fingerprint image to obtain a grayscale image;
[0120] Performing contrast enhancement on the grayscale image to obtain a contrast-enhanced image;
[0121] Fingerprint features are extracted from the contrast-enhanced image, and fingerprint recognition is performed based on the extraction result.
[0122] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
[0123] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.
[0124] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.
[0125] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0126] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0127] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0128] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0129] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0130] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0131] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0132] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0133] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.
[0134] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0135] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A fingerprint recognition method, characterized in that: include: Acquiring a fingerprint image collected by a non-contact image acquisition device; Performing filtering and grayscale processing on the fingerprint image to obtain a grayscale image; Performing contrast enhancement on the grayscale image to obtain a contrast-enhanced image; Extracting fingerprint features from the contrast-enhanced image, and performing fingerprint recognition based on the extraction result; The performing filtering and grayscale processing on the fingerprint image to obtain a grayscale image includes: Performing filtering processing on the fingerprint image; Mapping each pixel of the filtered image to a corresponding grayscale through a preset mapping method to obtain the grayscale image; The step of performing contrast enhancement on the grayscale image to obtain a contrast enhanced image includes: Using an adaptive contrast enhancement algorithm, the contrast of the grayscale image is enhanced to obtain a contrast-enhanced image; The step of using an adaptive contrast enhancement algorithm to perform contrast enhancement on the grayscale image to obtain a contrast-enhanced image includes: Performing mean filtering on a local area with pixels of the grayscale image as the center to obtain a low-frequency image; Subtracting the low-frequency image from the grayscale image to obtain a high-frequency component of the grayscale image; The high frequency component is amplified using a contrast gain, and the amplified high frequency component is added to the low frequency image to obtain the contrast enhanced image, wherein the contrast gain is obtained by dividing the grayscale average by the local variance of each pixel.
2. The method according to claim 1, characterized in that Before extracting fingerprint features from the contrast-enhanced image and performing fingerprint recognition based on the extraction results, the method further includes: Performing image denoising on the contrast-enhanced image to obtain a denoised image; Extracting fingerprint features from the contrast-enhanced image and performing fingerprint recognition based on the extraction result, including: Fingerprint features are extracted from the denoised image, and fingerprint recognition is performed based on the extraction result.
3. The method according to claim 2, characterized in that Performing image denoising on the contrast-enhanced image to obtain a denoised image includes: The image after contrast enhancement is subjected to image denoising by using a three-dimensional block matching algorithm to obtain a denoised image.
4. The method according to claim 1, characterized in that Acquire fingerprint images collected by non-contact image acquisition equipment, including: acquiring an image acquired by a non-contact image acquisition device; performing image recognition on the image; Based on the image recognition result, a fingerprint image containing the fingerprint is cut out from the collected image.
5. The method according to claim 1, characterized in that Acquire fingerprint images collected by non-contact image acquisition equipment, including: Acquire multiple fingerprint images continuously collected by a non-contact image acquisition device; Fingerprint recognition is performed based on the extraction results, including: Fingerprint recognition is performed based on multiple extraction results.
6. A fingerprint recognition device, characterized in that: include: An image acquisition unit, an image processing unit, and a fingerprint recognition unit, wherein: The image acquisition unit is used to acquire the fingerprint image acquired by the non-contact image acquisition device; The image processing unit is used to perform filtering and grayscale processing on the fingerprint image to obtain a grayscale image; The image processing unit is used to perform contrast enhancement on the grayscale image to obtain a contrast-enhanced image; The fingerprint recognition unit is used to extract fingerprint features from the contrast-enhanced image and perform fingerprint recognition based on the extraction result; The image processing unit is used for: Performing filtering processing on the fingerprint image; Mapping each pixel of the filtered image to a corresponding grayscale through a preset mapping method to obtain the grayscale image; The image processing unit is used for: Using an adaptive contrast enhancement algorithm, the contrast of the grayscale image is enhanced to obtain a contrast-enhanced image; The image processing unit is used for: Performing mean filtering on a local area with pixels of the grayscale image as the center to obtain a low-frequency image; Subtracting the low-frequency image from the grayscale image to obtain a high-frequency component of the grayscale image; The high frequency component is amplified using a contrast gain, and the amplified high frequency component is added to the low frequency image to obtain the contrast enhanced image, wherein the contrast gain is obtained by dividing the grayscale average by the local variance of each pixel.
7. The device according to claim 6, characterized in that The image processing unit is further used to: extract fingerprint features from the contrast-enhanced image, and before performing fingerprint recognition based on the extraction result, Performing image denoising on the contrast-enhanced image to obtain a denoised image; The fingerprint recognition unit is used for: Fingerprint features are extracted from the denoised image, and fingerprint recognition is performed based on the extraction result.
8. An electronic device, comprising: processor; as well as A memory configured to store computer executable instructions which, when executed, cause the processor to: Acquiring a fingerprint image collected by a non-contact image acquisition device; Performing filtering and grayscale processing on the fingerprint image to obtain a grayscale image; Performing contrast enhancement on the grayscale image to obtain a contrast-enhanced image; Extracting fingerprint features from the contrast-enhanced image, and performing fingerprint recognition based on the extraction result; The performing filtering and grayscale processing on the fingerprint image to obtain a grayscale image includes: Performing filtering processing on the fingerprint image; Mapping each pixel of the filtered image to a corresponding grayscale through a preset mapping method to obtain the grayscale image; The step of performing contrast enhancement on the grayscale image to obtain a contrast enhanced image includes: Using an adaptive contrast enhancement algorithm, the contrast of the grayscale image is enhanced to obtain a contrast-enhanced image; The step of using an adaptive contrast enhancement algorithm to perform contrast enhancement on the grayscale image to obtain a contrast-enhanced image includes: Performing mean filtering on a local area with pixels of the grayscale image as the center to obtain a low-frequency image; Subtracting the low-frequency image from the grayscale image to obtain a high-frequency component of the grayscale image; The high frequency component is amplified using a contrast gain, and the amplified high frequency component is added to the low frequency image to obtain the contrast enhanced image, wherein the contrast gain is obtained by dividing the grayscale average by the local variance of each pixel.
9. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, cause the electronic device to perform the following operations: Acquiring a fingerprint image collected by a non-contact image acquisition device; Performing filtering and grayscale processing on the fingerprint image to obtain a grayscale image; Performing contrast enhancement on the grayscale image to obtain a contrast-enhanced image; Extracting fingerprint features from the contrast-enhanced image, and performing fingerprint recognition based on the extraction result; The performing filtering and grayscale processing on the fingerprint image to obtain a grayscale image includes: Performing filtering processing on the fingerprint image; Mapping each pixel of the filtered image to a corresponding grayscale through a preset mapping method to obtain the grayscale image; The step of performing contrast enhancement on the grayscale image to obtain a contrast enhanced image includes: Using an adaptive contrast enhancement algorithm, the contrast of the grayscale image is enhanced to obtain a contrast-enhanced image; The step of using an adaptive contrast enhancement algorithm to perform contrast enhancement on the grayscale image to obtain a contrast-enhanced image includes: Performing mean filtering on a local area with pixels of the grayscale image as the center to obtain a low-frequency image; Subtracting the low-frequency image from the grayscale image to obtain a high-frequency component of the grayscale image; The high frequency component is amplified using a contrast gain, and the amplified high frequency component is added to the low frequency image to obtain the contrast enhanced image, wherein the contrast gain is obtained by dividing the grayscale average by the local variance of each pixel.
Citation Information
Patent Citations
Method for reinforcing fingerprint image based on one-dimensional filtering
CN101329726A
Electronic lock system achieving recognition through fingerprints
CN105788048A
A fingerprint image enhancement method based on phase stretching transformation
CN109544474A
Image processing method and device for fingerprint identification
CN110728201A
