WO2020199178A1 - 指纹识别的方法、装置和电子设备 - Google Patents

指纹识别的方法、装置和电子设备 Download PDF

Info

Publication number
WO2020199178A1
WO2020199178A1 PCT/CN2019/081427 CN2019081427W WO2020199178A1 WO 2020199178 A1 WO2020199178 A1 WO 2020199178A1 CN 2019081427 W CN2019081427 W CN 2019081427W WO 2020199178 A1 WO2020199178 A1 WO 2020199178A1
Authority
WO
WIPO (PCT)
Prior art keywords
fingerprint
template
image
frame
data
Prior art date
Application number
PCT/CN2019/081427
Other languages
English (en)
French (fr)
Inventor
李彦青
Original Assignee
深圳市汇顶科技股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市汇顶科技股份有限公司 filed Critical 深圳市汇顶科技股份有限公司
Priority to CN201980000496.3A priority Critical patent/CN110199295A/zh
Priority to PCT/CN2019/081427 priority patent/WO2020199178A1/zh
Publication of WO2020199178A1 publication Critical patent/WO2020199178A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/757—Matching configurations of points or features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12—Fingerprints or palmprints
    • G06V40/13—Sensors therefor
    • G06V40/1318—Sensors therefor using electro-optical elements or layers, e.g. electroluminescent sensing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12—Fingerprints or palmprints
    • G06V40/1347—Preprocessing; Feature extraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12—Fingerprints or palmprints
    • G06V40/1365—Matching; Classification

Definitions

  • the embodiments of the present application relate to the field of biometric identification, and more specifically, to methods, devices, and electronic equipment for fingerprint identification.
  • the fingerprint image collected in the optical fingerprint recognition technology has a higher resolution, and the amount of data contained in the fingerprint image is also larger. It takes time to process the fingerprint image. Longer. Especially when the user has registered multiple fingerprint templates, the speed of fingerprint recognition is obviously affected, which affects the user experience.
  • the embodiments of the present application provide a fingerprint recognition method, device, and electronic equipment, which can increase the speed of fingerprint recognition and improve user experience.
  • a fingerprint recognition method which includes: processing at least one frame of fingerprint image to obtain characteristic data of the at least one frame of fingerprint image; according to the characteristic data of the at least one frame of fingerprint image and the first When fingerprint identification is performed on the template data of a fingerprint template, the second fingerprint template is processed in parallel to obtain the template data of the second fingerprint template.
  • the method further includes: when processing the at least one frame of fingerprint image, processing the first fingerprint template in parallel to obtain template data of the first fingerprint template .
  • the processing at least one frame of fingerprint images includes: processing the at least one frame of fingerprint images in parallel.
  • the method further includes: if fingerprint recognition is successful based on the characteristic data of any one of the at least one fingerprint image and the template data of the first fingerprint template, then Confirm that the fingerprint recognition is successful.
  • the method further includes: if fingerprint recognition fails according to the feature data of the at least one frame of fingerprint image and the template data of the first fingerprint template, then according to the at least one frame of fingerprint image
  • the characteristic data and the template data of the second fingerprint template perform fingerprint identification.
  • processing the first frame of the fingerprint image in the at least one frame of fingerprint image includes: performing image preprocessing on the first frame of fingerprint image; based on the first frame after image preprocessing Fingerprint image, perform feature extraction twice in parallel to obtain the first feature data and second feature data of the first frame of fingerprint image respectively, wherein the first feature data is the first frame of fingerprint after image preprocessing
  • the image is obtained by feature extraction
  • the second feature data is obtained by performing image enhancement on the first fingerprint image after image preprocessing and then performing feature extraction.
  • the performing fingerprint recognition based on the feature data of the at least one frame of fingerprint image and the template data of the first fingerprint template includes: if the first feature data and the first fingerprint If the template data of the template fails to perform fingerprint recognition, the fingerprint recognition is performed according to the second characteristic data and the template data of the first fingerprint template.
  • processing the fingerprint image of the non-first frame in the at least one frame of fingerprint image includes: sequentially performing image preprocessing, image enhancement, and feature extraction on the non-first frame of fingerprint image.
  • the processing the second fingerprint template includes: decrypting and decompressing the second fingerprint template.
  • the method is executed by a first processing unit and a second processing unit, the first processing unit is configured to process the at least one frame of fingerprint image and perform fingerprint recognition, and the first The second processing unit is used to process at least one fingerprint template.
  • the first processing unit is, for example, a CPU, a DSP, or a VPU.
  • the second processing unit is, for example, a CPU, a DSP, or a VPU.
  • the type of the first processing unit and the second processing unit are the same or different.
  • the CPU is, for example, an ARM.
  • a fingerprint recognition device including:
  • the first processing unit is configured to process at least one frame of fingerprint image to obtain characteristic data of the at least one frame of fingerprint image; and perform fingerprinting according to the characteristic data of the at least one frame of fingerprint image and the template data of the first fingerprint template Identify
  • the second processing unit is configured to process the second fingerprint template in parallel when the first processing unit performs fingerprint identification based on the characteristic data of the at least one frame of fingerprint image and the template data of the first fingerprint template respectively To obtain the template data of the second fingerprint template.
  • the second processing unit is further configured to process the first fingerprint template in parallel when the first processing unit processes the at least one frame of fingerprint image, Obtain template data of the first fingerprint template.
  • the first processing unit is specifically configured to process the at least one frame of fingerprint image in parallel.
  • the first processing unit is further configured to perform fingerprinting based on the characteristic data of any one of the at least one fingerprint image and the template data of the first fingerprint template. If the recognition is successful, it is determined that the fingerprint recognition is successful.
  • the first processing unit is further configured to: if fingerprint recognition fails according to the feature data of the at least one frame of fingerprint image and the template data of the first fingerprint template, then according to the at least one The feature data of the frame fingerprint image and the template data of the second fingerprint template are fingerprinted.
  • the first processing unit is specifically configured to: perform image preprocessing on the first frame of fingerprint image; perform two features in parallel based on the first frame of fingerprint image after image preprocessing. Extraction to obtain the first feature data and the second feature data of the first frame of fingerprint image respectively, wherein the first feature data is obtained by performing feature extraction on the first frame of fingerprint image after image preprocessing, the The second feature data is obtained by performing image enhancement on the first fingerprint image after image preprocessing, and then performing feature extraction.
  • the first processing unit is specifically configured to: if fingerprint recognition fails according to the first characteristic data and template data of the first fingerprint template, then according to the second characteristic data Perform fingerprint identification with the template data of the first fingerprint template.
  • the first processing unit is specifically configured to: sequentially perform image preprocessing, image enhancement, and feature extraction on the fingerprint image of the non-first frame.
  • the second processing unit is specifically configured to: decrypt and decompress the second fingerprint template.
  • the first processing unit is, for example, a CPU, a DSP, or a VPU.
  • the second processing unit is, for example, a CPU, a DSP, or a VPU.
  • the type of the first processing unit and the second processing unit are the same or different.
  • the CPU is, for example, an ARM.
  • the CPU is an advanced reduced instruction set machine ARM.
  • a chip for implementing the above-mentioned first aspect or any possible implementation of the first aspect.
  • the chip includes a processor, configured to call and run a computer program from the memory, so that a device installed with the chip executes the method in the first aspect or any possible implementation of the first aspect.
  • a computer-readable storage medium for storing a computer program that enables a computer to execute the method in the first aspect or any possible implementation of the first aspect.
  • an electronic device including the fingerprint recognition device in the second aspect or any possible implementation of the second aspect.
  • the second fingerprint template is processed in parallel.
  • the fingerprint image and the The fingerprint template performs fingerprint recognition without waiting for the processing time of the second fingerprint template, thereby increasing the speed of fingerprint recognition and improving user experience.
  • Fig. 1 is a schematic diagram of the structure of an electronic device to which this application can be applied.
  • Fig. 2 is a schematic cross-sectional view of the electronic device shown in Fig. 1 along the A-A' direction.
  • Fig. 3 is a schematic flowchart of a fingerprint identification method used in the related art.
  • Fig. 4 is a schematic flowchart of a fingerprint identification method according to an embodiment of the present application.
  • FIG. 5 is a flowchart of a possible implementation manner of the fingerprint identification method in an embodiment of the present application.
  • FIG. 6 is a flowchart of a possible implementation manner of the fingerprint identification method in the embodiment of the present application.
  • FIG. 7 is a flowchart of a possible implementation manner of the fingerprint identification method in an embodiment of the present application.
  • Fig. 8 is a schematic block diagram of a fingerprint identification device according to an embodiment of the present application.
  • embodiments of this application can be applied to optical fingerprint systems, including but not limited to optical fingerprint identification systems and medical diagnostic products based on optical fingerprint imaging.
  • the embodiments of this application only take optical fingerprint systems as an example for description, but should not The embodiments of the application constitute any limitation, and the embodiments of the present application are also applicable to other systems using optical imaging technology.
  • the optical fingerprint system provided in the embodiments of this application can be applied to smart phones, tablet computers, and other mobile terminals with display screens or other terminal devices; more specifically, in the above-mentioned terminal devices, the optical fingerprint
  • the module may be specifically an optical fingerprint module, which may be arranged in a partial area or the entire area below the display screen to form an under-display or under-screen optical fingerprint system.
  • the optical fingerprint module can also be partially or fully integrated into the display screen of the terminal device to form an in-display or in-screen optical fingerprint system.
  • FIG. 1 is a schematic diagram of the electronic device 10
  • FIG. 2 is a schematic cross-sectional view of the electronic device 10 shown in FIG. 1 along the A-A' direction.
  • the terminal device 10 includes a display screen 120 and an optical fingerprint module 130.
  • the optical fingerprint module 130 is arranged in a partial area below the display screen 120.
  • the optical fingerprint module 130 includes an optical fingerprint sensor, and the optical fingerprint sensor includes a sensing array 133 having a plurality of optical sensing units 131.
  • the area where the sensing array 133 is located or its sensing area is the fingerprint detection area 121 of the optical fingerprint module 130 (also referred to as fingerprint collection area, fingerprint recognition area, etc.). As shown in FIG. 1, the fingerprint detection area 121 is located in the display area of the display screen 120.
  • the optical fingerprint module 130 may also be arranged in other positions, such as the side of the display screen 120 or the non-transparent area of the edge of the terminal device 10, and the optical fingerprint module 130 The optical signal of at least part of the display area of the display screen 120 is guided to the optical fingerprint module 130 so that the fingerprint detection area 121 is actually located in the display area of the display screen 120.
  • the area of the fingerprint detection area 121 may be different from the area of the sensing array 133 of the optical fingerprint module 130, for example, through an optical path design such as lens imaging, a reflective folding optical path design, or other optical paths such as light convergence or reflection.
  • the design can make the area of the fingerprint detection area 121 of the optical fingerprint module 130 larger than the area of the sensing array 133 of the optical fingerprint module 130.
  • the fingerprint detection area 121 of the optical fingerprint module 130 can also be designed to be substantially the same as the area of the sensing array of the optical fingerprint module 130.
  • the terminal device 10 adopting the above structure does not need to reserve a space on the front side for the fingerprint button (such as the Home button), so that a full screen solution can be adopted, that is, the display area of the display screen 120 It can be basically extended to the front of the entire terminal device 10.
  • the optical fingerprint module 130 includes a light detection part 134 and an optical component 132.
  • the light detection part 134 includes the sensing array 133, a reading circuit electrically connected to the sensing array 133, and other auxiliary circuits, which can be fabricated on a chip (Die) by a semiconductor process, such as an optical imaging chip or Optical fingerprint sensor.
  • the sensing array 133 is specifically a photodetector (photodetector) array, which includes a plurality of photodetectors distributed in an array, and the photodetectors can be used as the optical sensing unit as described above.
  • the optical component 132 may be disposed above the sensing array 133 of the light detecting part 134, and it may specifically include a filter layer (Filter), a light guide layer or a light path guiding structure, and other optical elements.
  • the filter layer It can be used to filter out ambient light penetrating the finger, and the light guide layer or light path guiding structure is mainly used to guide the reflected light reflected from the surface of the finger to the sensor array 133 for optical detection.
  • the optical assembly 132 and the light detecting part 134 may be packaged in the same optical fingerprint component.
  • the optical component 132 and the optical detection part 134 can be packaged in the same optical fingerprint chip, or the optical component 132 can be arranged outside the chip where the optical detection part 134 is located, for example, the optical component 132 is attached above the chip, or some components of the optical assembly 132 are integrated into the chip.
  • the light guide layer or light path guiding structure of the optical component 132 has multiple implementation schemes.
  • the light guide layer may specifically be a collimator layer made on a semiconductor silicon wafer, which has multiple A collimating unit or a micro-hole array.
  • the collimating unit can be specifically a small hole.
  • the reflected light reflected from the finger the light that is perpendicularly incident on the collimating unit can pass through and be passed by the optical sensing unit below it.
  • the light with an excessively large incident angle is attenuated by multiple reflections inside the collimating unit. Therefore, each optical sensing unit can basically only receive the reflected light reflected by the fingerprint pattern directly above it.
  • the sensing array 133 can detect the fingerprint image of the finger.
  • the light guide layer or the light path guide structure may also be an optical lens (Lens) layer, which has one or more lens units, such as a lens group composed of one or more aspheric lenses, which The sensing array 133 of the light detecting part 134 is used to converge the reflected light reflected from the finger to the sensing array 133 of the light detection part 134 below, so that the sensing array 133 can perform imaging based on the reflected light, thereby obtaining a fingerprint image of the finger.
  • the optical lens layer may further have a pinhole formed in the optical path of the lens unit, and the pinhole may cooperate with the optical lens layer to expand the field of view of the optical fingerprint module 130 to improve The fingerprint imaging effect of the optical fingerprint module 130 is described.
  • the light guide layer or the light path guide structure may also specifically adopt a micro-lens (Micro-Lens) layer.
  • the micro-lens layer has a micro-lens array formed by a plurality of micro-lenses, which can be grown by semiconductors.
  • a process or other processes are formed above the sensing array 133 of the light detecting part 134, and each microlens may correspond to one of the sensing units of the sensing array 133, respectively.
  • other optical film layers may be formed between the microlens layer and the sensing unit, such as a dielectric layer or a passivation layer.
  • a light blocking layer (or called a light shielding layer) with microholes may also be included, wherein the microholes are formed between the corresponding microlens and the sensing unit.
  • the light blocking layer can block the optical interference between the adjacent microlens and the sensing unit, and make the light corresponding to the sensing unit converge into the microhole through the microlens and pass through the microhole. It is transmitted to the sensing unit for optical fingerprint imaging.
  • a micro lens layer may be further provided above or below the collimator layer or the optical lens layer.
  • the collimator layer or the optical lens layer is used in combination with the micro lens layer, its specific laminated structure or optical path may need to be adjusted according to actual needs.
  • the display screen 120 may be a display screen with a self-luminous display unit, such as an organic light-emitting diode (Organic Light-Emitting Diode, OLED) display or a micro-LED (Micro-LED) display Screen.
  • OLED Organic Light-Emitting Diode
  • the optical fingerprint module 130 may use the display unit (ie, an OLED light source) of the OLED display screen 120 located in the fingerprint detection area 121 as an excitation light source for optical fingerprint detection.
  • the display screen 120 emits a beam of light 111 to the target finger 140 above the fingerprint detection area 121.
  • the light 111 is reflected on the surface of the finger 140 to form reflected light or pass through all the fingers.
  • the finger 140 scatters to form scattered light.
  • the above-mentioned reflected light and scattered light are collectively referred to as reflected light. Because the ridge 141 and valley 142 of the fingerprint have different light reflection capabilities, the reflected light 151 from the fingerprint ridge and the reflected light 152 from the fingerprint valley have different light intensities, and the reflected light passes through the optical component 132.
  • the terminal device 10 realizes the optical fingerprint recognition function.
  • the optical fingerprint module 130 may also use a built-in light source or an external light source to provide an optical signal for fingerprint detection.
  • the optical fingerprint module 130 may be suitable for non-self-luminous display screens, such as liquid crystal display screens or other passively-luminous display screens.
  • the optical fingerprint system of the terminal device 10 may also include an excitation light source for optical fingerprint detection.
  • the excitation light source may specifically be an infrared light source or a light source of invisible light of a specific wavelength, which may be arranged under the backlight module of the liquid crystal display or arranged in the edge area under the protective cover of the terminal device 10, and the
  • the optical fingerprint module 130 may be arranged under the edge area of the liquid crystal panel or the protective cover and guided by the light path so that the fingerprint detection light can reach the optical fingerprint module 130; or, the optical fingerprint module 130 may also be arranged at all Below the backlight module, and the backlight module is designed to allow the fingerprint detection light to pass through the liquid crystal panel and the backlight module and reach the optical Fingerprint module 130.
  • the optical fingerprint module 130 uses a built-in light source or an external light source to provide an optical signal for fingerprint detection, the detection principle is the same as that described above.
  • the terminal device 10 further includes a transparent protective cover, and the cover may be a glass cover or a sapphire cover, which is located above the display screen 120 and covers the terminal.
  • the optical fingerprint module 130 may include only one optical fingerprint sensor.
  • the fingerprint detection area 121 of the optical fingerprint module 130 has a small area and a fixed position, so the user is performing During fingerprint input, it is necessary to press the finger to a specific position of the fingerprint detection area 121, otherwise the optical fingerprint module 130 may not be able to collect fingerprint images, resulting in poor user experience.
  • the optical fingerprint module 130 may specifically include multiple optical fingerprint sensors. The multiple optical fingerprint sensors may be arranged side by side under the display screen 120 in a splicing manner, and the sensing areas of the multiple optical fingerprint sensors collectively constitute the fingerprint detection area 121 of the optical fingerprint module 130.
  • the fingerprint detection area 121 of the optical fingerprint module 130 may include multiple sub-areas, and each sub-area corresponds to the sensing area of one of the optical fingerprint sensors, so that the fingerprint detection area of the optical fingerprint module 130 121 can be extended to the main area of the lower half of the display screen, that is, to the area where the finger is habitually pressed, so as to realize the blind fingerprint input operation.
  • the fingerprint detection area 130 can also be extended to half of the display area or even the entire display area, thereby realizing half-screen or full-screen fingerprint detection.
  • the fingerprint image collected by the optical fingerprint sensor needs to be processed and matched with the fingerprint template to obtain the result of fingerprint recognition.
  • Fingerprint template analysis refers to operations such as decryption and decompression of the fingerprint template after reading it, and the template data of the fingerprint template can be obtained.
  • the processing unit After the optical fingerprint sensor collects the fingerprint image, the processing unit performs image preprocessing on the fingerprint image, and performs feature extraction on the fingerprint image after the image preprocessing to obtain feature data of the fingerprint image. Fingerprint identification can be performed based on the characteristic data of the fingerprint image and the template data of the fingerprint template.
  • a user can register multiple fingerprint templates in an electronic device.
  • the fingerprint image needs to be matched with these fingerprint templates respectively. If the fingerprint image is successfully matched with a fingerprint template, the fingerprint recognition can be determined to be successful .
  • Fig. 3 shows a flowchart of a fingerprint identification method adopted in the related art.
  • the user has registered three fingerprint templates, namely fingerprint template 1, fingerprint template 2, and fingerprint template 3.
  • fingerprint template 1 fingerprint template 2
  • fingerprint template 3 fingerprint template 3.
  • the fingerprint template 1 is parsed and matched.
  • the fingerprint template 1 is parsed, and the obtained template data of the fingerprint template 1 is matched with the characteristic data of the fingerprint image to obtain the fingerprint identification result.
  • step 308 If the fingerprint recognition is successful, go to step 308; if the fingerprint recognition fails, go to step 303.
  • the fingerprint template 2 is parsed and matched.
  • the fingerprint template 2 is analyzed, and the obtained template data of the fingerprint template 2 is matched with the characteristic data of the fingerprint image to obtain the fingerprint identification result.
  • step 308 is executed; if the fingerprint identification fails, then step 305 is executed.
  • the fingerprint template 3 is parsed and matched.
  • the fingerprint template 3 is analyzed, and the obtained template data of the fingerprint template 3 is matched with the characteristic data of the fingerprint image to obtain the fingerprint identification result.
  • step 308 is executed; if the matching fails, step 307 is executed.
  • fingerprint identification is performed through a single thread.
  • a user registers multiple fingerprint templates, he can only parse each fingerprint template in turn and perform fingerprint matching, which results in longer time-consuming fingerprint recognition and affects user experience.
  • the embodiment of the present application provides a fingerprint recognition solution, which can increase the speed of fingerprint recognition and improve user experience by processing the fingerprint template and the fingerprint image in parallel.
  • FIG. 4 is a schematic flowchart of a method 400 for fingerprint identification according to an embodiment of the present application. As shown in FIG. 4, the method 400 includes some or all of the following steps.
  • At least one frame of fingerprint image is processed to obtain characteristic data of the at least one frame of fingerprint image.
  • the second fingerprint template is processed in parallel to obtain the template data of the second fingerprint template.
  • Perform fingerprint recognition based on the feature data of the fingerprint image and the template data of the fingerprint template which can refer to matching the feature data of the fingerprint image with the template data of the fingerprint template, for example, calculating the similarity between the feature data of the fingerprint image and the template data , So as to determine the fingerprint recognition result, for example, when the similarity is greater than the threshold, the fingerprint recognition is determined to be successful.
  • the method further includes: if fingerprint recognition is successful according to the characteristic data of any one of the fingerprint images in the at least one frame of fingerprint image and the template data of the first fingerprint template, then determining that the fingerprint recognition is successful.
  • the method further includes: if fingerprint recognition fails according to the characteristic data of the at least one frame of fingerprint image and the template data of the first fingerprint template, then according to the characteristic data of the at least one frame of fingerprint image and the second fingerprint template The template data is fingerprinted.
  • the at least one frame of fingerprint images may include one frame of fingerprint images or multiple frames of fingerprint images.
  • fingerprint recognition can be performed based on a retry strategy.
  • the Retry strategy means that when multiple frames of fingerprint images are collected, if fingerprint recognition is successful based on any one of the fingerprint images, then the fingerprint recognition can be considered successful.
  • the security level of the operation corresponding to fingerprint recognition it can also be set. If the fingerprint recognition is successful for part or all of the fingerprint images in the multi-frame fingerprint image, the fingerprint recognition can be considered as successful.
  • the embodiment of the application does not make any limitation on the number of at least one frame of fingerprint images, and does not set any limitation on the number of fingerprint templates registered by the user.
  • the at least one frame of fingerprint image collected by the optical fingerprint sensor is processed to obtain the characteristic data of the at least one frame of fingerprint image, and the characteristic data of the at least one frame of fingerprint image is separated from the template data of the first fingerprint template. Make a match.
  • the characteristic data of at least one frame of fingerprint image is matched with the template data of the first fingerprint template, the next fingerprint template, that is, the second fingerprint template, will be processed in parallel to obtain the template of the second fingerprint template data.
  • the feature data of the at least one frame of fingerprint image can continue to be matched with the template data of the second fingerprint template without waiting for the matching
  • the processing process of the second fingerprint template improves the efficiency of fingerprint identification and improves user experience.
  • the fingerprint identification and fingerprint template processing are performed in parallel, only two blocks of memory need to be allocated, and the size of each block of memory is the size required to store a fingerprint template or fingerprint image data. It is especially suitable for scenarios where the fingerprint template database is large but the memory resources are very limited.
  • the priority of the first fingerprint template here is higher than the priority of the second fingerprint template.
  • fingerprint templates with high priority are preferentially used for fingerprint identification. That is, in the order of priority from high to low, the fingerprint templates are processed sequentially to obtain template data and used for fingerprint identification.
  • the method further includes: when processing the at least one frame of fingerprint image, processing the first fingerprint template in parallel to obtain template data of the first fingerprint template.
  • the fingerprint image and the first fingerprint template can be processed in parallel, so that fingerprint recognition can be performed based on the characteristic data of the fingerprint image and the template data of the first fingerprint template. Therefore, the time for processing the first fingerprint template is saved, and the efficiency of fingerprint recognition is improved.
  • the at least one frame of fingerprint image includes only one frame of fingerprint image, and that the user has registered two fingerprint templates, namely, fingerprint template 1 and fingerprint template 2.
  • a fingerprint image is collected.
  • the fingerprint image is processed to obtain characteristic data of the fingerprint image.
  • steps 503 and 504 are performed in parallel.
  • fingerprint template 1 is read.
  • the fingerprint template 1 is processed to obtain template data 1.
  • 505 Perform fingerprint recognition according to the characteristic data of the fingerprint image and the template data 1.
  • steps 507 and 508 are performed in parallel.
  • fingerprint template 2 is read.
  • the fingerprint template 2 is processed to obtain template data 2.
  • step 509 is executed.
  • 509 Perform fingerprint identification according to the characteristic data of the fingerprint image and the template data 2.
  • thread 0 is used for fingerprint image processing and fingerprint identification
  • thread 1 is used for fingerprint template processing.
  • Thread 0 and thread 1 are executed in parallel.
  • the speed of fingerprint recognition is greatly improved and the user experience is improved.
  • processing at least one frame of fingerprint image includes: processing at least one frame of fingerprint image in parallel.
  • the optical fingerprint sensor can collect multiple frames of fingerprint images. Multiple threads can be used to process the multiple frames of fingerprint images in parallel, so as to obtain feature data of multiple frames of fingerprint images. If the matching fails according to the feature data of one frame of fingerprint image and the template data of a certain fingerprint template, the feature data of the next frame of fingerprint image can be matched with the template data of the fingerprint template.
  • the multiple threads may be multiple threads running in parallel on the same processing unit, for example, a CPU, or threads on different processing units that are independent of each other. That is, the method may be executed by one processing unit, or may be executed by multiple independent processing units.
  • the fingerprint identification method is executed by a first processing unit and a second processing unit.
  • the first processing unit is used to process at least one frame of fingerprint image and perform fingerprint recognition
  • the second processing unit is used to The fingerprint template is processed.
  • the first processing unit may be, for example, a central processing unit (CPU), a digital signal processor (Digital Signal Processor, DSP), a video processing unit (Video Processing Unit, VPU), and a graphics processor (Graphics Processing Unit, GPU), ready-made programmable gate array (Field Programmable Gate Array, FPGA), etc.
  • CPU central processing unit
  • DSP Digital Signal Processor
  • VPU Video Processing Unit
  • VPU graphics processor
  • GPU Graphics Processing Unit
  • FPGA Field Programmable Gate Array
  • the second processing unit may be, for example, a CPU, DSP, VPU, GPU, FPGA, or the like.
  • the CPU is, for example, an advanced reduced instruction set machine (Advanced RISCMachine, ARM), among which a reduced instruction set computer (Reduced Instruction Set Computer, RISC).
  • Advanced RISCMachine ARM
  • RISC Reduced Instruction Set Computer
  • the first processing unit and the second processing unit may be different processing units, and perform different operations in parallel.
  • the first processing unit is a DSP, which is used to perform fingerprint image processing and fingerprint recognition
  • the second processing unit is an ARM, which is used to perform fingerprint template processing.
  • the “parallel” in the embodiments of the present application refers to at least part of the simultaneous execution of multiple threads, and is not limited to the simultaneous start and/or end of two threads. For example, a certain thread may start execution first, and another thread may be started during the execution of the thread, and then the two threads may execute their respective operations in parallel, and the end moments of the two threads may also be the same or different.
  • the processing of the fingerprint image may include one or more of image preprocessing (hereinafter also referred to as preprocessing), image enhancement, and feature data extraction.
  • Image preprocessing may include, for example, filtering, convolution and other operations to eliminate interference signals such as noise in the fingerprint image.
  • Image enhancement can improve the quality of fingerprint images and enrich the amount of information in fingerprint images, thereby enhancing the effect of image interpretation and recognition.
  • the embodiment of the application does not limit the processing of the fingerprint image, and any fingerprint algorithm can be used to realize the processing of the fingerprint image.
  • processing the first fingerprint image in the at least one frame of fingerprint image includes: performing image preprocessing on the first fingerprint image; and performing two parallel operations on the first fingerprint image after image preprocessing.
  • the feature extraction is to obtain the first feature data and the second feature data of the first fingerprint image respectively.
  • the first feature data is obtained by performing feature extraction on the first fingerprint image after image preprocessing
  • the second feature data is obtained by performing image enhancement on the first fingerprint image after image preprocessing and then performing feature extraction. owned.
  • the first fingerprint image may be, for example, the first frame of fingerprint image, that is, the first frame of fingerprint image collected by the optical fingerprint sensor.
  • the first fingerprint image is taken as the first frame of fingerprint image as an example, but it is not limited to this.
  • the first fingerprint image may also be a non-first frame of fingerprint image.
  • performing fingerprint recognition based on the characteristic data of the at least one frame of fingerprint image and the template data of the first fingerprint template includes: if performing fingerprint recognition based on the first characteristic data and the template data of the first fingerprint template If it fails, fingerprint identification is performed according to the second characteristic data and the template data of the first fingerprint template.
  • the embodiment of the application may perform feature extraction twice on the first frame of the fingerprint image. After image preprocessing of the first frame of fingerprint image, feature extraction can be performed on the preprocessed first frame of fingerprint image to obtain the first feature data of the first frame of fingerprint image; in parallel, the preprocessed first frame of fingerprint image can be Perform image enhancement, and perform feature extraction after image enhancement, to obtain the second feature data of the first frame of fingerprint image.
  • the data amount of the second feature data is richer than the data amount of the first feature data. It can be understood that the second feature data is equivalent to the fine extraction of the first frame of fingerprint image, and the first feature data is equivalent to the rough extraction of the first frame of fingerprint image.
  • FIG. 6 Take Figure 6 as an example to illustrate the process of performing feature extraction twice on the first frame of fingerprint image.
  • thread 0 and thread 1 can be used to perform feature extraction twice to obtain the first feature data and second feature data of the first frame of fingerprint image.
  • the first frame of fingerprint image is collected.
  • image preprocessing is performed on the first frame of fingerprint image.
  • feature extraction is performed on the preprocessed fingerprint image to obtain the first feature data of the fingerprint image.
  • fingerprint identification is performed according to the template data of the fingerprint template and the first characteristic data.
  • steps 605 to 607 are performed in parallel.
  • feature extraction is performed on the fingerprint image after image enhancement to obtain second feature data of the fingerprint image.
  • fingerprint identification is performed according to the template data of the fingerprint template and the second characteristic data.
  • step 607 may not be performed; if the fingerprint recognition in step 604 fails, step 607 is performed. At this time, after determining that the fingerprint recognition in step 604 fails, fingerprint recognition can be performed directly based on the second feature data and template data. Since the extraction of the second feature data and the extraction of the first feature data are performed in parallel, there is no need to perform A longer wait.
  • processing the second fingerprint image in the at least one frame of fingerprint image includes: sequentially performing image preprocessing and feature extraction on the second fingerprint image; or sequentially performing image preprocessing on the second fingerprint image , Image enhancement and feature extraction.
  • the second fingerprint image may be, for example, a fingerprint image other than the first frame, such as the second frame fingerprint image and the third frame fingerprint image collected by the optical fingerprint sensor.
  • the second fingerprint image is a non-first frame fingerprint image as an example, but it is not limited to this, and the second fingerprint image may also be the first frame fingerprint image.
  • processing the fingerprint template may include, for example, decrypting and decompressing the read fingerprint template, which may also be referred to as parsing the fingerprint template.
  • the template data for fingerprint identification can be obtained, which can also be called the characteristic data of the fingerprint template.
  • Thread 0 to thread 4 are shown in FIG. 7.
  • Thread 0 to thread 4 may be 5 threads running in parallel on the same processor, or at least some of the threads 0 to 4 are running on different processors.
  • thread 0 is used to perform the reading and processing of the fingerprint template
  • thread 1 and thread 3 are both used to perform the processing and recognition of the first frame of fingerprint image
  • thread 2 is used to perform the processing and recognition of the second frame of fingerprint image
  • thread 4 is used to perform the processing and recognition of the third frame of fingerprint image.
  • fingerprint template 1 is read.
  • the fingerprint template 1 is processed to obtain the template data of the fingerprint template 1.
  • the fingerprint template 2 is processed to obtain the template data of the fingerprint template 2.
  • thread 1 is executed.
  • Steps 7101 to 7104 are run on thread 1.
  • the first frame of fingerprint image is acquired.
  • the first frame of fingerprint image is obtained from an optical fingerprint sensor.
  • feature extraction is performed on the preprocessed first frame of fingerprint image to obtain the first feature data of the first frame of fingerprint image.
  • fingerprint identification is performed according to the first feature data and the template data of the fingerprint template 1.
  • thread 3 is started.
  • Steps 7301 to 7303 are run on thread 3.
  • feature extraction is performed on the first frame of fingerprint image after image enhancement to obtain second feature data of the first frame of fingerprint image.
  • fingerprint identification is performed according to the second feature data and the template data of fingerprint template 1.
  • thread 2 is executed.
  • Thread 2 is used to run steps 7201 to 7205.
  • a second frame of fingerprint image is acquired.
  • the second frame of fingerprint image is obtained from an optical fingerprint sensor.
  • feature extraction is performed on the second frame of fingerprint image after image enhancement to obtain the feature data of the second frame of fingerprint image.
  • fingerprint identification is performed based on the feature data of the second frame of fingerprint image and the template data of fingerprint template 1.
  • thread 4 is executed.
  • Thread 4 is used to run steps 7401 to 7405.
  • the third frame of fingerprint image is acquired.
  • the third frame of fingerprint image is obtained from an optical fingerprint sensor.
  • feature extraction is performed on the third frame of fingerprint image after image enhancement to obtain the feature data of the second frame of fingerprint image.
  • fingerprint identification is performed based on the characteristic data of the third frame of fingerprint image and the template data of fingerprint template 1.
  • threads 0 to 4 can be processed in parallel.
  • steps 7101 to 7103 can be executed on thread 1 in parallel.
  • thread 0 and thread 1 can start at the same time.
  • thread 0 and thread 1 may not start at the same time.
  • thread 0 can be created before the finger is pressed, such as when powering on, and thread 1 can be created when the finger is pressed.
  • the thread 0 processes the fingerprint template 1 and obtains the template data, it can store the template data in the memory and wait for the creation of the thread 1.
  • 7201 to 7205 can be run on thread 2 in parallel, and 7401 to 7405 can be run on thread 4 in parallel, so as to respectively complete the identification of each frame of fingerprint image.
  • thread 0 When fingerprint recognition is performed on threads 1 to 4, thread 0 can read and process the next frame of fingerprint template, which is fingerprint template 2, in parallel.
  • Step 7500 can be executed on any thread.
  • the fingerprint recognition on any one of thread 1 to thread 4 is successful, it can be considered that the fingerprint recognition is successful.
  • FIG. 7 is only an example, and the running time of each thread may vary according to actual conditions.
  • the operations of other threads can be terminated without having to perform the remaining steps of the thread shown in FIG. 7, thereby reducing unnecessary operations.
  • fingerprint template 2 For example, suppose that the first feature data of the fingerprint image of the first frame and the template data of the fingerprint template 1 are matched successfully first. If fingerprint template 2 has not been processed on thread 0 at this time, the processing of fingerprint template 2 can be terminated; if only part of the steps shown in Figure 7 are executed in threads 2 to 4 at this time, the subsequent restoring can be terminated. Steps not performed.
  • the template data of fingerprint template 2 can be used directly for fingerprint recognition without waiting for the processing of fingerprint template 2.
  • the template data of the fingerprint template 2 can be transferred to each thread respectively, so as to be used for fingerprint identification of each thread.
  • the size of the sequence number of the above-mentioned processes does not mean the order of execution.
  • the execution order of each process should be determined by its function and internal logic, and should not correspond to the implementation process of the embodiments of the present application. Constitute any limitation.
  • FIG. 8 is a schematic block diagram of a fingerprint recognition device according to an embodiment of the present application. As shown in FIG. 8, the fingerprint recognition device 800 includes:
  • the first processing unit 810 is configured to process at least one frame of fingerprint image to obtain characteristic data of the at least one frame of fingerprint image; and perform processing according to the characteristic data of the at least one frame of fingerprint image and the template data of the first fingerprint template Fingerprint recognition;
  • the second processing unit 820 is configured to process the second fingerprint template in parallel when the first processing unit 810 performs fingerprint recognition based on the characteristic data of the at least one frame of fingerprint image and the template data of the first fingerprint template respectively To obtain the template data of the second fingerprint template.
  • the second fingerprint template is processed in parallel, so that when the fingerprint recognition based on the first fingerprint template fails, it can be directly based on the fingerprint image and the first fingerprint template. For fingerprint recognition, there is no need to wait for the processing time of the second fingerprint template, thereby increasing the speed of fingerprint recognition and improving user experience.
  • the first processing unit 810 and the second processing unit 820 may be different processing units independent of each other, and these different processing units perform different operations in parallel.
  • the first processing unit 810 is a DSP and is used to perform fingerprint image processing and fingerprint recognition
  • the second processing unit 820 is an ARM and is used to perform fingerprint template processing.
  • first processing unit 810 and the second processing unit 820 may also be two processing units respectively corresponding to different threads in the same processor, and are respectively used to execute operations on the respective corresponding threads.
  • the first processing unit 810 may be, for example, a CPU, DSP, VPU, GPU, or the like.
  • the second processing unit 820 may be, for example, a CPU, a DSP, a VPU, or a GPU.
  • the CPU is, for example, an ARM.
  • the second processing unit 820 is further configured to: when the first processing unit 810 processes the at least one frame of fingerprint image, process the first fingerprint template in parallel to obtain the Template data of the first fingerprint template.
  • the first processing unit 810 is specifically configured to process the at least one frame of fingerprint image in parallel.
  • the first processing unit 810 is further configured to: if fingerprint recognition is successful according to the characteristic data of any one of the at least one fingerprint image and the template data of the first fingerprint template, then Confirm that the fingerprint recognition is successful.
  • the first processing unit 810 is further configured to: if fingerprint recognition fails according to the feature data of the at least one frame of fingerprint image and the template data of the first fingerprint template, then according to the at least one frame of fingerprint image The characteristic data and the template data of the second fingerprint template perform fingerprint identification.
  • the first processing unit 810 is specifically configured to: perform image preprocessing on the first frame of fingerprint image; based on the first frame of fingerprint image after image preprocessing, perform two feature extractions in parallel to obtain respectively The first feature data and the second feature data of the first frame of fingerprint image, wherein the first feature data is obtained by feature extraction on the first frame of fingerprint image after image preprocessing, and the second feature data It is obtained by performing image enhancement on the first fingerprint image after image preprocessing, and then performing feature extraction.
  • the first processing unit 810 is specifically configured to: if fingerprint recognition fails according to the first characteristic data and the template data of the fingerprint template, perform fingerprint recognition according to the second characteristic data and the fingerprint template The template data is fingerprinted.
  • the first processing unit 810 is specifically configured to: sequentially perform image preprocessing, image enhancement, and feature extraction on the non-first frame fingerprint image.
  • the second processing unit 820 is specifically configured to: decrypt and decompress the second fingerprint template.
  • the fingerprint recognition device 800 may further include an optical fingerprint sensor for collecting at least one frame of fingerprint image.
  • the fingerprint recognition device 800 may correspond to the optical fingerprint module 130 in the foregoing embodiment, for example.
  • Optical fingerprint sensor may correspond to the optical fingerprint module 130 in the foregoing embodiment, for example.
  • An embodiment of the present application also provides an electronic device, which includes an optical fingerprint sensor and the fingerprint recognition device in the various embodiments of the present application described above.
  • the electronic devices in the embodiments of the present application may be portable or mobile computing devices such as terminal devices, mobile phones, tablet computers, notebook computers, desktop computers, game devices, in-vehicle electronic devices, or wearable smart devices, and Electronic databases, automobiles, bank automated teller machines (Automated Teller Machine, ATM) and other electronic equipment.
  • the wearable smart device includes full-featured, large-sized, complete or partial functions that can be implemented without relying on smart phones, such as smart watches or smart glasses, etc., and only focus on a certain type of application function, and need to cooperate with other devices such as smart phones Use, such as various types of smart bracelets, smart jewelry and other equipment for physical sign monitoring.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Image Input (AREA)
  • Collating Specific Patterns (AREA)

Abstract

本申请实施例提供了一种指纹识别的方法，能够提高指纹识别的速度，提升用户体验。该方法包括：对至少一帧指纹图像进行处理，得到所述至少一帧指纹图像的特征数据；在将所述至少一帧指纹图像的特征数据分别与第一指纹模板的模板数据进行匹配时，并行地对第二指纹模板进行处理，得到所述第二指纹模板的特征数据；根据匹配结果，确定指纹识别结果。

Description

指纹识别的方法、装置和电子设备 技术领域
本申请实施例涉及生物特征识别领域，并且更具体地，涉及指纹识别的方法、装置和电子设备。
背景技术
相比于电容式指纹识别技术，光学指纹识别技术中采集到的指纹图像具有更高的分辨率，指纹图像中包含的数据量也更大，在对该指纹图像进行处理时的耗时也就更长。尤其在用户注册了多个指纹模板的情况下，指纹识别的速度明显受到影响，影响用户体验。
发明内容
本申请实施例提供一种指纹识别的方法、装置和电子设备，能够提高指纹识别的速度，提升用户体验。
第一方面，提供了一种指纹识别的方法，包括：对至少一帧指纹图像进行处理，得到所述至少一帧指纹图像的特征数据；在根据所述至少一帧指纹图像的特征数据和第一指纹模板的模板数据进行指纹识别时，并行地对第二指纹模板进行处理，得到所述第二指纹模板的模板数据。
在一种可能的实现方式中，所述方法还包括：在对所述至少一帧指纹图像进行处理时，并行地对所述第一指纹模板进行处理，得到所述第一指纹模板的模板数据。
在一种可能的实现方式中，所述对至少一帧指纹图像进行处理，包括：并行地对所述至少一帧指纹图像进行处理。
在一种可能的实现方式中，所述方法还包括：若根据所述至少一帧指纹图像中的任意一帧指纹图像的特征数据和所述第一指纹模板的模板数据进行指纹识别成功，则确定指纹识别成功。
在一种可能的实现方式中，所述方法还包括：若根据所述至少一帧指纹图像的特征数据和第一指纹模板的模板数据进行指纹识别失败，则根据所述至少一帧指纹图像的特征数据和所述第二指纹模板的模板数据进行指纹识别。
在一种可能的实现方式中，对所述至少一帧指纹图像中的首帧指纹图像进行处理，包括：对所述首帧指纹图像进行图像预处理；基于图像预处理后的所述首帧指纹图像，并行地进行两次特征提取，分别得到所述首帧指纹图像的第一特征数据和第二特征数据，其中，所述第一特征数据是对图像预处理后的所述首帧指纹图像进行特征提取得到的，所述第二特征数据是对图像预处理后的所述第一指纹图像进行图像增强后再进行特征提取得到的。
在一种可能的实现方式中，所述根据所述至少一帧指纹图像的特征数据和第一指纹模板的模板数据进行指纹识别，包括：若根据所述第一特征数据和所述第一指纹模板的模板数据进行指纹识别失败，则根据所述第二特征数据和所述第一指纹模板的模板数据进行指纹识别。
在一种可能的实现方式中，对所述至少一帧指纹图像中的非首帧指纹图像进行处理，包括：对所述非首帧指纹图像依次进行图像预处理、图像增强和特征提取。
在一种可能的实现方式中，所述对第二指纹模板进行处理，包括：对所述第二指纹模板进行解密和解压缩处理。
在一种可能的实现方式中，所述方法由第一处理单元和第二处理单元执行，所述第一处理单元用于对所述至少一帧指纹图像进行处理并进行指纹识别，所述第二处理单元用于对至少一个指纹模板进行处理。
所述第一处理单元例如为CPU、DSP或者VPU。
所述第二处理单元例如为CPU、DSP或者VPU。
第一处理单元与第二处理单元的类型相同或者不同。
所述CPU例如为ARM。
第二方面，提供了一种指纹识别的装置，包括：
第一处理单元，用于对至少一帧指纹图像进行处理，得到所述至少一帧指纹图像的特征数据；并根据所述至少一帧指纹图像的特征数据和第一指纹模板的模板数据进行指纹识别；
所述第二处理单元，用于在所述第一处理单元根据所述至少一帧指纹图像的特征数据分别与第一指纹模板的模板数据进行指纹识别时，并行地对第二指纹模板进行处理，得到所述第二指纹模板的模板数据。
在一种可能的实现方式中，所述第二处理单元还用于：在所述第一处理单元对所述至少一帧指纹图像进行处理时，并行地对所述第一指纹模板进行 处理，得到所述第一指纹模板的模板数据。
在一种可能的实现方式中，所述第一处理单元具体用于：并行地对所述至少一帧指纹图像进行处理。
在一种可能的实现方式中，所述第一处理单元还用于：若根据所述至少一帧指纹图像中的任意一帧指纹图像的特征数据和所述第一指纹模板的模板数据进行指纹识别成功，则确定指纹识别成功。
在一种可能的实现方式中，所述第一处理单元还用于：若根据所述至少一帧指纹图像的特征数据和第一指纹模板的模板数据进行指纹识别失败，则根据所述至少一帧指纹图像的特征数据和所述第二指纹模板的模板数据进行指纹识别。
在一种可能的实现方式中，所述第一处理单元具体用于：对所述首帧指纹图像进行图像预处理；基于图像预处理后的所述首帧指纹图像，并行地进行两次特征提取，分别得到所述首帧指纹图像的第一特征数据和第二特征数据，其中，所述第一特征数据是对图像预处理后的所述首帧指纹图像进行特征提取得到的，所述第二特征数据是对图像预处理后的所述第一指纹图像进行图像增强后再进行特征提取得到的。
在一种可能的实现方式中，所述第一处理单元具体用于：若根据所述第一特征数据和所述第一指纹模板的模板数据进行指纹识别失败，则根据所述第二特征数据和所述第一指纹模板的模板数据进行指纹识别。
在一种可能的实现方式中，所述第一处理单元具体用于：对所述非首帧指纹图像依次进行图像预处理、图像增强和特征提取。
在一种可能的实现方式中，所述第二处理单元具体用于：对所述第二指纹模板进行解密和解压缩处理。
所述第一处理单元例如为CPU、DSP或者VPU。
所述第二处理单元例如为CPU、DSP或者VPU。
第一处理单元与第二处理单元的类型相同或者不同。
所述CPU例如为ARM。
在一种可能的实现方式中，所述CPU为进阶精简指令集机器ARM。
第三方面，提供了一种芯片，用于实现上述第一方面或第一方面的任意可能的实现方式中的方法。可选地，该芯片包括处理器，用于从存储器中调用并运行计算机程序，使得安装有该芯片的设备执行如上述第一方面或第一 方面的任意可能的实现方式中的方法。
第四方面，提供了一种计算机可读存储介质，用于存储计算机程序，该计算机程序使得计算机执行上述第一方面或第一方面的任意可能的实现方式中的方法。
第五方面，提供了一种电子设备，包括第二方面或第二方面的任意可能的实现方式中的指纹识别的装置。
基于上述技术方案，在根据指纹图像和第一指纹模板进行指纹识别时，并行地对第二指纹模板进行处理，这样，当基于第一指纹模板的指纹识别失败后，可以直接根据指纹图像和第而指纹模板进行指纹识别，而无需等待对第二指纹模板的处理时间，从而提高了指纹识别的速度，提升了用户体验。
附图说明
图1是本申请可以适用的电子设备的结构示意图。
图2是图1所示的电子设备沿A-A’方向的剖面示意图。
图3是相关技术中使用的指纹识别方法的示意性流程图。
图4是本申请实施例的指纹识别的方法的示意性流程图。
图5是本申请实施例的指纹识别的方法的一种可能的实现方式的流程图。
图6是本申请实施例的指纹识别的方法的一种可能的实现方式的流程图。
图7是本申请实施例的指纹识别的方法的一种可能的实现方式的流程图。
图8是本申请实施例的指纹识别的装置的示意性框图。
具体实施方式
下面将结合附图，对本申请实施例中的技术方案进行描述。
应理解，本申请实施例可以应用于光学指纹系统，包括但不限于光学指纹识别系统和基于光学指纹成像的医疗诊断产品，本申请实施例仅以光学指纹系统为例进行说明，但不应对本申请实施例构成任何限定，本申请实施例同样适用于其他采用光学成像技术的系统等。
作为一种常见的应用场景，本申请实施例提供的光学指纹系统可以应用在智能手机、平板电脑以及其他具有显示屏的移动终端或者其他终端设备；更具体地，在上述终端设备中，光学指纹模组可以具体为光学指纹模组，其可以设置在显示屏下方的局部区域或者全部区域，从而形成屏下 (Under-display或Under-screen)光学指纹系统。或者，所述光学指纹模组也可以部分或者全部集成至所述终端设备的显示屏内部，从而形成屏内(In-display或In-screen)光学指纹系统。
图1和图2示出了本申请实施例可以适用的电子设备的示意图。其中，图1为电子设备10的示意图，图2为图1所示的电子设备10沿A-A’方向的剖面示意图。
所述终端设备10包括显示屏120和光学指纹模组130。其中，所述光学指纹模组130设置在所述显示屏120下方的局部区域。所述光学指纹模组130包括光学指纹传感器，所述光学指纹传感器包括具有多个光学感应单元131的感应阵列133。所述感应阵列133所在区域或者其感应区域为所述光学指纹模组130的指纹检测区域121(也可以称为指纹采集区域、指纹识别区域等)。如图1所示，所述指纹检测区域121位于所述显示屏120的显示区域之中。在一种替代实施例中，所述光学指纹模组130还可以设置在其他位置，比如所述显示屏120的侧面或者所述终端设备10的边缘非透光区域，并通过光路设计来将来自所述显示屏120的至少部分显示区域的光信号导引到所述光学指纹模组130，从而使得所述指纹检测区域121实际上位于所述显示屏120的显示区域。
应当理解，所述指纹检测区域121的面积可以与所述光学指纹模组130的感应阵列133的面积不同，例如通过例如透镜成像的光路设计、反射式折叠光路设计或者其他光线汇聚或者反射等光路设计，可以使得所述光学指纹模组130的指纹检测区域121的面积大于所述光学指纹模组130的感应阵列133的面积。在其他替代实现方式中，如果采用例如光线准直方式进行光路引导，所述光学指纹模组130的指纹检测区域121也可以设计成与所述光学指纹模组130的感应阵列的面积基本一致。
因此，使用者在需要对所述终端设备进行解锁或者其他指纹验证的时候，只需要将手指按压在位于所述显示屏120的指纹检测区域121，便可以实现指纹输入。由于指纹检测可以在屏内实现，因此采用上述结构的终端设备10无需其正面专门预留空间来设置指纹按键(比如Home键)，从而可以采用全面屏方案，即所述显示屏120的显示区域可以基本扩展到整个终端设备10的正面。
作为一种可选的实现方式，如图1所示，所述光学指纹模组130包括光 检测部分134和光学组件132。所述光检测部分134包括所述感应阵列133以及与所述感应阵列133电性连接的读取电路及其他辅助电路，其可以在通过半导体工艺制作在一个芯片(Die)，比如光学成像芯片或者光学指纹传感器。所述感应阵列133具体为光探测器(Photo detector)阵列，其包括多个呈阵列式分布的光探测器，所述光探测器可以作为如上所述的光学感应单元。所述光学组件132可以设置在所述光检测部分134的感应阵列133的上方，其可以具体包括滤光层(Filter)、导光层或光路引导结构、以及其他光学元件，所述滤光层可以用于滤除穿透手指的环境光，而所述导光层或光路引导结构主要用于从手指表面反射回来的反射光导引至所述感应阵列133进行光学检测。
在具体实现上，所述光学组件132可以与所述光检测部分134封装在同一个光学指纹部件。比如，所述光学组件132可以与所述光学检测部分134封装在同一个光学指纹芯片，也可以将所述光学组件132设置在所述光检测部分134所在的芯片外部，比如将所述光学组件132贴合在所述芯片上方，或者将所述光学组件132的部分元件集成在上述芯片之中。
其中，所述光学组件132的导光层或者光路引导结构有多种实现方案，比如，所述导光层可以具体为在半导体硅片制作而成的准直器(Collimator)层，其具有多个准直单元或者微孔阵列，所述准直单元可以具体为小孔，从手指反射回来的反射光中，垂直入射到所述准直单元的光线可以穿过并被其下方的光学感应单元接收，而入射角度过大的光线在所述准直单元内部经过多次反射被衰减掉，因此每一个光学感应单元基本只能接收到其正上方的指纹纹路反射回来的反射光，从而所述感应阵列133便可以检测出手指的指纹图像。
在另一种实施例中，所述导光层或者光路引导结构也可以为光学透镜(Lens)层，其具有一个或多个透镜单元，比如一个或多个非球面透镜组成的透镜组，其用于将从手指反射回来的反射光汇聚到其下方的光检测部分134的感应阵列133，以使得所述感应阵列133可以基于所述反射光进行成像，从而得到所述手指的指纹图像。可选地，所述光学透镜层在所述透镜单元的光路中还可以形成有针孔，所述针孔可以配合所述光学透镜层扩大所述光学指纹模组130的视场，以提高所述光学指纹模组130的指纹成像效果。
在其他实施例中，所述导光层或者光路引导结构也可以具体采用微透镜 (Micro-Lens)层，所述微透镜层具有由多个微透镜形成的微透镜阵列，其可以通过半导体生长工艺或者其他工艺形成在所述光检测部分134的感应阵列133上方，并且每一个微透镜可以分别对应于所述感应阵列133的其中一个感应单元。并且，所述微透镜层和所述感应单元之间还可以形成其他光学膜层，比如介质层或者钝化层。更具体地，所述微透镜层和所述感应单元之间还可以包括具有微孔的挡光层(或称为遮光层)，其中所述微孔形成在其对应的微透镜和感应单元之间，所述挡光层可以阻挡相邻微透镜和感应单元之间的光学干扰，并使得所述感应单元所对应的光线通过所述微透镜汇聚到所述微孔内部并经由所述微孔传输到所述感应单元以进行光学指纹成像。
应当理解，上述导光层或者光路引导结构的几种实现方案可以单独使用也可以结合使用。比如，可以在所述准直器层或者所述光学透镜层的上方或下方进一步设置微透镜层。当然，在所述准直器层或者所述光学透镜层与所述微透镜层结合使用时，其具体叠层结构或者光路可能需要按照实际需要进行调整。
作为一种可选的实施例，所述显示屏120可以采用具有自发光显示单元的显示屏，比如有机发光二极管(Organic Light-Emitting Diode，OLED)显示屏或者微型发光二极管(Micro-LED)显示屏。以采用OLED显示屏为例，所述光学指纹模组130可以利用所述OLED显示屏120位于所述指纹检测区域121的显示单元(即OLED光源)来作为光学指纹检测的激励光源。当手指140按压在所述指纹检测区域121时，显示屏120向所述指纹检测区域121上方的目标手指140发出一束光111，该光111在手指140的表面发生反射形成反射光或者经过所述手指140内部散射而形成散射光，在相关专利申请中，为便于描述，上述反射光和散射光统称为反射光。由于指纹的脊(ridge)141与谷(valley)142对于光的反射能力不同，因此，来自指纹脊的反射光151和来自指纹谷的反射光152具有不同的光强，反射光经过光学组件132后，被光学指纹模组130中的感应阵列133所接收并转换为相应的电信号，即指纹检测信号；基于所述指纹检测信号便可以获得指纹图像数据，并且可以进一步进行指纹匹配验证，从而在终端设备10实现光学指纹识别功能。
在其他实施例中，所述光学指纹模组130也可以采用内置光源或者外置光源来提供用于进行指纹检测的光信号。在这种情况下，所述光学指纹模组130可以适用于非自发光显示屏，比如液晶显示屏或者其他的被动发光显示 屏。以应用在具有背光模组和液晶面板的液晶显示屏为例，为支持液晶显示屏的屏下指纹检测，所述终端设备10的光学指纹系统还可以包括用于光学指纹检测的激励光源，所述激励光源可以具体为红外光源或者特定波长非可见光的光源，其可以设置在所述液晶显示屏的背光模组下方或者设置在所述终端设备10的保护盖板下方的边缘区域，而所述光学指纹模组130可以设置液晶面板或者保护盖板的边缘区域下方并通过光路引导以使得指纹检测光可以到达所述光学指纹模组130；或者，所述光学指纹模组130也可以设置在所述背光模组下方，且所述背光模组通过对扩散片、增亮片、反射片等膜层进行开孔或者其他光学设计以允许指纹检测光穿过液晶面板和背光模组并到达所述光学指纹模组130。当采用所述光学指纹模组130采用内置光源或者外置光源来提供用于进行指纹检测的光信号时，其检测原理与上面描述内容是一致的。
应当理解的是，在具体实现上，所述终端设备10还包括透明保护盖板，所述盖板可以为玻璃盖板或者蓝宝石盖板，其位于所述显示屏120的上方并覆盖所述终端设备10的正面。因此，本申请实施例中，所谓的手指按压在所述显示屏120实际上是指按压在所述显示屏120上方的盖板或者覆盖所述盖板的保护层表面。
另一方面，在某些实施例中，所述光学指纹模组130可以仅包括一个光学指纹传感器，此时光学指纹模组130的指纹检测区域121的面积较小且位置固定，因此用户在进行指纹输入时需要将手指按压到所述指纹检测区域121的特定位置，否则光学指纹模组130可能无法采集到指纹图像而造成用户体验不佳。在其他替代实施例中，所述光学指纹模组130可以具体包括多个光学指纹传感器。所述多个光学指纹传感器可以通过拼接方式并排设置在所述显示屏120的下方，且所述多个光学指纹传感器的感应区域共同构成所述光学指纹模组130的指纹检测区域121。也就是说，所述光学指纹模组130的指纹检测区域121可以包括多个子区域，每个子区域分别对应于其中一个光学指纹传感器的感应区域，从而将所述光学指纹模组130的指纹检测区域121可以扩展到所述显示屏的下半部分的主要区域，即扩展到手指惯常按压区域，从而实现盲按式指纹输入操作。可替代地，当所述光学指纹传感器数量足够时，所述指纹检测区域130还可以扩展到半个显示区域甚至整个显示区域，从而实现半屏或者全屏指纹检测。
光学指纹传感器采集的指纹图像需要进行处理，并与指纹模板进行匹配，从而获得指纹识别的结果。
通常，需要进行指纹模板解析、图像预处理、特征提取和指纹匹配。指纹模板解析是指读取指纹模板后对其进行的解密和解压缩等操作，可以获得该指纹模板的模板数据。光学指纹传感器采集到指纹图像后，处理单元对指纹图像进行图像预处理，并对图像预处理后的指纹图像进行特征提取，得到该指纹图像的特征数据。基于该指纹图像的特征数据和指纹模板的模板数据可以进行指纹识别。
通常，用户可以在电子设备中注册多个指纹模板，在进行指纹识别时，需要将指纹图像分别与这些指纹模板进行匹配，如果该指纹图像与某个指纹模板匹配成功，则可以确定指纹识别成功。
图3示出了相关技术中采用的指纹识别的方法的流程图。假设用户注册了三个指纹模板，即指纹模板1、指纹模板2和指纹模板3。在进行指纹识别时，采用单线程对指纹图像和指纹模板进行处理。其中：
在301中，解析指纹模板1，并进行匹配。
具体地，解析指纹模板1，并将得到的指纹模板1的模板数据与指纹图像的特征数据进行匹配，得到指纹识别结果。
在302中，确定指纹识别是否成功。
如果指纹识别成功，则执行步骤308；如果指纹识别失败，则执行步骤303。
在303中，解析指纹模板2，并进行匹配。
具体地，解析指纹模板2，并将得到的指纹模板2的模板数据与指纹图像的特征数据进行匹配，得到指纹识别结果。
在304中，确定指纹识别是否成功。
如果指纹识别成功，则执行步骤308；如果指纹识别失败，则执行步骤305。
在305中，解析指纹模板3，并进行匹配。
具体地，解析指纹模板3，并将得到的指纹模板3的模板数据与指纹图像的特征数据进行匹配，得到指纹识别结果。
在306中，判断匹配是否成功。
如果匹配识别成功，则执行步骤308；如果匹配失败，则执行步骤307。
可以看出，图3中是通过单线程进行指纹识别的。在用户注册多个指纹模板的情况下，只能依次解析每个指纹模板并进行指纹匹配，导致指纹识别的耗时较长，影响用户体验。
本申请实施例提供了一种指纹识别的方案，通过并行地对指纹模板和指纹图像进行处理，从而提高指纹识别的速度，提升用户体验。
图4是根据本申请实施例的指纹识别的方法400的示意性流程图，如图4所示，该方法400包括以下步骤中的部分或全部。
在410中，对至少一帧指纹图像进行处理，得到该至少一帧指纹图像的特征数据。
在420中，在根据该至少一帧指纹图像的特征数据和第一指纹模板的模板数据进行指纹识别时，并行地对第二指纹模板进行处理，得到该第二指纹模板的模板数据。
根据指纹图像的特征数据和指纹模板的模板数据进行指纹识别，可以指，将该指纹图像的特征数据与指纹模板的模板数据进行匹配，例如计算指纹图像的特征数据与模板数据之间的相似度，从而确定指纹识别结果，例如在相似度大于阈值时确定指纹识别成功。
可选地，该方法还包括：若根据该至少一帧指纹图像中的任意一帧指纹图像的特征数据和该第一指纹模板的模板数据进行指纹识别成功，则确定指纹识别成功。
可选地，该方法还包括：若根据该至少一帧指纹图像的特征数据和第一指纹模板的模板数据进行指纹识别失败，则根据该至少一帧指纹图像的特征数据和该第二指纹模板的模板数据进行指纹识别。
该至少一帧指纹图像可以包括一帧指纹图像或者多帧指纹图像。当包括多帧指纹图像时，可以基于重试(Retry)策略进行指纹识别。Retry策略是指，当采集多帧指纹图像时，如果根据其中任意一帧指纹图像进行指纹识别成功，则可以认为指纹识别是成功的。
当然，根据指纹识别所对应的操作的安全级别，也可以设置，如果多帧指纹图像中的部分或全部指纹图像均进行指纹识别成功，才可以认为指纹识别是成功的。
本申请实施例对该至少一帧指纹图像的数量不做任何限定，并且对用户注册的指纹模板的数量不做任何限定。
该实施例中，对光学指纹传感器采集到的至少一帧指纹图像进行处理，得到至少一帧指纹图像的特征数据后，将该至少一帧指纹图像的特征数据分别和第一指纹模板的模板数据进行匹配。并且，在将至少一帧指纹图像的特征数据分别与第一指纹模板的模板数据进行匹配时，会并行地对下一个指纹模板，即第二指纹模板进行处理，得到该第二指纹模板的模板数据。
因此，当该至少一帧指纹图像与该第一指纹模板的模板数据均匹配失败后，可以继续将该至少一帧指纹图像的特征数据与第二指纹模板的模板数据进行匹配，而无需等待对第二指纹模板的处理过程，提高了指纹识别的效率，提升了用户体验。
并且，由于对指纹识别和指纹模板的处理是并行进行的，因此只需要分配两块内存，其中每块内存的大小为存储一个指纹模板或指纹图像的数据量所需的大小。特别适用于指纹模板的数据库较大但是内存资源又很有限的场景。
这里的第一指纹模板的优先级高于第二指纹模板的优先级。其中，优先级高的指纹模板优先用于指纹识别。即，按照优先级从高至低的顺序，依次对指纹模板进行处理以得到模板数据并用于指纹识别。
可选地，在410中，该方法还包括：在对该至少一帧指纹图像进行处理时，并行地对该第一指纹模板进行处理，得到该第一指纹模板的模板数据。
也就是说，可以并行地对指纹图像进行处理以及对第一指纹模板进行处理，从而根据指纹图像的特征数据和第一指纹模板的模板数据进行指纹识别。因此，节约了对第一指纹模板进行处理的时间，提高了指纹识别的效率。
例如图5所示，假设该至少一帧指纹图像仅包括一帧指纹图像，且假设用户注册了两个指纹模板，即指纹模板1和指纹模板2。线程0用于对指纹模板进行处理；线程1用于对该指纹图像进行处理和识别。
在501中，采集指纹图像。
在502中，对该指纹图像进行处理，得到指纹图像的特征数据。
在执行步骤501和502的过程中，并行地执行步骤503和504。
在503中，读取指纹模板1。
在504中，对指纹模板1进行处理，得到模板数据1。
505，根据指纹图像的特征数据和模板数据1进行指纹识别。
506，判断指纹识别是否成功。
其中，在执行步骤505和506的过程中，并行地执行步骤507和508。
在507中，读取指纹模板2。
在508中，对指纹模板2进行处理，得到模板数据2。
其中，在506中，若判断指纹识别成功，则结束指纹识别流程；若判断指纹识别失败，则执行步骤509。
509，根据指纹图像的特征数据和模板数据2进行指纹识别。
其中，若判断指纹识别成功，可以执行例如解锁等操作；若指纹识别失败，例如可以拒绝解锁。
从图5中可以看出，线程0用于指纹图像的处理和指纹识别，线程1用于指纹模板的处理。线程0和线程1并行地执行，相比于图3中的串行方式，大大提高了指纹识别的速度，提升了用户体验。
可选地，在410中，对至少一帧指纹图像进行处理，包括：并行地对至少一帧指纹图像进行处理。
当采用Retry策略时，光学指纹传感器可以采集多帧指纹图像。可以采用多个线程分别对这多帧指纹图像并行地进行处理，从而获得多帧指纹图像的特征数据。若根据一帧指纹图像的特征数据与某个指纹模板的模板数据进行匹配失败，则可以根据下一帧指纹图像的特征数据与该指纹模板的模板数据进行匹配。
应理解，本申请实施例中所有并行的流程，均可以通过独立的线程来完成。例如，多帧指纹图像的处理流程可以分别在多个线程上执行；又例如，指纹图像的处理流程与指纹模板的处理流程可以在不同的线程上执行。
这多个线程可以是同一个处理单元例如CPU上并行运行的多个线程，也可以是相互独立的不同处理单元上的线程。即，该方法可以由一个处理单元执行，也可以由相互独立的多个处理单元执行。
例如，该指纹识别的方法由第一处理单元和第二处理单元执行，该第一处理单元用于对至少一帧指纹图像进行处理以及进行指纹识别，该第二处理单单元用于对至少一个指纹模板进行处理。
该第一处理单元例如可以是中央处理器(Central Processing Unit，CPU)、数字信号处理器(Digital Signal Processor，DSP)、视频处理单元(Video Processing Unit，VPU)、图形处理器(Graphics Processing Unit，GPU)、现成可编程门阵列(Field Programmable Gate Array，FPGA)等。
该第二处理单元例如可以是CPU、DSP、VPU、GPU或者FPGA等。
该CPU例如为进阶精简指令集机器(AdvancedRISCMachine，ARM)，其中精简指令集计算机(Reduced Instruction Set Computer，RISC)。
该第一处理单元和该第二处理单元可以是不同的处理单元，并且，并行地执行不同的操作。例如第一处理单元为DSP，用于执行指纹图像的处理和指纹识别；第二处理单元为ARM，用于执行指纹模板的处理。
本申请实施例中所述的“并行地”，是指多个线程之间至少部分同时进行，而不限定于两个线程同时开始和/或同时结束。例如，可以某个线程先开始执行，并在该线程执行的过程中启动另一个线程，之后两个线程并行地执行各自对应的操作，并且这两个线程的结束时刻也可以相同或者不同。
当该不同线程上需要执行的操作由不同的处理器来执行，此处的“并行地”即指硬件环境中的多个处理器之间的并行。
本申请实施例中，对指纹图像的处理可以包括图像预处理(以下也简称预处理)、图像增强、提取特征数据等过程中的一种或多种。图像预处理例如可以包括滤波、卷积等操作，以消除指纹图像中的噪声等干扰信号。图像增强可以改善指纹图像的质量、丰富指纹图像的信息量，从而加强图像判读和识别的效果。本申请实施例对指纹图像的处理不做限定，可以使用任何指纹算法实现对指纹图像的处理。
可选地，对该至少一帧指纹图像中的第一指纹图像进行处理，包括：对该第一指纹图像进行图像预处理；基于图像预处理后的该第一指纹图像，并行地进行两次特征提取，分别得到该第一指纹图像的第一特征数据和第二特征数据。
其中，该第一特征数据是对图像预处理后的该第一指纹图像进行特征提取得到的，该第二特征数据是对图像预处理后的该第一指纹图像进行图像增强后再进行特征提取得到的。
其中，该第一指纹图像例如可以为首帧指纹图像，即光学指纹传感器采集到的第一帧指纹图像。
以下，均以该第一指纹图像为首帧指纹图像为例进行说明，但并不限于此，该第一指纹图像也可以为非首帧指纹图像。
进一步地，可选地，根据所述至少一帧指纹图像的特征数据和第一指纹模板的模板数据进行指纹识别，包括：若根据该第一特征数据和第一指纹模 板的模板数据进行指纹识别失败，则根据该第二特征数据和第一指纹模板的模板数据进行指纹识别。
本申请实施例可以对首帧指纹图像进行两次特征提取。在对首帧指纹图像进行图像预处理后，可以对预处理后的首帧指纹图像进行特征提取，得到首帧指纹图像的第一特征数据；并行地，可以对预处理后的首帧指纹图像进行图像增强，并在进行图像增强之后进行特征提取，得到首帧指纹图像的第二特征数据。
由于对指纹图像进行图像增强后可以获得更加丰富的指纹数据，因此，第二特征数据的数据量比第一特征数据的数据量丰富。可以理解，第二特征数据相当于对首帧指纹图像进行细提取，第一特征数据相当于对首帧指纹图像进行粗提取。
以图6为例说明对首帧指纹图像进行两次特征提取的过程。如图6所示，在对首帧指纹图像进行处理时，可以分别使用线程0和线程1进行两次特征提取，分别得到首帧指纹图像的第一特征数据和第二特征数据。
在601中，采集首帧指纹图像。
在602中，对首帧指纹图像进行图像预处理。
在603中，对预处理后的指纹图像进行特征提取得到指纹图像的第一特征数据。
在604中，根据指纹模板的模板数据和第一特征数据进行指纹识别。
在执行步骤603和604的过程中，并行地执行步骤605至607。
在605中，对预处理后的指纹图像进行图像增强。
在606中，对图像增强后的指纹图像进行特征提取，得到指纹图像的第二特征数据。
在607中，根据指纹模板的模板数据和第二特征数据进行指纹识别。
其中，可选地，如果步骤604中的指纹识别成功，则可以不执行步骤607；如果步骤604中的指纹识别失败，则执行步骤607。这时，在确定步骤604中的指纹识别失败后，可以直接根据第二特征数据和模板数据进行指纹识别，由于第二特征数据的提取与第一特征数据的提取是并行进行的，因而无需进行较长时间的等待。
可选地，对该至少一帧指纹图像中的第二指纹图像进行处理，包括：对该第二指纹图像依次进行图像预处理和特征提取；或者，对该第二指纹图像 依次进行图像预处理、图像增强和特征提取。
其中，该第二指纹图像例如可以为非首帧指纹图像，例如光学指纹传感器采集到的第二帧指纹图像、第三帧指纹图像等。
以下，均以该第二指纹图像为非首帧指纹图像为例进行说明，但并不限于此，该第二指纹图像也可以为首帧指纹图像。
本申请实施例中，对指纹模板进行处理，例如可以包括对读取的指纹模板进行解密和解压缩等处理，也可以称为解析指纹模板。对指纹模板进行处理后能够获得用于指纹识别的模板数据，也可以称为指纹模板的特征数据。
下面以图7为例，详细描述本申请实施例的一种可能的指纹识别的方法的实现方式。其中，图7中示出了线程0至线程4。线程0至线程4可以是同一个处理器上并行运行的5个线程，或者，线程0至线程4中的至少部分线程分别运行在不同的处理器上。
其中，线程0用于执行指纹模板的读取和处理；线程1和线程3均用于执行第一帧指纹图像的处理和识别；线程2用于执行第二帧指纹图像的处理和识别；线程4用于执行第三帧指纹图像的处理和识别。
启动线程0。在线程0上运行步骤7001至7004。
在7001中，读取指纹模板1。
在7002中，对指纹模板1进行处理，得到指纹模板1的模板数据。
在7003中，读取指纹模板2。
在7004中，对指纹模板2进行处理，得到指纹模板2的模板数据。
当采集到第一帧指纹图之后，开始执行线程1。
线程1上运行步骤7101至7104。
在7101中，获取第一帧指纹图像。
例如从光学指纹传感器获取该第一帧指纹图像。
在7102中，对第一帧指纹图像进行图像预处理。
在7103中，对预处理后的第一帧指纹图像进行特征提取，得到第一帧指纹图像的第一特征数据。
并且，图像预处理后的指纹图像被传输至线程3。
在7104中，根据该第一特征数据和指纹模板1的模板数据进行指纹识别。
当线程1执行完步骤7102后，启动线程3。
线程3上运行步骤7301至7303。
在7301中，对从线程1接收到的预处理后的第一帧指纹图像进行图像增强；
在7302中，对图像增强后的第一帧指纹图像进行特征提取，得到第一帧指纹图像的第二特征数据。
在7303中，根据该第二特征数据和指纹模板1的模板数据进行指纹识别。
当采集到第二帧指纹图之后，开始执行线程2。
线程2上用于运行步骤7201至7205。
在7201中，获取第二帧指纹图像。
例如从光学指纹传感器获取该第二帧指纹图像。
在7202中，对第二帧指纹图像进行图像预处理。
在7203中，对预处理后的第二帧指纹图像进行图像增强。
在7204中，对图像增强后的第二帧指纹图像进行特征提取，得到第二帧指纹图像的特征数据。
在7205中，根据第二帧指纹图像的特征数据和指纹模板1的模板数据进行指纹识别。
当采集到第三帧指纹图之后，开始执行线程4。
线程4上用于运行步骤7401至7405。
在7401中，获取第三帧指纹图像。
例如从光学指纹传感器获取该第三帧指纹图像。
在7402中，对第三帧指纹图像进行图像预处理。
在7403中，对预处理后的第三帧指纹图像进行图像增强。
在7404中，对图像增强后的第三帧指纹图像进行特征提取，得到第二帧指纹图像的特征数据。
在7405中，根据第三帧指纹图像的特征数据和指纹模板1的模板数据进行指纹识别。
其中，线程0至线程4中的部分或全部线程可以并行处理。
在线程0上运行步骤7001和7002时，可以并行地在线程1上执行步骤7101至7103。
其中，线程0和线程1可以同时开始。
或者，线程0和线程1也可以不同时开始。例如，可以在手指按压之前例如开机时创建线程0，而在手指按压时创建线程1。线程0在对指纹模板1进行处理并获得模板数据后，可以将该模板数据存储在内存中，并等待线程1的创建。
在线程1上运行7103和7104时，可以并行地在线程3上运行7301至7303，从而实现对第一帧指纹图像的两次特征提取和指纹识别。
在线程1上运行7101至7104时，可以并行地在线程2上运行7201至7205，并且并行地在线程4上运行7401至7405，从而分别完成每帧指纹图像的识别。
在线程1至线程4上进行指纹识别时，线程0上可以并行地读取和处理下一帧指纹模板即指纹模板2。
步骤7500可以在任意一个线程上执行。
在7500中，判断线程1至线程4中是否有线程识别成功。
例如，如果线程1至线程4中任意一个线程上的指纹识别成功，则可以认为指纹识别成功。
此时，可以通知其他线程终止操作。
应理解，图7仅仅是一种示例，各个线程的运行时间可能会根据实际情况而发生变化。当某个线程上的指纹识别操作成功时，可以终止其他线程的操作，而不必执行完图7中所示的该线程的剩余步骤，从而减少不必要的操作。
举例来说，假设第一帧指纹图像的第一特征数据与指纹模板1的模板数据最先匹配成功。如果此时线程0上还没有处理完指纹模板2，则可以终止对指纹模板2的处理；如果此时线程2至线程4中仅执行了图7中所示的部分步骤，那么可以终止后续还未执行的步骤。
如果在7500中，线程1至线程4中的指纹识别均没有成功，则可以直接使用指纹模板2的模板数据进行指纹识别，而无需再等待对指纹模板2的处理。
根据每帧指纹图像的特征数据与指纹模板2的模板数据进行指纹识别的过程，可以参考图7中虚线框中所述的流程。获得指纹模板2的模板数据后，该模板数据可以分别传递至各个线程，从而用于各个线程进行指纹识别。
需要说明的是，在不冲突的前提下，本申请描述的各个实施例和/或各个 实施例中的技术特征可以任意的相互组合，组合之后得到的技术方案也应落入本申请的保护范围。
在本申请的各种实施例中，上述各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
上文结合图4至图7，详细描述了本申请的方法实施例，下文结合图8，详细描述本申请的装置实施例。应理解，装置实施例与方法实施例相互对应，类似的描述可以参照方法实施例。
图8是根据本申请实施例的指纹识别的装置的示意性框图，如图8所示，该指纹识别的装置800包括：
第一处理单元810，用于对至少一帧指纹图像进行处理，得到所述至少一帧指纹图像的特征数据；并根据所述至少一帧指纹图像的特征数据和第一指纹模板的模板数据进行指纹识别；
第二处理单元820，用于在所述第一处理单元810根据所述至少一帧指纹图像的特征数据分别与第一指纹模板的模板数据进行指纹识别时，并行地对第二指纹模板进行处理，得到所述第二指纹模板的模板数据。
因此，在根据指纹图像和第一指纹模板进行指纹识别时，并行地对第二指纹模板进行处理，这样，当基于第一指纹模板的指纹识别失败后，可以直接根据指纹图像和第而指纹模板进行指纹识别，二无需等待对第二指纹模板的处理时间，从而提高了指纹识别的速度，提升了用户体验。
该第一处理单元810和该第二处理单元820可以是相互独立的不同的处理单元，并且这些不同的处理单元并行地执行不同的操作。例如第一处理单元810为DSP，用于执行指纹图像的处理和指纹识别；第二处理单元820为ARM，用于执行指纹模板的处理。
或者，第一处理单元810和第二处理单元820也可以是同一个处理器中分别对应于不同线程的两个处理单元，分别用于执行各自对应的线程上的操作。
该第一处理单元810例如可以是CPU、DSP、VPU或者GPU等。
该第二处理单元820例如可以是CPU、DSP、VPU或者GPU等。
该CPU例如为ARM。
可选地，所述第二处理单元820还用于：在所述第一处理单元810对所 述至少一帧指纹图像进行处理时，并行地对所述第一指纹模板进行处理，得到所述第一指纹模板的模板数据。
可选地，所述第一处理单元810具体用于：并行地对所述至少一帧指纹图像进行处理。
可选地，所述第一处理单元810还用于：若根据所述至少一帧指纹图像中的任意一帧指纹图像的特征数据和所述第一指纹模板的模板数据进行指纹识别成功，则确定指纹识别成功。
可选地，所述第一处理单元810还用于：若根据所述至少一帧指纹图像的特征数据和第一指纹模板的模板数据进行指纹识别失败，则根据所述至少一帧指纹图像的特征数据和所述第二指纹模板的模板数据进行指纹识别。
可选地，所述第一处理单元810具体用于：对所述首帧指纹图像进行图像预处理；基于图像预处理后的所述首帧指纹图像，并行地进行两次特征提取，分别得到所述首帧指纹图像的第一特征数据和第二特征数据，其中，所述第一特征数据是对图像预处理后的所述首帧指纹图像进行特征提取得到的，所述第二特征数据是对图像预处理后的所述第一指纹图像进行图像增强后再进行特征提取得到的。
可选地，所述第一处理单元810具体用于：若根据所述第一特征数据和所述指纹模板的模板数据进行指纹识别失败，则根据所述第二特征数据和所述指纹模板的模板数据进行指纹识别。
可选地，所述第一处理单元810具体用于：对所述非首帧指纹图像依次进行图像预处理、图像增强和特征提取。
可选地，所述第二处理单元820具体用于：对所述第二指纹模板进行解密和解压缩处理。
可选地，所述指纹识别的装置800还可以包括光学指纹传感器，用于采集至少一帧指纹图像，该指纹识别的装置800例如可以对应于前文所述实施例中的光学指纹模组130中的光学指纹传感器。
本申请实施例还提供了一种电子设备，该电子设备包括光学指纹传感器以及上述本申请各种实施例中的指纹识别的装置。
作为示例而非限定，本申请实施例中的电子设备可以为终端设备、手机、平板电脑、笔记本电脑、台式机电脑、游戏设备、车载电子设备或穿戴式智能设备等便携式或移动计算设备，以及电子数据库、汽车、银行自动柜员机 (Automated Teller Machine，ATM)等其他电子设备。该穿戴式智能设备包括功能全、尺寸大、可不依赖智能手机实现完整或部分的功能，例如：智能手表或智能眼镜等，以及只专注于某一类应用功能，需要和其它设备如智能手机配合使用，如各类进行体征监测的智能手环、智能首饰等设备。
需要说明的是，在不冲突的前提下，本申请描述的各个实施例和/或各个实施例中的技术特征可以任意的相互组合，组合之后得到的技术方案也应落入本申请的保护范围。
应理解，本申请实施例中的具体的例子只是为了帮助本领域技术人员更好地理解本申请实施例，而非限制本申请实施例的范围，本领域技术人员可以在上述实施例的基础上进行各种改进和变形，而这些改进或者变形均落在本申请的保护范围内。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以所述权利要求的保护范围为准。

Claims (26)

  1. 一种指纹识别的方法，其特征在于，所述方法包括：
    对至少一帧指纹图像进行处理，得到所述至少一帧指纹图像的特征数据；
    在根据所述至少一帧指纹图像的特征数据和第一指纹模板的模板数据进行指纹识别时，并行地对第二指纹模板进行处理，得到所述第二指纹模板的模板数据。
  2. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    在对所述至少一帧指纹图像进行处理时，并行地对所述第一指纹模板进行处理，得到所述第一指纹模板的模板数据。
  3. 根据权利要求1或2所述的方法，其特征在于，所述对至少一帧指纹图像进行处理，包括：
    并行地对所述至少一帧指纹图像进行处理。
  4. 根据权利要求1至3中任一项所述的方法，其特征在于，所述方法还包括：
    若根据所述至少一帧指纹图像中的任意一帧指纹图像的特征数据和所述第一指纹模板的模板数据进行指纹识别成功，则确定指纹识别成功。
  5. 根据权利要求1至4中任一项所述的方法，其特征在于，所述方法还包括：
    若根据所述至少一帧指纹图像的特征数据和第一指纹模板的模板数据进行指纹识别失败，则根据所述至少一帧指纹图像的特征数据和所述第二指纹模板的模板数据进行指纹识别。
  6. 根据权利要求1至5中任一项所述的方法，其特征在于，对所述至少一帧指纹图像中的首帧指纹图像进行处理，包括：
    对所述首帧指纹图像进行图像预处理；
    基于图像预处理后的所述首帧指纹图像，并行地进行两次特征提取，分别得到所述首帧指纹图像的第一特征数据和第二特征数据，其中，所述第一特征数据是对图像预处理后的所述首帧指纹图像进行特征提取得到的，所述第二特征数据是对图像预处理后的所述第一指纹图像进行图像增强后再进行特征提取得到的。
  7. 根据权利要求6所述的方法，其特征在于，所述根据所述至少一帧指纹图像的特征数据和第一指纹模板的模板数据进行指纹识别，包括：
    若根据所述第一特征数据和所述第一指纹模板的模板数据进行指纹识别失败，则根据所述第二特征数据和所述第一指纹模板的模板数据进行指纹识别。
  8. 根据权利要求1至7中任一项所述的方法，其特征在于，对所述至少一帧指纹图像中的非首帧指纹图像进行处理，包括：
    对所述非首帧指纹图像依次进行图像预处理、图像增强和特征提取。
  9. 根据权利要求1至8中任一项所述的方法，其特征在于，所述对第二指纹模板进行处理，包括：
    对所述第二指纹模板进行解密和解压缩处理。
  10. 根据权利要求1至9中任一项所述的方法，其特征在于，所述方法由第一处理单元和第二处理单元执行，所述第一处理单元用于对所述至少一帧指纹图像进行处理并进行指纹识别，所述第二处理单元用于对至少一个指纹模板进行处理。
  11. 根据权利要求10所述的方法，其特征在于，所述第一处理单元为以下中的任意一种：中央处理器CPU、数字信号处理器DSP和视频处理单元VPU。
  12. 根据权利要求11所述的方法，其特征在于，所述第二处理单元为以下中的任意一种：CPU、DSP和VPU。
  13. 根据权利要求11或12所述的方法，其特征在于，所述CPU为进阶精简指令集机器ARM。
  14. 一种指纹识别的装置，其特征在于，包括：
    第一处理单元，用于对至少一帧指纹图像进行处理，得到所述至少一帧指纹图像的特征数据；并根据所述至少一帧指纹图像的特征数据和第一指纹模板的模板数据进行指纹识别；
    第二处理单元，用于在所述第一处理单元根据所述至少一帧指纹图像的特征数据分别与第一指纹模板的模板数据进行指纹识别时，并行地对第二指纹模板进行处理，得到所述第二指纹模板的模板数据。
  15. 根据权利要求14所述的装置，其特征在于，所述第二处理单元还用于：
    在所述第一处理单元对所述至少一帧指纹图像进行处理时，并行地对所述第一指纹模板进行处理，得到所述第一指纹模板的模板数据。
  16. 根据权利要求14或15所述的装置，其特征在于，所述第一处理单元具体用于：
    并行地对所述至少一帧指纹图像进行处理。
  17. 根据权利要求14至16中任一项所述的装置，其特征在于，所述第一处理单元还用于：
    若根据所述至少一帧指纹图像中的任意一帧指纹图像的特征数据和所述第一指纹模板的模板数据进行指纹识别成功，则确定指纹识别成功。
  18. 根据权利要求14至17中任一项所述的装置，其特征在于，所述第一处理单元还用于：
    若根据所述至少一帧指纹图像的特征数据和第一指纹模板的模板数据进行指纹识别失败，则根据所述至少一帧指纹图像的特征数据和所述第二指纹模板的模板数据进行指纹识别。
  19. 根据权利要求14至18中任一项所述的装置，其特征在于，所述第一处理单元具体用于：
    对所述首帧指纹图像进行图像预处理；
    基于图像预处理后的所述首帧指纹图像，并行地进行两次特征提取，分别得到所述首帧指纹图像的第一特征数据和第二特征数据，其中，所述第一特征数据是对图像预处理后的所述首帧指纹图像进行特征提取得到的，所述第二特征数据是对图像预处理后的所述第一指纹图像进行图像增强后再进行特征提取得到的。
  20. 根据权利要求19所述的装置，其特征在于，所述第一处理单元具体用于：
    若根据所述第一特征数据和所述第一指纹模板的模板数据进行指纹识别失败，则根据所述第二特征数据和所述第一指纹模板的模板数据进行指纹识别。
  21. 根据权利要求14至20中任一项所述的装置，其特征在于，所述第一处理单元具体用于：
    对所述非首帧指纹图像依次进行图像预处理、图像增强和特征提取。
  22. 根据权利要求14至21中任一项所述的装置，其特征在于，所述第二处理单元具体用于：
    对所述第二指纹模板进行解密和解压缩处理。
  23. 根据权利要求22所述的装置，其特征在于，所述第一处理单元为以下中的任意一种：中央处理器CPU、数字信号处理器DSP和视频处理单元VPU。
  24. 根据权利要求23所述的装置，其特征在于，所述第二处理单元为以下中的任意一种：CPU、DSP和VPU。
  25. 根据权利要求23或24所述的装置，其特征在于，所述CPU为进阶精简指令集机器ARM。
  26. 一种电子设备，其特征在于，包括：
    光学指纹传感器，用于采用至少一帧指纹图像；以及，
    根据权利要求14至25中任一项所述的指纹识别的装置。
PCT/CN2019/081427 2019-04-04 2019-04-04 指纹识别的方法、装置和电子设备 WO2020199178A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201980000496.3A CN110199295A (zh) 2019-04-04 2019-04-04 指纹识别的方法、装置和电子设备
PCT/CN2019/081427 WO2020199178A1 (zh) 2019-04-04 2019-04-04 指纹识别的方法、装置和电子设备

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2019/081427 WO2020199178A1 (zh) 2019-04-04 2019-04-04 指纹识别的方法、装置和电子设备

Publications (1)

Publication Number Publication Date
WO2020199178A1 true WO2020199178A1 (zh) 2020-10-08

Family

ID=67756126

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/081427 WO2020199178A1 (zh) 2019-04-04 2019-04-04 指纹识别的方法、装置和电子设备

Country Status (2)

Country Link
CN (1) CN110199295A (zh)
WO (1) WO2020199178A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111209556A (zh) * 2020-01-14 2020-05-29 北京集创北方科技股份有限公司 鉴权装置及电子设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104933411A (zh) * 2015-06-16 2015-09-23 迪安杰科技无锡有限公司 指纹识别处理方法及系统
CN107278308A (zh) * 2017-05-20 2017-10-20 深圳信炜科技有限公司 图像识别方法、图像识别装置、电子装置及计算机存储介质
CN107851186A (zh) * 2016-05-13 2018-03-27 指纹卡有限公司 使用并行处理的指纹认证
CN109543570A (zh) * 2018-11-06 2019-03-29 Oppo广东移动通信有限公司 指纹识别方法及相关产品

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN100414558C (zh) * 2002-12-06 2008-08-27 中国科学院自动化研究所 基于模板学习的自动指纹识别系统和方法
CN101483524A (zh) * 2009-02-25 2009-07-15 李苏 网络分布式指纹识别系统及其实现方法
US20150109214A1 (en) * 2013-10-22 2015-04-23 Weidong Shi Methods and Apparatuses of touch-fingerprinting Display
CN106682470A (zh) * 2015-11-09 2017-05-17 南昌欧菲生物识别技术有限公司 基于加密指纹信息的指纹识别系统、终端设备及方法
WO2017091933A1 (zh) * 2015-11-30 2017-06-08 宇龙计算机通信科技(深圳)有限公司 一种指纹采集方法、装置及电子设备
CN107831992B (zh) * 2016-03-14 2021-01-29 Oppo广东移动通信有限公司 解锁控制方法及相关产品
CN106022047B (zh) * 2016-05-24 2017-10-24 广东欧珀移动通信有限公司 一种指纹解锁方法及终端
CN106022069B (zh) * 2016-05-30 2019-08-20 Oppo广东移动通信有限公司 一种解锁控制方法及移动终端
CN106096360B (zh) * 2016-05-31 2019-02-22 Oppo广东移动通信有限公司 一种解锁控制方法及终端设备
CN106096515B (zh) * 2016-05-31 2019-10-25 Oppo广东移动通信有限公司 一种解锁控制方法及终端设备
CN108073885B (zh) * 2016-11-18 2021-11-12 比亚迪半导体股份有限公司 指纹识别方法及电子装置
WO2018148900A1 (zh) * 2017-02-16 2018-08-23 深圳市汇顶科技股份有限公司 基于指纹识别的校验方法、装置、以及交易系统

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104933411A (zh) * 2015-06-16 2015-09-23 迪安杰科技无锡有限公司 指纹识别处理方法及系统
CN107851186A (zh) * 2016-05-13 2018-03-27 指纹卡有限公司 使用并行处理的指纹认证
CN107278308A (zh) * 2017-05-20 2017-10-20 深圳信炜科技有限公司 图像识别方法、图像识别装置、电子装置及计算机存储介质
CN109543570A (zh) * 2018-11-06 2019-03-29 Oppo广东移动通信有限公司 指纹识别方法及相关产品

Also Published As

Publication number Publication date
CN110199295A (zh) 2019-09-03

Similar Documents

Publication Publication Date Title
CN110062931B (zh) 指纹识别装置、指纹识别方法和电子设备
WO2020093251A1 (zh) 基于双感应区的识别指纹方法、指纹识别系统和电子设备
WO2020168495A1 (zh) 用于指纹识别的方法、装置和终端设备
US11210491B2 (en) Fingerprint sensor under a display module with tilted receiving optics
CN109416739B (zh) 基于多传感器的屏下指纹采集方法、系统和电子设备
WO2020186415A1 (zh) 指纹识别的装置、方法和电子设备
CN111095275B (zh) 指纹识别的装置、方法和电子设备
US11048906B2 (en) Method and apparatus for fingerprint identification and terminal device
CN210181627U (zh) 指纹识别的装置和电子设备
EP3764277B1 (en) Fingerprint recognition method, apparatus, and electronic device
WO2021138776A1 (zh) 指纹防伪的方法、指纹识别装置和电子设备
WO2020220223A1 (zh) 用于指纹识别的方法和电子设备
CN111066027B (zh) 图像采集的装置、方法和电子设备
WO2020061748A1 (zh) 光学图像采集装置和电子设备
WO2020199178A1 (zh) 指纹识别的方法、装置和电子设备
WO2020172773A1 (zh) 指纹识别的方法、装置和电子设备
EP3770737B1 (en) Fingerprint recognition method and apparatus, and electronic device
WO2021056318A1 (zh) 指纹识别的方法、装置和电子设备
WO2020061734A1 (zh) 注册指纹的方法、指纹注册装置和电子设备
WO2020061754A1 (zh) 基于多传感器的屏下指纹认证方法、系统和电子设备
WO2020146984A1 (zh) 基于多安全环境的指纹识别方法、指纹识别系统和电子设备
CN111242111B (zh) 指纹识别方法、装置和电子设备
CN109564624B (zh) 辨识指纹Logo的方法、装置和电子设备
WO2021042248A1 (zh) 指纹检测的方法、装置和电子设备
WO2020191659A1 (zh) 一种应用于终端设备的屏下指纹识别方法以及终端设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19923316

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19923316

Country of ref document: EP

Kind code of ref document: A1