WO2023077640A1 - 指纹识别装置和识别方法、触控显示装置以及电子设备 - Google Patents

指纹识别装置和识别方法、触控显示装置以及电子设备 Download PDF

Info

Publication number
WO2023077640A1
WO2023077640A1 PCT/CN2021/141760 CN2021141760W WO2023077640A1 WO 2023077640 A1 WO2023077640 A1 WO 2023077640A1 CN 2021141760 W CN2021141760 W CN 2021141760W WO 2023077640 A1 WO2023077640 A1 WO 2023077640A1
Authority
WO
WIPO (PCT)
Prior art keywords
color
filter unit
image
finger
units
Prior art date
Application number
PCT/CN2021/141760
Other languages
English (en)
French (fr)
Inventor
冯继雄
田志民
王长海
李保梁
刘奇
Original Assignee
北京集创北方科技股份有限公司
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 北京集创北方科技股份有限公司 filed Critical 北京集创北方科技股份有限公司
Publication of WO2023077640A1 publication Critical patent/WO2023077640A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
    • G06F3/041—Digitisers, e.g. for touch screens or touch pads, characterised by the transducing means
    • 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

Definitions

  • the present application relates to the technical field of information processing, and in particular to a fingerprint identification device and identification method, a touch display device and electronic equipment.
  • Optical fingerprint under the screen is a fingerprint identification technology applied to mobile smart terminals. It perfectly integrates the optical fingerprint sensor under the display screen, without designing physical buttons. Users can directly touch the designated area of the mobile terminal display screen to realize fingerprint identification. . This technology drives the design innovation of mobile smart terminals, bringing users an unparalleled experience.
  • Fake fingerprints are usually made of materials such as silica gel.
  • silica gel When fingerprint recognition is attacked by a fingerprint mold, it is impossible to judge whether the collected image is a real finger or a mold, resulting in false recognition and unlocking.
  • the embodiment of the present application provides a fingerprint identification device to effectively identify the authenticity of the finger.
  • a fingerprint identification device which may include:
  • An image sensor located below the optical lens; the image sensor includes a pixel array with a plurality of pixel units;
  • a plurality of filter units are located above the plurality of pixel units, and below the optical lens, at least one filter unit has a coverage area larger or smaller than the area of a pixel unit; the plurality of filter units include transparent a filter unit and a color filter unit of at least one color;
  • the image sensor is configured to receive an optical signal reflected by the object to be identified above the screen and pass through the optical lens and the plurality of filter units to obtain a color fingerprint image, and the color fingerprint image is configured as It is used to determine whether the object to be recognized is a real finger.
  • the transparent filter unit may be configured to directly acquire an optical signal; the color filter unit may be configured to acquire an optical signal of a corresponding color; the pixel unit may be configured to The acquired light signals are converted into corresponding images.
  • the color filter units may be distributed above the plurality of pixel units in a manner of being dense in the middle and sparse in the edges.
  • the color filter units may be distributed above the plurality of pixel units in a spiral, radial or mosaic manner.
  • the color filter unit may include a filter unit of at least one color among a magenta filter unit, a cyan filter unit and a yellow filter unit.
  • the magenta filter unit can simultaneously allow red light bands and blue light bands to pass through; the cyan filter unit can simultaneously allow green wave bands and blue light bands to pass through; the yellow filter unit can simultaneously allow Red band and green band pass.
  • the central wavelength range of the magenta filter unit may be 440nm to 475nm, the upper cutoff wavelength may be 520nm, and the lower cutoff wavelength may be 620nm;
  • the central wavelength range of the cyan filter unit may be 460nm to 550nm, and the upper cut-off wavelength may be 620nm;
  • the central wavelength range of the yellow filter unit may be 520nm to 620nm, and the lower cut-off wavelength may be 460nm.
  • the transparent filter unit may be an infrared filter film coated on the pixel unit; or, the transparent filter unit may be an air gap; or, the transparent filter unit may be an The transparent optical medium other than the infrared filter film and the air gap.
  • the pixel unit covered with the color filter unit may be configured to acquire a color image of the finger for judging the authenticity of the finger, and the pixel unit covered with the transparent filter unit may be Configured to acquire grayscale images of fingerprints for fingerprint identification.
  • the ratio of the number of color filter units to the number of all pixel units can be controlled within a first threshold.
  • the ratio of the number of color filter units to the number of all pixel units may be less than 6%.
  • the number of consecutive color filter units may be less than seven.
  • the plurality of color filter units may be randomly distributed above the pixel array with unequal intervals.
  • the embodiment of the present application also provides a touch display device, and the touch display device may include:
  • the fingerprint identification device according to any one of the above, wherein the fingerprint identification device is located below the screen.
  • the screen is any one of a liquid crystal display panel, a micro light emitting diode display panel, a mini light emitting diode display panel, a quantum dot light emitting diode display panel and an organic light emitting diode display panel.
  • a fingerprint identification method which can be performed by the fingerprint identification device described in some embodiments of the present application, wherein the method may include:
  • the color fingerprint image includes a color image and a grayscale image
  • the fingerprint authentication fails.
  • the process of forming the color image may be as follows: placing the finger on the screen, the light spot under the screen is reflected by the finger, passes through the optical lens, and then passes through the light spot on the image sensor.
  • the color filter unit is configured to form the color image on the pixel units of the pixel array.
  • the process of forming the grayscale image may be as follows: placing the finger on the screen, the light spot under the light spot under the screen is reflected by the finger, passes through the optical lens, and then passes through the image sensor.
  • the transparent filter unit is used to form the grayscale image on the pixel units of the pixel array.
  • the step of determining whether the finger is genuine according to the color image may include: analyzing the color image through a classification algorithm of machine learning to classify real and fake fingers, thereby determining whether the finger is real or fake.
  • the embodiment of the present application also provides an electronic device, and the electronic device may include:
  • a touch display device according to any one of the above;
  • a central processing unit the central processing unit is communicatively connected to the touch display device.
  • a fingerprint recognition device which includes an optical lens under the screen, an image sensor under the optical lens, a pixel array in the image sensor, and a filter unit; wherein, the pixel array It includes a plurality of pixel units, and above the pixel units includes a transparent filter unit and a color filter unit of at least one color.
  • the device is used to effectively identify the authenticity of the finger: put the finger on the screen, the finger is reflected through the optical lens and multiple filter units to form a light signal, and the image sensor receives the light signal to form a color fingerprint image, according to the color fingerprint image can be Effective identification of true and false fingers.
  • Fig. 1 is the schematic diagram of the basic device of fingerprint identification in the background technology
  • FIG. 2 is a schematic structural diagram of a filter unit and a first pixel unit provided by an embodiment of the present application;
  • Fig. 3 is a color schematic diagram of the filter unit provided by the embodiment of the present application.
  • FIG. 4 is a schematic diagram of the color bands of the filter unit provided in the embodiment of the present application.
  • Fig. 5 is a schematic diagram of the wavelength band of the infrared filter film provided by the embodiment of the present application.
  • FIG. 6 is a schematic diagram of the distribution of filter units provided by the embodiment of the present application.
  • Fig. 7 is a schematic diagram of the arrangement of the filter unit provided by the embodiment of the present application.
  • FIG. 8 is a schematic flowchart of a fingerprint identification method provided by an embodiment of the present application.
  • Fig. 9 is a schematic diagram of color fingerprint image classification provided by the embodiment of the present application.
  • FIG. 10 is a schematic structural diagram of a touch display device provided by an embodiment of the present application.
  • FIG. 11 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • the fingerprint identification device of the present application may include an optical lens located under a screen, and an image sensor located under the optical lens, wherein the image sensor has a pixel array and a plurality of filter units.
  • the image sensor When performing fingerprint recognition, place your finger on the screen, and the light spot under the screen will enter the optical lens through the reflection of the finger, and then form an image on the image sensor.
  • the pixel array includes a plurality of pixel units, and the plurality of filter units include a transparent filter unit and a color filter unit of at least one color.
  • the transparent filter unit can be configured to directly obtain light signals; the color filter unit can be configured to obtain light signals of corresponding colors, such as the yellow filter unit to obtain yellow light signals; the pixel unit can be configured to obtain the obtained The light signal is converted into a corresponding image.
  • a plurality of filter units are located above the plurality of pixel units and below the optical lens, wherein at least one filter unit covers an area larger or smaller than that of a pixel unit.
  • one filter unit 221 covers three pixel units 212, that is, the coverage area of one filter unit 221 is larger than the area of one pixel unit 212; as shown in b in Figure 2, the filter unit 221 , the filter unit 222 and the filter unit 223 cover one pixel unit 212 , that is, the coverage area of one filter unit 221 is smaller than the area of one pixel unit 212 .
  • the coverage area of the filter unit of the present application is different from that of the pixel unit, and there is no need to completely align the filter unit with the pixel unit one-to-one, thereby reducing the difficulty of the process and improving the yield rate.
  • the color of the color filter unit is at least one of magenta 340 , cyan 350 or yellow 360 .
  • magenta 340 can be formed by mixing red 310 and blue 330
  • cyan 350 can be formed by mixing green 320 and blue 330
  • yellow can be formed by mixing red 310 and green 320 .
  • magenta 340 is formed by mixing red 310 and blue 330
  • the magenta filter unit can allow the passage of red and blue light bands
  • cyan 350 is formed by mixing green 320 and blue 330, so the cyan filter unit
  • the unit can allow green and blue bands to pass through
  • yellow is formed by mixing red 310 and green 320, so the yellow filter unit can allow red and green bands to pass through.
  • the wavelength range of the blue filter can be 440nm to 475nm in the central wavelength range, and the upper cutoff wavelength range is about 550nm; They are 620nm and 460nm respectively; the wavelength range of the red filter can be about 550nm at the lower cut-off wavelength.
  • the central wavelength range of the magenta filter unit is 440nm to 475nm, the upper cut-off wavelength is 520nm, and the lower cut-off wavelength is 620nm.
  • the magenta filter unit When the magenta filter unit is used, the magenta light on the color filter unit The transmittance is higher than that of cyan light and yellow light; the central wavelength range of the cyan filter unit is 460nm to 550nm, and the upper cut-off wavelength is 620nm.
  • the transmittance of cyan light on the color filter unit Higher than magenta light and yellow light; the central wavelength range of the yellow filter unit is 520nm to 620nm, and the lower cut-off wavelength is 460nm.
  • the transmittance of yellow light on the color filter unit is higher than that of Magenta light and cyan light.
  • the transparent filter unit may be an infrared filter film coated on the pixel unit, as shown in FIG. 5 , the upper cut-off wavelength of the infrared filter film is 660 nm.
  • the fingerprint image collected by the pixel unit is a fingerprint image with infrared rays filtered out.
  • the transparent filter unit can also be an air gap, or a transparent optical medium other than the infrared filter film and the air gap. Therefore, the pixel unit covering the color filter unit can be configured to obtain a color image of the finger for fingerprint identification, and the pixel unit covering the transparent filter unit can be configured to obtain a grayscale image of the fingerprint for fingerprint identification.
  • the fingerprint identification device of the present application can be used for fingerprint identification, while avoiding the judgment of a fake finger that is not the user's own. Its realization can be achieved by controlling the number of filter units to ensure the efficiency of fingerprint identification, and combining the number of color filter units with the The ratio of the numbers of all pixel units is controlled within the first threshold. In one embodiment, the ratio of the number of color filter units to the number of all pixel units is less than 6%.
  • the number of consecutive color filter units is less than seven.
  • Multiple color filter units can be randomly distributed above the pixel array with unequal intervals.
  • the color filter units may be adjacent or non-adjacent, so discrete distribution or continuous distribution may be used.
  • FIG. 6 it shows a situation where multiple color filter units are randomly distributed above the pixel array.
  • the distribution of random unequal spacing is conducive to fingerprint identification and can also realize the judgment of the authenticity of the finger.
  • the color filter units can be distributed over the plurality of pixel units in a manner of being dense in the middle and sparse in the edges. Since the finger touches more in the middle area, more color filter units can be arranged in the middle area, and relatively few color filter units can be arranged in the edge, so as to realize the effective utilization of the color filter units.
  • the color filter units can also be distributed above the pixel array according to a certain shape. As shown in a in Figure 7, a plurality of color filter units are distributed above the pixel array in a spiral shape; as shown in b in Figure 7, a plurality of color filter units are distributed in the pixel array in a radial shape above; as shown in c in FIG. 7 , a plurality of color filter units are distributed above the pixel array in a mosaic shape. It should be noted that the spiral lines and radial lines in the figure are only used to indicate the shape of the arrangement of the color filter units, not real lines.
  • the fingerprint identification device of the present application can effectively identify whether the finger is the user's own finger, and avoid finger molds for fingerprint identification. It puts the finger on the top of the screen, forms an optical signal through an optical lens and multiple filter units, and the optical signal is generated by the image.
  • the sensor receives and forms a color fingerprint image, and the color fingerprint image can effectively determine the authenticity of the finger.
  • FIG. 8 is a schematic flowchart of a fingerprint identification method provided by an embodiment of the present application. As shown in FIG. 5, the method can be performed by the above-mentioned fingerprint identification device, and the method can include the following steps S810-step S850:
  • Step S810 Obtain a color fingerprint image in the image sensor, wherein the color fingerprint image includes a color image and a grayscale image.
  • the color fingerprint image formed in the image sensor is acquired, and the color fingerprint image includes a color image and a grayscale image.
  • the formation process of the color image is: place your finger on the screen, the light spot under the screen is reflected by the finger, passes through the optical lens, and then passes through the color filter unit on the image sensor to form on the pixel unit of the pixel queue.
  • Color image; the formation process of grayscale image is: put your finger on the screen, the light spot under the light spot under the screen is reflected by the finger, passes through the optical lens, and then passes through the transparent filter unit on the image sensor.
  • a grayscale image is formed on the pixel unit.
  • Step S820 Determine whether the finger is real according to the color image.
  • the color image is analyzed through a classification algorithm of machine learning to realize the classification of real and fake fingers, so as to determine the authenticity of the fingers.
  • classification models that can be selected include support vector machines, decision trees, Bayesian and other models.
  • a color image is analyzed.
  • the color images of the known true and false fingers can be divided into two parts: 80% of the code segment is used as a training data set; 20% of the code segment is used as a verification data set.
  • For the training data set set its color image as the input parameter x, and set the true and false fingers corresponding to the color image as the output result f(x).
  • Build a decision tree model and put the verification data set into the model to continuously iterate the training model to obtain the decision tree model that fits the training data set closest.
  • the verification data set is used to prune the generated decision tree model and select the optimal subtree, that is, the optimal decision tree model is obtained by setting the loss function.
  • the regularized maximum likelihood function is usually chosen as the loss function.
  • the color image of the unknown finger is true or false as the input parameter x, input in the obtained optimal decision tree model, the output of the optimal decision tree model corresponds to f(x), this f(x) is the color image finger true False judgment result.
  • Step S830 If the finger is true, determine whether the grayscale image is successfully matched.
  • the fingerprint information missing from the pixel unit in the gray-scale image can be interpolated or fitted to obtain a complete gray-scale fingerprint image.
  • Step S840 If the grayscale image is successfully matched, the fingerprint authentication is successful.
  • the fingerprint authentication is successful, and the fingerprint can be successfully accessed into mobile phones, computers and other devices.
  • Step S850 If the color image and the grayscale image in the image sensor cannot be acquired, the finger is fake or the grayscale image fails to match, then the fingerprint authentication fails.
  • the fingerprint authentication fails; when the output f(x) shows that the finger in the color image is false, the fingerprint authentication fails; when the grayscale image and the input If the fingerprint matching fails, the fingerprint entry fails.
  • Fig. 10 is a touch display device 1000 shown in an embodiment of the present application.
  • the touch display device 1000 may include a screen 1010 and a fingerprint recognition device 1020, wherein the screen 1010 may be a liquid crystal display panel, a micro-light emitting diode display panel, a mini Any one of a light emitting diode display panel, a quantum dot light emitting diode display panel and an organic light emitting diode display panel.
  • the fingerprint recognition device 1020 may be the fingerprint recognition device in the foregoing device embodiments, which can be used to execute the content in the method embodiment shown in FIG. 8 , and for the sake of brevity, details are not repeated here.
  • Fig. 11 shows an electronic device 1100 according to an embodiment of the present application.
  • the electronic device 1100 may include a central processing unit 1110 and a touch display device 1120, wherein the central processing unit 1110 is connected to the touch display device 1120 in communication, and the touch display
  • the device 1120 may be the touch display device in the aforementioned device embodiments.
  • the disclosed devices and devices may also be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the flow charts and block diagrams in the accompanying drawings show the architecture, functions and possible implementations of devices, devices and computer program products according to multiple embodiments of the present application. operate.
  • each block in a flowchart or block diagram may represent a module, program segment, or portion of code that contains one or more executable instruction.
  • the functions noted in the block may occur out of the order noted in the figures.
  • two blocks in succession may, in fact, be executed substantially concurrently, or they may sometimes be executed in the reverse order, depending upon the functionality involved.
  • each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations can be implemented by a dedicated hardware-based system that performs the specified function or action , or may be implemented by a combination of dedicated hardware and computer instructions.
  • each functional module in each embodiment of the present application may be integrated to form an independent part, each module may exist independently, or two or more modules may be integrated to form an independent part.
  • the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium.
  • the computer software product is stored in a storage medium, including several
  • the instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the apparatus in various embodiments of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disc, etc., which can store program codes. .
  • the present application provides a fingerprint identification device and identification method, a touch display device and electronic equipment.
  • the fingerprint identification device includes: an optical lens located under a screen; an image sensor located under the optical lens; the image sensor includes a plurality of A pixel array of pixel units; a plurality of filter units are located above the plurality of pixel units and below the optical lens, at least one filter unit has a coverage area larger or smaller than the area of a pixel unit; the plurality of filter units include transparent A filter unit and a color filter unit of at least one color; the image sensor is configured to receive an optical signal reflected by an object to be identified above the screen and pass through an optical lens and a plurality of filter units to obtain a color fingerprint image.
  • the fingerprint image is configured to determine whether the object to be identified is a real finger.
  • the scheme obtains the color information of the finger by using the color filter unit to effectively identify the authenticity of the finger.
  • the fingerprint identification device and identification method, touch display device and electronic equipment of the present application are reproducible and can be used in various industrial applications.
  • the fingerprint identification device and identification method, touch display device and electronic equipment of the present application can be used in the technical field of information processing.

Abstract

本申请提供一种指纹识别装置、触控显示装置以及电子设备，指纹识别装置包括：光学透镜，位于一屏幕的下方；图像传感器，位于光学透镜的下方；图像传感器包括具有多个像素单元的像素阵列；多个滤光单元，位于多个像素单元的上方，光学透镜的下方，至少有一个滤光单元的覆盖面积大于或小于一个像素单元的面积；多个滤光单元包括透明滤光单元及至少一种颜色的彩色滤光单元；图像传感器配置成用于接收屏幕上方的待识别对象反射的并穿过光学透镜和多个滤光单元的光信号，得到彩色指纹图像，彩色指纹图像配置成用于确定所述待识别对象是否为真实手指。该方案通过利用彩色滤光单元，获取手指的颜色信息，有效识别手指的真假。

Description

指纹识别装置和识别方法、触控显示装置以及电子设备
相关申请的交叉引用
本申请要求于2021年11月05日提交中国国家知识产权局的申请号为202111306750.8、名称为“指纹识别装置、触控显示装置以及电子设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及信息处理技术领域，特别涉及一种指纹识别装置和识别方法、触控显示装置以及电子设备。
背景技术
屏下光学指纹是一种应用于移动智能终端的指纹识别技术，其将光学指纹传感器完美地集成到显示屏下，无需设计实体按键，用户直接轻触移动终端显示屏指定区域即可实现指纹识别。该技术驱动了移动智能终端的设计革新，为用户带来无与伦比的使用体验。
但是，目前假指纹的出现降低了指纹识别装置的安全性。假指纹通常是利用硅胶等材料做成，指纹识别在受到指纹模具攻击时，无法判断采集的图像是否为真手指还是模具，从而造成错误识别和解锁。
发明内容
本申请实施例提供了指纹识别装置，用以有效识别手指真假的问题。
本申请的一些实施例提供了一种指纹识别装置，可以包括：
光学透镜，位于一屏幕的下方；
图像传感器，位于所述光学透镜的下方；所述图像传感器包括具有多个像素单元的像素阵列；
多个滤光单元，位于所述多个像素单元的上方，所述光学透镜的下方，至少有一个滤光单元的覆盖面积大于或小于一个像素单元的面积；所述多个滤光单元包括透明滤光单元及至少一种颜色的彩色滤光单元；
所述图像传感器配置成用于接收所述屏幕上方的待识别对象反射的并穿过所述光学透镜和所述多个滤光单元的光信号，得到彩色指纹图像，所述彩色指纹图像配置成用于确定所述待识别对象是否为真实手指。
在一实施例中，所述透明滤光单元可以配置成用于直接获取光信号；所述彩色滤光单元可以配置成用于获取对应颜色的光信号；所述像素单元可以配置成用于将获取的光信号转换成对应的图像。
在一实施例中，所述彩色滤光单元可以以中间密、边缘疏的方式分布在所述多个像素 单元上方。
在一实施例中，所述彩色滤光单元可以以螺旋状、放射状或马赛克形状的方式分布在所述多个像素单元上方。
在一实施例中，所述彩色滤光单元可以包括品红色滤光单元、青色滤光单元和黄色滤光单元中的至少一种颜色的滤光单元。
在一实施例中，所述品红色滤光单元可以同时允许红光波段和蓝光波段通过；所述青色滤光单元可以同时允许绿色波段和蓝色波段通过；所述黄色滤光单元可以同时允许红色波段和绿色波段通过。
在一实施例中，所述品红色滤光单元的中心波段范围可以是440nm至475nm，上截止波长可以为520nm，下截止波长可以为620nm；
所述青色滤光单元的中心波段范围可以是460nm至550nm，上截止波长可以为620nm；
所述黄色滤光单元的中心波段范围可以是520nm至620nm，下截止波长可以为460nm。
在一实施例中，所述透明滤光单元可以为涂覆在像素单元上的红外滤光膜；或者，所述透明滤光单元可以为空气间隙；或者，所述透明滤光单元可以为除所述红外滤光膜和空气间隙以外的透明光学介质。
在一实施例中，覆盖有所述彩色滤光单元的所述像素单元可以配置成用于获取手指的彩色图像进行手指真假的判断，覆盖有所述透明滤光单元的所述像素单元可以配置成用于获取指纹的灰度图像进行指纹识别。
在一实施例中，所述彩色滤光单元的数量与所有像素单元的数量之比可以控制在第一阈值内。
在一实施例中，所述彩色滤光单元的数量与所有像素单元的数量之比可以小于6％。
在一实施例中，连续的所述彩色滤光单元的数量可以小于7个。
在一实施例中，所述多个彩色滤光单元随机可以分布在所述像素阵列的上方，间距不相等。
本申请实施例还提供了一种触控显示装置，所述触控显示装置可以包括：
屏幕；
上述任意一项的指纹识别装置，所述指纹识别装置位于所述屏幕的下方。
在一实施例中，所述屏幕为液晶显示面板、微发光二极管显示面板、迷你发光二极管显示面板、量子点发光二极管显示面板和有机发光二极管显示面板中的任意一种。
本申请的另一些实施例提供了一种指纹识别方法，所述方法能够由本申请的一些实施例所述的指纹识别装置来执行，其特征在于，所述方法可以包括：
获取图像传感器中的彩色指纹图像，其中，所述彩色指纹图像包括彩色图像和灰度图 像；
根据所述彩色图像确定手指是否为真；
若所述手指为真，判断所述灰度图像是否匹配成功；
若所述灰度图像匹配成功，则指纹认证成功；
若无法获取所述图像传感器中的所述彩色图像和所述灰度图像、所述手指为假或所述灰度图像匹配失败，则指纹认证失败。
在一实施例中，所述彩色图像的形成过程可以为：将所述手指放置在屏幕上，屏幕下的光斑下经所述手指的反射穿过光学透镜，再穿过所述图像传感器上的彩色滤光单元，在像素队列的像素单元上形成所述彩色图像。
在一实施例中，所述灰度图像的形成过程可以为：将所述手指放置在屏幕上，屏幕下的光斑下的光斑经所述手指的反射穿过光学透镜，再穿过图像传感器上的透明滤光单元，在像素队列的像素单元上形成所述灰度图像。
在一实施例中，根据所述彩色图像确定手指是否为真的步骤可以包括：通过机器学习的分类算法来分析所述彩色图像，实现真假手指的分类，从而确定所述手指的真假。
本申请实施例还提供了一种电子设备，所述电子设备可以包括：
上述任意一项的触控显示装置；
中央处理单元，所述中央处理单元与所述触控显示装置通信连接。
本申请上述实施例提供的技术方案，设计了一种指纹识别装置，该装置包括一屏幕下方的光学透镜、光学透镜下方的图像传感器、图像传感器中的像素阵列和滤光单元；其中，像素阵列包括多个像素单元，像素单元的上方包括透明滤光单元及至少一种颜色的彩色滤光单元。该装置用于有效识别手指的真假：将手指放在屏幕上方，手指经反射穿过光学透镜和多个滤光单元形成光信号，图像传感器接收光信号形成彩色指纹图像，根据彩色指纹图像能够有效识别手指的真假。
附图说明
为了更清楚地说明本申请实施例的技术方案，下面将对本申请实施例中所需要使用的附图作简单地介绍。
图1为背景技术中指纹识别的基本装置示意图；
图2为本申请实施例提供的滤光单元和第一像素单元的结构示意图；
图3为本申请实施例提供的滤光单元的颜色示意图；
图4为本申请实施例提供的滤光单元的颜色波段示意图；
图5为本申请实施例提供的红外滤光膜的波段示意图；
图6为本申请实施例提供的滤光单元的分布示意图；
图7为本申请实施例提供的滤光单元的排布示意图；
图8为本申请实施例提供的一种指纹识别方法的流程示意图；
图9为本申请实施例提供的彩色指纹图像分类示意图；
图10为本申请实施例提供的触控显示装置的结构示意图；
图11为本申请实施例提供的电子设备的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行描述。
相似的标号和字母在下面的附图中表示类似项，因此，一旦某一项在一个附图中被定义，则在随后的附图中不需要对其进行进一步定义和解释。同时，在本申请的描述中，术语“第一”、“第二”等仅用于区分描述，而不能理解为指示或暗示相对重要性。
如图1所示，本申请的指纹识别装置可以包括位于一屏幕下方的光学透镜、位于光学透镜下方的图像传感器，其中，图像传感器具有像素队列和多个滤光单元。在进行指纹识别时，将手指放置于屏幕上，屏幕下的光斑经过手指的反射进入光学透镜，进而在图像传感器上成像。像素队列包括多个像素单元，多个滤光单元包括透明滤光单元及至少一种颜色的彩色滤光单元。透明滤光单元可以配置成用于直接获取光信号；彩色滤光单元可以配置成用于获取对应颜色的光信号，如黄色滤光单元获取黄色光信号；像素单元可以配置成用于将获取的光信号转换成对应的图像。
多个滤光单元位于多个像素单元的上方，光学透镜的下方，其中，至少有一个滤光单元的覆盖面积大于或小于一个像素单元的面积。如图2中a所示，一个滤光单元221覆盖在三个像素单元212上，即一个滤光单元221的覆盖面积大于一个像素单元212的面积；如图2中b所示，滤光单元221、滤光单元222和滤光单元223覆盖在一个像素单元212上，即一个滤光单元221的覆盖面积小于一个像素单元212的面积。
需要说明的是，本申请的滤光单元的覆盖面积与像素单元覆盖面积不同，无需使滤光单元与像素单元一对一完全对准，从而降低了工艺难度，提高了良品率。
如图3所示，本申请实施例中，彩色滤光单元的颜色至少为品红色340、青色350或黄色360中的一种。根据自然界的三基色原理，品红色340可以由红色310和蓝色330混合而成，青色350可以由绿色320和蓝色330混合而成，黄色可以由红色310和绿色320混合而成。
由于品红色340是由红色310和蓝色330混合而成，故品红色滤光单元能够允许红光波段和蓝光波段通过；青色350是由绿色320和蓝色330混合而成，故青色滤光单元能够允许绿色波段和蓝色波段通过；黄色是由红色310和绿色320混合而成，故黄色滤光单元能够允许红色波段和绿色波段通过。
在一实施例中，蓝色滤光片的波段范围可以是中心波段为440nm～475nm，上截止波段约为550nm；绿色滤光片的波段范围可以是中心波段为520nm～550nm，上下截止波段约分别为620nm、460nm；红色滤光片的波段范围可以是下截止波段约为550nm。如图4所示，品红色滤光单元的中心波段范围是440nm至475nm，上截止波长为520nm，下截止波长为620nm，当采用品红色滤光单元时，在彩色滤光单元上品红色光的透过率高于青色光和黄色光；青色滤光单元的中心波段范围是460nm至550nm，上截止波长为620nm，当采用青色滤光单元时，在彩色滤光单元上青色光的透过率高于品红色光和黄色光；黄色滤光单元的中心波段范围是520nm至620nm，下截止波长为460nm，当采用黄色滤光单元时，在彩色滤光单元上黄色光的透过率高于品红色光和青色光。
于一实施例中，透明滤光单元上可以为涂覆在像素单元上的红外滤光膜，如图5所示，红外滤光膜的上截止波长为660nm。如此，指纹检测信号经过该透明滤光单元后，经像素单元所采集的为滤除红外光线的指纹图像。如此，可避免红外光等环境光信号的影响，从而能够提升指纹识别性能。透明滤光单元也可以为空气间隙，或者除红外滤光膜和空气间隙以外的透明光学介质。因此，覆盖彩色滤光单元的像素单元可以配置成用于获取手指的彩色图像进行手指真假的判断，覆盖透明滤光单元的像素单元可以配置成用于获取指纹的灰度图像进行指纹识别。
本申请的指纹识别装置可用于指纹识别，同时避免非用户本人的假手指的判断，其实现方式可以通过控制滤光单元的数量，以保证指纹识别的效率，并且将彩色滤光单元的数量与所有像素单元的数量之比控制在第一阈值内。在一实施例中，彩色滤光单元的数量与所有像素单元的数量之比小于6％。
当多个彩色滤光单元在像素阵列的上方连续分布，且连续数量过多，则会导致连续部分的指纹无法被识别，故需要将连续的多个彩色滤光单元的数量控制在第二阈值内。在一实施例中，连续的多个彩色滤光单元的数量小于7个。
多个彩色滤光单元可随机分布在像素阵列的上方，间距不相等。在随机分布时，彩色滤光单元可能存在相邻现象，也可能存在不相邻现象，因此可以采用离散分布的方式，或是也可以采用连续分布的方式。如图6所示，展示了一种多个彩色滤光单元随机分布在像素阵列上方的情形，该随机不等间距的分布情况有利于指纹识别，也能实现手指真假的判断。
彩色滤光单元可按照中间密、边缘疏的方式分布在多个像素单元上方。由于手指在中间区域的接触较多，故可以在中间区域设置较多的彩色滤光单元，边缘设置相对较少的彩色滤光单元，实现彩色滤光单元的有效利用。
彩色滤光单元也可按照一定的形状分布在像素阵列的上方。如图7中a所示，多个彩 色滤光单元按照螺旋线形状分布在所述像素阵列的上方；如图7中b所示，多个彩色滤光单元按照放射线形状分布在所述像素阵列的上方；如图7中c所示，多个彩色滤光单元按照马赛克形状分布在所述像素阵列的上方。需要说明的是，图中的螺旋线和放射线仅用于指示彩色滤光单元排布的形状，不是真实存在的线。
本申请的指纹识别该装置能够有效识别手指是否为用户本人的手指，避免手指模具进行指纹识别，其通过手指放在屏幕上方，经由光学透镜和多个滤光单元形成光信号，光信号由图像传感器接收形成彩色指纹图像，彩色指纹图像进而有效的确定手指的真假。
图8为本申请实施例提供的一种指纹识别方法的流程示意图。如图5所示，该方法可由上述指纹识别装置来执行，该方法可以包括以下步骤S810-步骤S850：
步骤S810：获取图像传感器中的彩色指纹图像，其中，彩色指纹图像包括彩色图像和灰度图像。
在本步骤中，获取图像传感器中形成的彩色指纹图像，彩色指纹图像包括彩色图像和灰度图像。其中，彩色图像的形成过程为：将手指放置在屏幕上，屏幕下的光斑下经手指的反射穿过光学透镜，再穿过图像传感器上的彩色滤光单元，在像素队列的像素单元上形成彩色图像；灰度图像的形成过程为：将手指放置在屏幕上，屏幕下的光斑下的光斑经手指的反射穿过光学透镜，再穿过图像传感器上的透明滤光单元，在像素队列的像素单元上形成灰度图像。
步骤S820：根据彩色图像确定手指是否为真。
在本步骤中，如图9所示，通过机器学习的分类算法来分析彩色图像，实现真假手指的分类，从而确定手指的真假。可以选取的分类模型有支持向量机、决策树、贝叶斯等模型。
以决策树模型为例，对彩色图像进行分析。将已知手指真假的彩色图像可以分为两部分，分别为：80％的代码段作为训练数据集；20％的代码段作为验证数据集。
对于训练数据集，将其彩色图像设置为输入参数x，彩色图像对应的手指真假设置为输出结果f(x)。构建决策树模型，并将验证数据集放入模型中不断迭代训练模型，得到对训练数据集拟合最接近的决策树模型。
训练数据集对模型训练完毕后，再用验证数据集对已生成的决策树模型进行剪枝并选择最优子树，即通过设置损失函数来获得最优决策树模型。通常选取正则化的极大似然函数作为损失函数。
将未知手指真假的彩色图像作为输入参数x，在获得的最优决策树模型中输入，最优决策树模型的输出对应的f(x)，此f(x)即为该彩色图像手指真假的判定结果。
步骤S830：若手指为真，判断灰度图像是否匹配成功。
在本步骤中，若输出的f(x)显示彩色图像中的手指为真，则进行灰度图像的匹配，并判断该灰度图像与录入的指纹是否匹配成功。
在进行灰度指图像的匹配之前，可以先对灰度图像中像素单元缺失的指纹信息进行插值或拟合等处理，得到完整的灰度指纹图像。
步骤S840：若灰度图像匹配成功，则指纹认证成功。
在本步骤中，当灰度指纹图像与录入的指纹匹配成功，则该指纹认证成功，可成功进入手机、电脑等设备。
步骤S850：若无法获取图像传感器中的彩色图像和灰度图像、手指为假或灰度图像匹配失败，则指纹认证失败。
在本步骤中，当无法获取图像传感器中的彩色图像和指纹图像，则指纹认证失败；当输出的f(x)显示彩色图像中的手指为假，则指纹认证失败；当灰度图像与录入的指纹匹配失败，则指纹录入失败。
图10为本申请一实施例示出的一种触控显示装置1000，触控显示装置1000可以包括屏幕1010和指纹识别装置1020，其中，屏幕1010可以为液晶显示面板、微发光二极管显示面板、迷你发光二极管显示面板、量子点发光二极管显示面板和有机发光二极管显示面板中的任意一种。指纹识别装置1020可以为前述装置实施例中的指纹识别装置，其能够用于执行图8中所述方法实施例中的内容，为了简洁，这里不再赘述。
图11为本申请一实施例示出的一种电子设备1100，电子设备1100可以包括中央处理单元1110和触控显示装置1120，其中，中央处理单元1110与触控显示装置1120通信连接，触控显示装置1120可以为前述装置实施例中的触控显示装置。在本申请所提供的几个实施例中，所揭露的装置和装置，也可以通过其它的方式实现。以上所描述的装置实施例仅仅是示意性的，例如，附图中的流程图和框图显示了根据本申请的多个实施例的装置、装置和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段或代码的一部分，模块、程序段或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。在有些作为替换的实现方式中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个连续的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或动作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
另外，在本申请各个实施例中的各功能模块可以集成在一起形成一个独立的部分，也可以是各个模块单独存在，也可以两个或两个以上模块集成形成一个独立的部分。
功能如果以软件功能模块的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对相关技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例装置的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
工业实用性
本申请提供了一种指纹识别装置和识别方法、触控显示装置以及电子设备，指纹识别装置包括：光学透镜，位于一屏幕的下方；图像传感器，位于光学透镜的下方；图像传感器包括具有多个像素单元的像素阵列；多个滤光单元，位于多个像素单元的上方，光学透镜的下方，至少有一个滤光单元的覆盖面积大于或小于一个像素单元的面积；多个滤光单元包括透明滤光单元及至少一种颜色的彩色滤光单元；图像传感器配置成用于接收屏幕上方的待识别对象反射的并穿过光学透镜和多个滤光单元的光信号，得到彩色指纹图像，彩色指纹图像配置成用于确定所述待识别对象是否为真实手指。该方案通过利用彩色滤光单元，获取手指的颜色信息，有效识别手指的真假。
此外，可以理解的是，本申请的指纹识别装置和识别方法、触控显示装置以及电子设备是可以重现的，并且可以用在多种工业应用中。例如，本申请的指纹识别装置和识别方法、触控显示装置以及电子设备可以用于信息处理技术领域。

Claims (20)

  1. 一种指纹识别装置，其特征在于，包括：
    光学透镜，位于一屏幕的下方；
    图像传感器，位于所述光学透镜的下方；所述图像传感器包括具有多个像素单元的像素阵列；
    多个滤光单元，位于所述多个像素单元的上方，所述光学透镜的下方，至少有一个滤光单元的覆盖面积大于或小于一个像素单元的面积；所述多个滤光单元包括透明滤光单元及至少一种颜色的彩色滤光单元；
    所述图像传感器配置成用于接收所述屏幕上方的待识别对象反射的并穿过所述光学透镜和多个滤光单元的光信号，得到彩色指纹图像，所述彩色指纹图像配置成用于确定所述待识别对象是否为真实手指。
  2. 根据权利要求1所述的装置，其特征在于，所述透明滤光单元配置成用于直接获取光信号；所述彩色滤光单元配置成用于获取对应颜色的光信号；所述像素单元配置成用于将获取的光信号转换成对应的图像。
  3. 根据权利要求1或2所述的装置，其特征在于，所述彩色滤光单元以中间密、边缘疏的方式分布在所述多个像素单元上方。
  4. 根据权利要求1或2所述的装置，其特征在于，所述彩色滤光单元以螺旋状、放射状或马赛克形状的方式分布在所述多个像素单元上方。
  5. 根据权利要求1至3中任一项所述的装置，其特征在于，所述彩色滤光单元包括品红色滤光单元、青色滤光单元和黄色滤光单元中的至少一种颜色的滤光单元。
  6. 根据权利要求5所述的装置，其特征在于，所述品红色滤光单元同时允许红光波段和蓝光波段通过；所述青色滤光单元同时允许绿色波段和蓝色波段通过；所述黄色滤光单元同时允许红色波段和绿色波段通过。
  7. 根据权利要求6所述的装置，其特征在于，所述品红色滤光单元的中心波段范围是440nm至475nm，上截止波长为520nm，下截止波长为620nm；
    所述青色滤光单元的中心波段范围是460nm至550nm，上截止波长为620nm；
    所述黄色滤光单元的中心波段范围是520nm至620nm，下截止波长为460nm。
  8. 根据权利要求1至7中任一项所述的装置，其特征在于，
    所述透明滤光单元为涂覆在像素单元上的红外滤光膜；或者，所述透明滤光单元为空气间隙；或者，所述透明滤光单元为除所述红外滤光膜和空气间隙以外的透明光学介质。
  9. 根据权利要求1至8中任一项所述的装置，其特征在于，覆盖有所述彩色滤光单元 的所述像素单元配置成用于获取手指的彩色图像进行手指真假的判断，覆盖有所述透明滤光单元的所述像素单元配置成用于获取指纹的灰度图像进行指纹识别。
  10. 根据权利要求1至9中任一项所述的装置，其特征在于，所述彩色滤光单元的数量与所有像素单元的数量之比控制在第一阈值内。
  11. 根据权利要求1至10中任一项所述的装置，其特征在于，所述彩色滤光单元的数量与所有像素单元的数量之比小于6％。
  12. 根据权利要求1至11中任一项所述的装置，其特征在于，连续的所述彩色滤光单元的数量小于7个。
  13. 根据权利要求1至12中任一项所述的装置，其特征在于，多个所述彩色滤光单元随机分布在所述像素阵列的上方，间距不相等。
  14. 一种触控显示装置，其特征在于，包括：
    屏幕；
    权利要求1-13任意一项所述的指纹识别装置，所述指纹识别装置位于所述屏幕的下方。
  15. 根据权利要求14所述的触控显示装置，其特征在于，所述屏幕为液晶显示面板、微发光二极管显示面板、迷你发光二极管显示面板、量子点发光二极管显示面板和有机发光二极管显示面板中的任意一种。
  16. 一种指纹识别方法，所述方法能够由权利要求1至15中任一项所述的指纹识别装置来执行，其特征在于，所述方法包括：
    获取图像传感器中的彩色指纹图像，其中，所述彩色指纹图像包括彩色图像和灰度图像；
    根据所述彩色图像确定手指是否为真；
    若所述手指为真，判断所述灰度图像是否匹配成功；
    若所述灰度图像匹配成功，则指纹认证成功；
    若无法获取所述图像传感器中的所述彩色图像和所述灰度图像、所述手指为假或所述灰度图像匹配失败，则指纹认证失败。
  17. 根据权利要求16所述的指纹识别方法，其特征在于，所述彩色图像的形成过程为：将所述手指放置在屏幕上，屏幕下的光斑下经所述手指的反射穿过光学透镜，再穿过所述图像传感器上的彩色滤光单元，在像素队列的像素单元上形成所述彩色图像。
  18. 根据权利要求16或17所述的指纹识别方法，其特征在于，所述灰度图像的形成过程为：将所述手指放置在屏幕上，屏幕下的光斑下的光斑经所述手指的反射穿过光学透镜，再穿过图像传感器上的透明滤光单元，在像素队列的像素单元上形成所述灰度图像。
  19. 根据权利要求16至18中任一项所述的指纹识别方法，其特征在于，根据所述彩色 图像确定手指是否为真的步骤包括：通过机器学习的分类算法来分析所述彩色图像，实现真假手指的分类，从而确定所述手指的真假。
  20. 一种电子设备，其特征在于，包括：
    权利要求14或15所述的触控显示装置；
    中央处理单元，所述中央处理单元与所述触控显示装置通信连接。
PCT/CN2021/141760 2021-11-05 2021-12-27 指纹识别装置和识别方法、触控显示装置以及电子设备 WO2023077640A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111306750.8 2021-11-05
CN202111306750.8A CN116092135A (zh) 2021-11-05 2021-11-05 指纹识别装置、触控显示装置以及电子设备

Publications (1)

Publication Number Publication Date
WO2023077640A1 true WO2023077640A1 (zh) 2023-05-11

Family

ID=86201155

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/141760 WO2023077640A1 (zh) 2021-11-05 2021-12-27 指纹识别装置和识别方法、触控显示装置以及电子设备

Country Status (2)

Country Link
CN (1) CN116092135A (zh)
WO (1) WO2023077640A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180225502A1 (en) * 2014-08-26 2018-08-09 Gingy Technology Inc. Fingerprint identification device and fingerprint identification method
CN111507229A (zh) * 2019-11-01 2020-08-07 深圳市汇顶科技股份有限公司 指纹识别装置和电子设备
CN111611952A (zh) * 2020-05-27 2020-09-01 深圳市汇顶科技股份有限公司 指纹识别装置和电子设备
CN111837132A (zh) * 2020-03-27 2020-10-27 深圳市汇顶科技股份有限公司 指纹检测的装置和电子设备
CN112069942A (zh) * 2020-08-24 2020-12-11 深圳阜时科技有限公司 屏下光学检测系统及电子设备

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20180225502A1 (en) * 2014-08-26 2018-08-09 Gingy Technology Inc. Fingerprint identification device and fingerprint identification method
CN111507229A (zh) * 2019-11-01 2020-08-07 深圳市汇顶科技股份有限公司 指纹识别装置和电子设备
CN111837132A (zh) * 2020-03-27 2020-10-27 深圳市汇顶科技股份有限公司 指纹检测的装置和电子设备
CN111611952A (zh) * 2020-05-27 2020-09-01 深圳市汇顶科技股份有限公司 指纹识别装置和电子设备
CN112069942A (zh) * 2020-08-24 2020-12-11 深圳阜时科技有限公司 屏下光学检测系统及电子设备

Also Published As

Publication number Publication date
CN116092135A (zh) 2023-05-09

Similar Documents

Publication Publication Date Title
TWI687832B (zh) 生物識別系統及用於生物識別之電腦實施方法
US11024256B2 (en) Adaptive image display based on colorspace conversions
US11551047B2 (en) Programmable logic array and colorspace conversions
US11200751B2 (en) Augmented reality system with color-based fiducial marker
US10719692B2 (en) Vein matching for difficult biometric authentication cases
US8160354B2 (en) Multi-stage image pattern recognizer
CN110069970A (zh) 活性测试方法和设备
JP7021871B2 (ja) 複数の生体認証器を用いたユーザ認証方法及びその装置
US8229209B2 (en) Neural network based pattern recognizer
GB2579583A (en) Anti-spoofing
JP2018501588A (ja) 四次元コード及び、四次元コードに基づく画像識別システム及び画像識別方法、四次元コード検索システム及び四次元コード検索方法
US8290250B2 (en) Method and apparatus for creating a pattern recognizer
Xu et al. A survey of CAPTCHA technologies to distinguish between human and computer
EP4088205B1 (en) System and method for disentangling features specific to users, actions and devices recorded in motion sensor data
WO2023116565A1 (zh) 智能设计网络安全架构图的方法
WO2023077640A1 (zh) 指纹识别装置和识别方法、触控显示装置以及电子设备
Sharma et al. A survey on face presentation attack detection mechanisms: hitherto and future perspectives
JP6493941B1 (ja) 個人認証方法及び個人認証装置
CN110363111A (zh) 基于镜头失真原理的人脸活体检测方法、装置及存储介质
CN216083749U (zh) 指纹识别装置、触控显示装置以及电子设备
CN115936961A (zh) 基于少样本对比学习网络的隐写分析方法、设备及介质
Gomez-Barrero et al. Multi-spectral convolutional neural networks for biometric presentation attack detection
WO2021048777A1 (en) A method for obtaining data from an image of an object of a user that has a biometric characteristic of the user
US20200349335A1 (en) Fingerprint sensing device
Mushtaq et al. Color separation in forensic image processing using interactive differential evolution