WO2022188141A1 - 一种指纹图像处理方法、指纹芯片及电子设备 - Google Patents

一种指纹图像处理方法、指纹芯片及电子设备 Download PDF

Info

Publication number
WO2022188141A1
WO2022188141A1 PCT/CN2021/080425 CN2021080425W WO2022188141A1 WO 2022188141 A1 WO2022188141 A1 WO 2022188141A1 CN 2021080425 W CN2021080425 W CN 2021080425W WO 2022188141 A1 WO2022188141 A1 WO 2022188141A1
Authority
WO
WIPO (PCT)
Prior art keywords
image data
fingerprint image
data
background
original
Prior art date
Application number
PCT/CN2021/080425
Other languages
English (en)
French (fr)
Inventor
李准
龙文勇
Original Assignee
敦泰电子(深圳)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 敦泰电子(深圳)有限公司 filed Critical 敦泰电子(深圳)有限公司
Priority to PCT/CN2021/080425 priority Critical patent/WO2022188141A1/zh
Priority to CN202180001794.1A priority patent/CN113272819A/zh
Priority to TW110133876A priority patent/TWI779825B/zh
Publication of WO2022188141A1 publication Critical patent/WO2022188141A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12Fingerprints or palmprints
    • G06V40/1382Detecting the live character of the finger, i.e. distinguishing from a fake or cadaver finger
    • G06V40/1388Detecting the live character of the finger, i.e. distinguishing from a fake or cadaver finger using image processing
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/20Image preprocessing
    • G06V10/28Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/20Image preprocessing
    • G06V10/30Noise filtering
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12Fingerprints or palmprints
    • G06V40/13Sensors therefor
    • G06V40/1318Sensors therefor using electro-optical elements or layers, e.g. electroluminescent sensing
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12Fingerprints or palmprints
    • G06V40/1365Matching; Classification

Definitions

  • the present application relates to the technical field of fingerprint identification, and in particular, to a fingerprint image processing method, a fingerprint chip and an electronic device.
  • Optical fingerprint recognition can be used to realize functions such as unlocking, payment, authorization authentication, etc., and it is more and more widely used in the field of smart phones and other electronic devices.
  • a tool without fingerprints is often used in advance to press an optical sensor to collect background data, and the background data is pre-stored. After acquiring the fingerprint pressing image obtained by pressing the finger on the optical sensor, the background noise in the fingerprint pressing image is eliminated by relying on the pre-stored background data to obtain the final fingerprint image.
  • the pre-stored background data is often fixed data collected in a specific application scenario, which is difficult to adapt to various application scenarios.
  • the fixed background data does not match the new application scene, and the background noise cannot be eliminated well, which affects the quality of the fingerprint image.
  • Embodiments of the present application provide a fingerprint image processing method, a fingerprint chip and an electronic device, which are used to realize automatic update of background data in an optical fingerprint identification process and improve the adaptability of fingerprint image analysis to application scenarios.
  • a first aspect of the embodiments of the present application provides a fingerprint image processing method, which may include:
  • the background data is updated according to the original fingerprint image data.
  • judging whether the original fingerprint image data and the fingerprint image data satisfy a preset condition may include:
  • the image parameters include image variance, image contrast, image consistency, image local standard deviation, image overall standard deviation, image effective area, and image matching degree. one or more.
  • the updating of the background data according to the original fingerprint image data may include:
  • base ij data ij *ratio+base ij *(1-ratio), where base ij is the element in the ith row and j column in the background data, and data ij is the element of the i-th row and j-column in the fingerprint image data, and ratio is a constant between 0 and 1.
  • performing a preset operation on the background data and the original fingerprint image data to obtain fingerprint image data which may include:
  • the fingerprint image data is obtained by subtracting the pixel values of the elements with the same number of rows and columns in the background data and the original fingerprint image data.
  • performing a preset operation on the background data and the original fingerprint image data to obtain fingerprint image data which may include:
  • the fingerprint image data is obtained by dividing the pixel values of the elements with the same number of rows and columns in the background data and the original fingerprint image data.
  • the fingerprint image processing method of the present application may further include:
  • Preset image operations are performed on the first image data and the second image data to obtain fingerprint image data.
  • the fingerprint image processing method of the present application may further include:
  • the background data is generated according to the combination of at least two original fingerprint image data that satisfy a preset condition.
  • a second aspect of the embodiments of the present application provides a fingerprint chip, which may include:
  • the acquisition module is used to collect the original fingerprint image and obtain the original fingerprint image data
  • a first judgment module for judging whether background data is stored
  • the first computing module if background data is stored, performs a preset operation on the background data and the original fingerprint image data to obtain fingerprint image data;
  • a second judgment module for judging whether the original fingerprint image data and the fingerprint image data satisfy a preset condition, and if the preset condition is met, an update module is triggered;
  • An update module configured to update the background data according to the original fingerprint image data.
  • the second judgment module of this application may include:
  • a first judging unit for judging whether the original fingerprint image data is real finger pressing data
  • the second judging unit is configured to judge whether the image parameters corresponding to the fingerprint image data meet the preset standard, and the image parameters include image variance, image contrast, image consistency, image local standard deviation, overall image standard deviation, image valid One or more of region and image matching degree.
  • the update module of this application may include:
  • the first computing module of this application may include:
  • the first calculation unit performs a subtraction operation on pixel values of elements with the same number of rows and columns in the background data and the original fingerprint image data to obtain fingerprint image data.
  • the first computing module of this application may include:
  • the second calculation unit is configured to perform a division operation on pixel values of elements with the same row and column numbers in the background data and the original fingerprint image data to obtain fingerprint image data.
  • the fingerprint chip of the present application may further include:
  • a filtering module which continuously performs mean filtering on the original fingerprint image data at least twice, and records the first image data obtained by the first mean filtering and the second image data obtained by the last mean filtering;
  • the third computing module is configured to perform a preset image operation on the first image data and the second image data to obtain fingerprint image data.
  • the fingerprint chip of the present application may further include:
  • the generating module is used for generating background data according to the combination of at least two original fingerprint image data that meet the preset conditions.
  • a third aspect of the embodiments of the present application provides an electronic device, the electronic device includes an optical fingerprint sensor and a processor, the optical fingerprint sensor is configured to generate raw image data, and the processor is configured to execute a computer program stored in a memory At the same time, the steps in the first aspect and any one of the possible implementation manners of the first aspect are implemented.
  • the fingerprint chip in the present application can determine whether the original fingerprint image data and the fingerprint image data meet the preset conditions, and if the preset conditions are met, the background data is updated according to the original fingerprint image data. .
  • the present application can realize automatic update of background data in the process of optical fingerprint identification, and improve the adaptability of fingerprint image analysis to application scenarios.
  • FIG. 1 is a schematic diagram of an embodiment of a fingerprint image processing method in the present application
  • FIG. 2 is a schematic diagram of another embodiment of a fingerprint image processing method in the present application.
  • FIG. 3 is a schematic diagram of a specific application embodiment of a fingerprint image processing method in the present application.
  • An embodiment of a fingerprint image processing method of the present application may include:
  • the optical fingerprint sensor can generate raw fingerprint image data based on the raw fingerprint image collected.
  • the original fingerprint image data is stored in the form of an image matrix, such as an M*N matrix with M rows and N columns, the value of each element in the matrix is a pixel value, and the range of pixel values is determined according to the number of data bits, such as 10-bit data is a value from 0 to 1024; 12-bit data is a value between 0 and 4096.
  • other data representing fingerprint information may also be used, which is not limited here.
  • the original fingerprint image data obtained at this stage has background noise, which needs to be further eliminated.
  • the fingerprint chip After obtaining the original fingerprint image data, the fingerprint chip needs to determine whether the background data is stored. If the background data is stored, the next step can be directly performed to calculate the fingerprint image data based on the existing background data. If no background data is stored, other procedures may be performed.
  • the background data in this application does not need to be pre-stored, but is automatically generated and continuously updated according to the original fingerprint image data obtained during use.
  • a preset algorithm can be used to perform operations on the acquired data to eliminate background noise to obtain the processed fingerprint image data.
  • the fingerprint chip performs a preset image operation on the background data and the original fingerprint image data to obtain the fingerprint image data may include: the background data and the original fingerprint image data have the same number of rows and columns; The pixel values of the elements are subtracted to obtain fingerprint image data.
  • the fingerprint chip performs a preset operation on the background data and the original fingerprint image data to obtain the fingerprint image data, which may include: elements with the same number of rows and columns in the background data and the original fingerprint image data;
  • the pixel value of the fingerprint image data is obtained by dividing the pixel value.
  • the fingerprint chip can determine whether the original fingerprint image data and the processed fingerprint image data meet the preset conditions, and if the preset conditions are met, determine the original fingerprint image. The data meets the background update conditions, and the next step is performed to update the background data according to the original fingerprint image data. If the preset conditions are not met, the background data will not be updated.
  • judging whether the original fingerprint image data and the fingerprint image data meet the preset conditions may specifically include: judging whether the original fingerprint image data is real finger pressing data; judging whether the fingerprint image data is real finger pressing data; Whether the image parameters corresponding to the data meet the preset standards, the image parameters may include one or more of image variance, image contrast, image consistency, image local standard deviation, image overall standard deviation, image effective area, and image matching degree.
  • the purpose of judging whether the original fingerprint image data is real finger pressing data is to determine whether the data obtained by the optical fingerprint sensor is obtained by real finger pressing, so as to prevent the use of fake finger attacks from destroying the fingerprint recognition function.
  • the image quality quality parameters can be combined and mapped based on image variance, image contrast and image consistency. If quality ⁇ thr_quality (the preset quality parameter threshold), the image parameters corresponding to the fingerprint image data do not meet the preset standards. Background data updates are not supported.
  • the effective area of the image can be calculated based on information such as image variance and image texture information. If area ⁇ thr_area (the preset area parameter threshold), the image parameters corresponding to the fingerprint image data do not meet the preset standards, and the background data update is not supported.
  • the image matching degree of the latest fingerprint image can be calculated. If the image matching degree is lower than the threshold value , the image parameters corresponding to the corresponding fingerprint image data do not meet the preset standards, and the background data update is not supported.
  • any of the above application scenarios that do not support background data update are not identified based on the image parameters corresponding to the fingerprint image data, it can be considered that background data update is supported. It can also be set that, when a specific scene in the above application scene that does not support background data update is identified, it can be considered that background data update is not supported. In practical applications, the preset conditions may be reasonably set based on the usage scenario, which is not limited here.
  • the fingerprint chip can update the background data according to the original fingerprint image data.
  • base ij is the element in the i-th row and j column in the background data
  • data ij is the element in the i-th row and j column in the fingerprint image data
  • ratio is a constant between 0 and 1, which can be tested in the program by experimental methods.
  • the fingerprint chip can generate the background data according to the combination of at least two fingerprint image data that meet the preset conditions.
  • base ij data1 ij *ratio+data2 ij *(1-ratio), where base ij is the element in the i-th row and j column in the background data, and data1 ij is the first fingerprint image data in the The element in the i-th row and the j-column, data2 ij is the element in the i-th row and the j column in the second fingerprint image data, and the ratio is a constant between 0 and 1.
  • the fingerprint chip after obtaining the fingerprint image data corresponding to the original fingerprint image data, the fingerprint chip can determine whether the original fingerprint image data and the fingerprint image data satisfy the preset conditions, and if the preset conditions are met, the background data is updated according to the fingerprint image data.
  • the present application can realize automatic update of background data in the process of optical fingerprint identification, and improve the adaptability of fingerprint image analysis to application scenarios.
  • a fingerprint image processing method may include:
  • the optical fingerprint sensor may generate an original fingerprint image based on the received photoelectric signal, and obtain original fingerprint image data based on the original fingerprint image.
  • the original fingerprint image data is an image matrix, such as an M*N matrix, where M is the number of image rows, and N is the number of image columns.
  • the value of each element in the matrix is a pixel value, and the expression of the pixel value is related to the number of data bits. 10-bit data is a value from 0 to 1024; 12-bit data is a value between 0 and 4096.
  • the fingerprint chip After acquiring the original fingerprint image data, the fingerprint chip needs to determine whether the background data is stored. If the background data is stored, the next step S203 can be directly executed, and the fingerprint image data is calculated based on the existing background data (refer to FIG. 1 ). example). If no background data is stored, step S204 may be executed.
  • the fingerprint chip in the present application can continuously perform mean filtering on the original fingerprint image data at least twice, and record the first image data obtained by the first mean filtering and the last mean filtering. obtained second image data.
  • the specific process is as follows: performing mean filtering on the original fingerprint image data for the first time to obtain filtered data data1 (first image data), and then performing mean filtering on data1, The filtered data data2 (second image data) is obtained.
  • the number of continuous mean filtering can be set as required, which is not limited here.
  • a preset image algorithm may be used to perform operations on the acquired data to eliminate background noise to obtain fingerprint image data.
  • the fingerprint chip performs a preset image operation on the first image data and the second image data to obtain the fingerprint image data, which may include: performing a preset image operation on the first image data and the second image data.
  • the pixel values of the elements with the same number of rows and columns are subtracted to obtain fingerprint image data.
  • the fingerprint chip in the present application performs a preset image operation on the first image data and the second image data to obtain the fingerprint image data, which may include: performing a preset image operation on the first image data and the second image data.
  • the pixel values of the elements with the same number of rows and columns in the data are divided to obtain fingerprint image data.
  • steps S203 and S206 in this embodiment are similar to the contents described in steps S103 to S104 in the above-mentioned embodiment shown in FIG. 1 , and are not repeated here.
  • the present embodiment does not need to collect and store background data, which saves the cost of fingerprint image analysis, and can dynamically update the background data in the fingerprint image analysis process, which improves the adaptability to application scenarios.
  • a specific application embodiment of a fingerprint image processing method in the present application may include:
  • the background data base is not pre-stored when the electronic device leaves the factory. For this purpose, it is necessary to collect valid data locally and record the number of valid data effcNums. When the effcNums reaches the preset threshold thr, the background data can be generated locally according to the valid data. base.
  • S2 collect the original fingerprint image, and obtain the original fingerprint image data
  • the optical fingerprint sensor may generate raw fingerprint image data based on the collected photoelectric signals.
  • the original fingerprint image data is self-analyzed.
  • the self-analysis process is: performing at least two consecutive mean filtering on the original fingerprint image data data, recording the first image data obtained by the first mean filtering and the second image data obtained by the last mean filtering;
  • the fingerprint image data is obtained by subtracting or dividing the pixel values of the elements with the same number of rows and columns in the second image data.
  • the background data base can be generated locally according to the valid data, and then the parsed fingerprint image data can be obtained based on the base data and the fingerprint image data.
  • the preset conditions may be reasonably set based on the usage scenario, which is not limited here.
  • the image quality quality parameters can be combined and mapped. If quality ⁇ thr_quality (the preset quality parameter threshold), the image parameters corresponding to the fingerprint image data do not meet the preset standards and do not Support background data update.
  • the effective area of the image can be calculated based on information such as image variance and image texture information. If area ⁇ thr_area (the preset area parameter threshold), the image parameters corresponding to the fingerprint image data do not meet the preset standards, and the background data update is not supported.
  • the image matching degree of the latest fingerprint image can be calculated. If the image matching degree is lower than the threshold value , the image parameters corresponding to the corresponding fingerprint image data do not meet the preset standards, and the background data update is not supported.
  • the embodiment of the present application also provides a fingerprint chip, which may include:
  • the acquisition module is used to collect the original fingerprint image and obtain the original fingerprint image data
  • a first judgment module for judging whether background data is stored
  • the first computing module if background data is stored, performs a preset operation on the background data and the original fingerprint image data to obtain fingerprint image data;
  • a second judgment module for judging whether the original fingerprint image data and the fingerprint image data satisfy a preset condition, and if the preset condition is met, an update module is triggered;
  • An update module configured to update the background data according to the original fingerprint image data.
  • the second judgment module of this application may include:
  • a first judging unit for judging whether the original fingerprint image data is real finger pressing data
  • the second judging unit is configured to judge whether the image parameters corresponding to the fingerprint image data meet the preset standard, and the image parameters include image variance, image contrast, image consistency, image local standard deviation, overall image standard deviation, image valid One or more of region and image matching degree.
  • the update module of this application may include:
  • the first computing module of this application may include:
  • the first calculation unit performs a subtraction operation on pixel values of elements with the same number of rows and columns in the background data and the original fingerprint image data to obtain fingerprint image data.
  • the first computing module of this application may include:
  • the second calculation unit is used for dividing the pixel values of the elements with the same number of rows and columns in the background data and the original fingerprint image data to obtain fingerprint image data.
  • the fingerprint chip of the present application may further include:
  • a filtering module which continuously performs mean filtering on the original fingerprint image data at least twice, and records the first image data obtained by the first mean filtering and the second image data obtained by the last mean filtering;
  • the third computing module is configured to perform a preset operation on the first image data and the second image data to obtain fingerprint image data.
  • the fingerprint chip in this application may also include:
  • the generating module is used for generating background data according to the combination of at least two original fingerprint image data that meet the preset conditions.
  • the present application provides an electronic device including the above fingerprint chip.
  • the electronic device 1 can be used to implement the steps in the above-mentioned embodiment of the fingerprint image processing method shown in FIG. 1 or FIG. 2 , for example, steps 101 to 105 shown in FIG. 1 .
  • the processor executes the computer program, the functions of each module or unit in the foregoing device embodiments are implemented.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Input (AREA)
  • Collating Specific Patterns (AREA)

Abstract

一种指纹图像处理方法、指纹芯片及电子设备,用于实现光学指纹识别过程中的背景数据的自动更新,提高指纹图像解析对应用场景的适应性。方法可包括:采集原始指纹图像,并获取原始指纹图像数据;判断是否存储有背景数据;若存储有背景数据,则对所述背景数据和所述原始指纹图像数据进行预设运算得到指纹图像数据;判断所述原始指纹图像数据以及所述指纹图像数据是否满足预设条件,若满足预设条件,根据所述原始指纹图像数据更新背景数据。

Description

一种指纹图像处理方法、指纹芯片及电子设备 技术领域
本申请涉及指纹识别技术领域,尤其涉及一种指纹图像处理方法、指纹芯片及电子设备。
背景技术
光学指纹识别可以用来实现解锁、支付、权限认证等功能,在智能手机以及其他电子设备领域应用越来越广泛。
在实现光学指纹识别功能过程中,往往需要消除指纹按压图像中的背景数据。相关技术中,往往会预先采用没有指纹的制具按压光学传感器采集到背景数据,并预存该背景数据。在获取手指按压光学传感器得到的指纹按压图像之后,依赖预存的背景数据消除指纹按压图像中的背景噪声,得到最终的指纹图像。
相关技术中,预存的背景数据往往是在特定的应用场景下采集的固定数据,难以适应多种应用场景。当应用场景发生变化时,固定的背景数据与新的应用场景不匹配,无法进行较好的背景噪声消除,影响指纹图像的质量。
发明内容
本申请实施例提供了一种指纹图像处理方法、指纹芯片及电子设备,用于实现光学指纹识别过程中的背景数据的自动更新,提高指纹图像解析对应用场景的适应性。
本申请实施例的第一方面提供一种指纹图像处理方法,可包括:
采集原始指纹图像,并获取原始指纹图像数据;
判断是否存储有背景数据;
若存储有背景数据,则对所述背景数据和所述原始指纹图像数据进行预设运算得到指纹图像数据;
判断所述原始指纹图像数据以及所述指纹图像数据是否满足预设条件,若满足预设条件,根据所述原始指纹图像数据更新背景数据。
可选的,作为一种可能的实施方式,本申请中,判断所述原始指纹图像数据以及所述指纹图像数据是否满足预设条件,可包括:
判断所述原始指纹图像数据是否为真实手指按压数据;
判断所述指纹图像数据对应的图像参数是否符合预设标准,所述图像参数包括图像方差、图像对比度、图像一致性、图像局部标准差、图像整体标准差、图像有效区域、图像匹配度中的一种或多种。
可选的,作为一种可能的实施方式,本申请中,所述根据所述原始指纹图像数据更新背景数据,可包括:
若已存在背景数据base,则根据公式base ij=data ij*ratio+base ij*(1-ratio)更新背景数据中各个元素,其中base ij为背景数据中第i行j列的元素,data ij为指纹图像数据中第i行j列的元素,ratio为0至1之间的常数。
可选的,作为一种可能的实施方式,本申请中,对所述背景数据和所述原始指纹图像数据进行预设运算得到指纹图像数据,可包括:
对所述背景数据和所述原始指纹图像数据中行列数相同元素的像素值进行减法运算得到指纹图像数据。
可选的,作为一种可能的实施方式,本申请中,对所述背景数据和所述原始指纹图像数据进行预设运算得到指纹图像数据,可包括:
对所述背景数据和所述原始指纹图像数据中行列数相同元素的像素值进行除法运算得到指纹图像数据。
可选的,作为一种可能的实施方式,若没有存储背景数据,本申请的指纹图像处理方法,还可以包括:
对所述原始指纹图像数据连续进行至少两次均值滤波,记录第一次均值滤波得到的第一图像数据和最后一次均值滤波得到的第二图像数据;
对所述第一图像数据和所述第二图像数据进行预设图像运算得到指纹图像数据。
可选的,作为一种可能的实施方式,若没有存储背景数据,本申请的指纹图像处理方法,还可以包括:
根据至少两个满足预设条件的原始指纹图像数据组合生成背景数据。
本申请实施例第二方面提供了一种指纹芯片,可包括:
采集模块,用于采集原始指纹图像,并获取原始指纹图像数据;
第一判断模块,用于判断是否存储有背景数据;
第一计算模块,若存储有背景数据,则对所述背景数据和所述原始指纹图像数据进行预设运算得到指纹图像数据;
第二判断模块,判断所述原始指纹图像数据以及所述指纹图像数据是否满足预设条件,若满足预设条件,则触发更新模块;
更新模块,用于根据所述原始指纹图像数据更新背景数据。
可选的,作为一种可能的实施方式,本申请的第二判断模块,可以包括:
第一判断单元,用于判断所述原始指纹图像数据是否为真实手指按压数据;
第二判断单元,用于判断所述指纹图像数据对应的图像参数是否符合预设标准,所述图像参数包括图像方差、图像对比度、图像一致性、图像局部标准差、图像整体标准差、图像有效区域、图像匹配度中的一种或多种。
可选的,作为一种可能的实施方式,本申请的更新模块可以包括:
更新单元,若已存在背景数据base,则根据公式base ij=data ij*ratio+base ij*(1-ratio)更新背景数据中各个元素,其中base ij为背景数据中第i行j列的元素,data ij为原始指纹图像数据中第i行j列的元素,ratio为0至1之间的常数。
可选的,作为一种可能的实施方式,本申请的第一计算模块,可以包括:
第一计算单元,对所述背景数据和所述原始指纹图像数据中行列数相同元素的像素值进行减法运算得到指纹图像数据。
可选的,作为一种可能的实施方式,本申请的第一计算模块,可以包括:
第二计算单元,用于对所述背景数据和所述原始指纹图像数据中行列数相同元素的像素值进行除法运算得到指纹图像数据。
可选的,作为一种可能的实施方式,本申请的指纹芯片,还可以包括:
滤波模块,对所述原始指纹图像数据连续进行至少两次均值滤波,记录第一次均值滤波得到的第一图像数据和最后一次均值滤波得到的第二图像数据;
第三计算模块,用于对所述第一图像数据和所述第二图像数据进行预设图像运算得到指纹图像数据。
可选的,作为一种可能的实施方式,本申请的指纹芯片,还可以包括:
生成模块,用于根据至少两个满足预设条件的原始指纹图像数据组合生成背景数据。
本申请实施例第三方面提供了一种电子设备,所述电子设备包括光学指纹传感器及处理器,所述光学指纹传感器用于生成原始图像数据,所述处理器用于执行存储器中存储的计算机程序时实现如第一方面及第一方面中任意一种可能的实施方式中的步骤。
本申请中的指纹芯片在获取原始指纹图像数据对应的指纹图像数据之后,可以判断原始指纹图像数据以及指纹图像数据是否满足预设条件,若满足预设条件,则根据原始指纹图像数据更新背景数据。相对于相关技术,本申请可以实现光学指纹识别过程中的背景数据的自动更新,提高了指纹图像解析对应用场景的适应性。
附图说明
图1为本申请中一种指纹图像处理方法的一个实施例示意图;
图2为本申请中一种指纹图像处理方法的另一个实施例示意图;
图3为本申请中一种指纹图像处理方法的一个具体应用实施例示意图。
具体实施方式
下面将结合本申请的附图,对本申请的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本申请一部分实施例,而不是全部的实施例。基于本申请中的实施例,本领域技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本申请保护的范围。
本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”、“第三”、“第四”等(如果存在)是用于区别类似的对象,而不必用于描述特定的顺序或先后次序。应该理解这样使用的术语在适当情况下可以互换,以便这里描述的实施例能够以除了在这里图示或描述的内容以外的顺序实施。此外,术语“包括”和“具有”以及他们的任何变形,意图在于覆盖不排他的包含,例如,包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元,而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
为了便于理解,下面对本申请的具体流程进行描述,请参阅图1,本申请一种指纹图像处理方法的一个实施例可包括:
S101、采集原始指纹图像,并获取原始指纹图像数据;
在手指按压光学指纹传感器之后,光学指纹传感器可以基于采集到原始指纹图像,并生成原始指纹图像数据。
本实施例中原始指纹图像数据为图像矩阵的形式进行存储,例如M行N列的M*N矩阵,矩阵中的每一个元素的值为像素值,像素值的范围根据数据位数确定,如10位数据,就是0到1024的数值;12位数据,就是0到4096之间的数值。在其它实施例中,也可采用其它表征指纹信息的数据,此处不做限定。其中,该阶段获取到的原始指纹图像数据,存在背景噪声,需要进一步消除背景噪声。
S102、判断是否存储有背景数据;
在获取到获取原始指纹图像数据之后,指纹芯片需要判断是否存储有背景数据,若存储有背景数据,则可以直接执行下一步,基于已有的背景数据计算指纹图像数据。若没有存储背景数据,则可以执行其它过程。
其中,需要说明的是,本申请中的背景数据无需预存,而是根据使用过程中获取到的原始指纹图像数据自动生成并不断更新。
S103、对背景数据和原始指纹图像数据进行预设运算得到指纹图像数据;
在获取到背景数据和原始指纹图像数据之后,可以采用预设算法对获取到的数据进行运算,以消除背景噪声得到处理后指纹图像数据。
可选的,作为一种可能的实施方式,本申请中,指纹芯片对背景数据和原始指纹图像数据进行预设图像运算得到指纹图像数据可以包括:对背景数据和原始指纹图像数据中行列数相同元素的像素值进行减法运算得到指纹图像数据。示例性的,图像矩阵中的第i行j列的元素img ij=fliter_data1 ij-fliter_data2 ij或img ij=fliter_data2 ij-fliter_data1 ij,其中,fliter_data1 ij为背景数据中第i行j列的元素,fliter_data2 ij为原始指纹图像数据中第i行j列的元素。
可选的,作为一种可能的实施方式,本申请中,指纹芯片对背景数据和原始指纹图像数据进行预设运算得到指纹图像数据可以包括:对背景数据和原始指纹图像数据中行列数相同元素的像素值进行除法运算得到指纹图像数据。示例性的,图像矩阵中的第i行j列的元素img ij=fliter_data1 ij/fliter_data2 ij或img ij =fliter_data2 ij/fliter_data1 ij,其中,fliter_data1 ij为背景数据中第i行j列的元素,fliter_data2 ij为原始指纹图像数据中第i行j列的元素。
S104、判断原始指纹图像数据以及指纹图像数据是否满足预设条件;
为了提高指纹图像处理芯片对应用场景的适应性,需要实时更新背景数据。具体的,在获取到原始指纹图像数据对应的指纹图像数据之后,指纹芯片可以判断原始指纹图像数据以及处理后的指纹图像数据是否满足预设条件,若满足预设条件,则确定该原始指纹图像数据满足背景更新条件,并执行下一步,根据原始指纹图像数据更新背景数据。若不满足预设条件,则不进行背景数据的更新。
可选的,作为一种可能的实施方式,本申请中,判断原始指纹图像数据以及指纹图像数据是否满足预设条件,具体可以包括:判断原始指纹图像数据是否为真实手指按压数据;判断指纹图像数据对应的图像参数是否符合预设标准,图像参数可以包括图像方差、图像对比度、图像一致性、图像局部标准差、图像整体标准差、图像有效区域、图像匹配度中的一种或多种。
其中,判断原始指纹图像数据是否为真实手指按压数据,是为了判断光学指纹传感器获取到的数据是否为真实的手指按压得到,以防止使用假手指攻击破坏指纹识别功能。
为了便于理解,示例性的,对指纹图像数据对应的图像参数不符合预设标准,不支持背景数据更新的常见应用场景进行说明。实际应用中,基于图像方差、图像对比度和图像一致性可以组合映射得到图像质量quality参数,若quality<thr_quality(预设的quality参数阈值),则指纹图像数据对应的图像参数不符合预设标准,不支持背景数据更新。基于图像方差、图像纹理信息等信息可以计算图像有效区域area,若area<thr_area(预设的area参数阈值)则指纹图像数据对应的图像参数不符合预设标准,不支持背景数据更新。基于图像局部标准差和图像整体标准差可以判断指纹图像是否存在漏光区域,若存在漏光区域,则指纹图像数据对应的图像参数不符合预设标准,不支持背景数据更新。基于当前获取到的最新的指纹图像数据对应的图像与已存的指纹图像的旋转角度、水平平移量、竖直平移量,可以计算最新的指纹图像的图像匹配度,若图像匹配度低于阈值,则对应的指纹图像数据对应的图像参数不符合预设标 准,不支持背景数据更新。若基于指纹图像数据对应的图像参数没有识别出任何一种上述不支持背景数据更新的应用场景,则可以认为支持背景数据更新。也可以设置为,当识别出上述不支持背景数据更新的应用场景中的特定场景,则可以认为不支持背景数据更新。实际应用中,可以基于使用场景对预设条件进行合理设置,此处不做限定。
S105、根据原始指纹图像数据更新背景数据。
若指纹图像数据满足背景更新条件,则指纹芯片可以根据原始指纹图像数据更新背景数据。
可选的,作为一种可能的实施方式,若已存在背景数据base,更新背景数据的具体过程可以包括:根据公式base ij=data ij*ratio+base ij*(1-ratio)更新背景数据中各个元素,其中base ij为背景数据中第i行j列的元素,data ij为指纹图像数据中第i行j列的元素,ratio为0至1之间的常数,可通过实验方法,在程序中合理设定ratio值。若没有存储背景数据,指纹芯片可以根据至少两个满足预设条件的指纹图像数据组合生成背景数据。根据公式base ij=data1 ij*ratio+data2 ij*(1-ratio)更新背景数据中各个元素,其中base ij为背景数据中第i行j列的元素,data1 ij为第一个指纹图像数据中第i行j列的元素,data2 ij为第二个指纹图像数据中第i行j列的元素,ratio为0至1之间的常数。
本申请中,指纹芯片在获取原始指纹图像数据对应的指纹图像数据之后,可以判断原始指纹图像数据以及指纹图像数据是否满足预设条件,若满足预设条件,则根据指纹图像数据更新背景数据。相对于相关技术,本申请可以实现光学指纹识别过程中的背景数据的自动更新,提高了指纹图像解析对应用场景的适应性。
在上述实施例的基础上,为了进一步提高指纹图像解析对应用场景的适应性,本申请提出了无需在电子设备出厂时预存背景数据的技术方案。请参阅图2,本申请中,一种指纹图像处理方法的另一个实施例可包括:
S201、采集原始指纹图像,并获取原始指纹图像数据;
在手指按压光学指纹传感器之后,光学指纹传感器可以基于接收到的光电信号生成原始指纹图像,并基于原始指纹图像获取原始指纹图像数据。
本实施例中,原始指纹图像数据为图像矩阵,例如M*N矩阵,M为图像行数,N为图像列数。矩阵中的每一个元素的值为像素值,像素值的表现形式和数据位数有关系,10位数据,就是0到1024的数值;12位数据,就是0到4096之间的数值。
其中,该阶段获取到的指纹按压图像中存在背景噪声,需要进一步消除背景噪声。在其它实施例中,也可采用其它表征指纹信息的数据,此处不做限定。
S202、判断是否存储有背景数据;
在获取到原始指纹图像数据之后,指纹芯片需要判断是否存储有背景数据,若存储有背景数据,则可以直接执行下一步S203,基于已有的背景数据计算指纹图像数据(参照图1所示的实施例)。若没有存储背景数据,则可以执行步骤S204。
S203、对背景数据和原始指纹图像数据进行预设运算得到指纹图像数据;
S204、对原始指纹图像数据连续进行至少两次均值滤波,记录第一次均值滤波得到的第一图像数据和最后一次均值滤波得到的第二图像数据;
未侦测到背景数据时,为了消除背景噪声,本申请中的指纹芯片可以对原始指纹图像数据连续进行至少两次均值滤波,记录第一次均值滤波得到的第一图像数据和最后一次均值滤波得到的第二图像数据。
示例性的,以连续进行两次均值滤波为例,具体过程为:对原始指纹图像数据进行第一次均值滤波,得到滤波后的数据data1(第一图像数据),然后对data1进行均值滤波,得到滤波后的数据data2(第二图像数据)。
可以理解的是,连续进行均值滤波的次数越多,得到图像中噪声及纹理等细节信息越少。实际应用中,可以根据需求设置连续均值滤波的次数,此处不做限定。
S205、对第一图像数据和第二图像数据进行预设运算得到指纹图像数据;
在获取到第一图像数据和第二图像数据之后,可以采用预设图像算法对获取到的数据进行运算,以消除背景噪声得到指纹图像数据。
可选的,作为一种可能的实施方式,本申请,指纹芯片对第一图像数据和第二图像数据进行预设图像运算得到指纹图像数据,可以包括:对第一图像数据和第二图像数据中行列数相同元素的像素值进行减法运算得到指纹图像数 据。
可选的,作为一种可能的实施方式,本申请中的指纹芯片对第一图像数据和第二图像数据进行预设图像运算得到指纹图像数据,可以包括:对第一图像数据和第二图像数据中行列数相同元素的像素值进行除法运算得到指纹图像数据。
S206、判断原始指纹图像数据以及预设运算得到的指纹图像数据是否满足预设条件;
本实施例中步骤S203、S206中描述的内容与上述图1所示的实施例中步骤S103至S104中描述的内容类似,此处不做赘述。
S207、采用满足预设条件的指纹图像数据更新背景数据。
可选的,在步骤S206之后,若没有存储背景数据,指纹芯片可以根据至少两个满足预设条件的指纹图像数据组合生成背景数据。根据公式base ij=data1 ij*ratio+data2 ij*(1-ratio)更新背景数据中各个元素,其中base ij为背景数据中第i行j列的元素,data1 ij为第一个指纹图像数据中第i行j列的元素,data2 ij为第二个指纹图像数据中第i行j列的元素,ratio为0至1之间的常数。
相对于相关技术,本实施例中无需采集和存储背景数据,节约了指纹图像解析成本,而且可以动态更新指纹图像解析过程中的背景数据,提高了对应用场景的适应性。
为了理解,下面将结合具体应用实施例对本申请中的指纹图像处理方法进行描述。请参阅图3,本申请中的一种指纹图像处理方法的一个具体应用实施例可包括:
S1:将有效数据数量effcNums置0;
本实施例中,在电子设备出厂时没有预存背景数据base,为此需要在本地采集有效数据,并记录有效数据数量effcNums,当effcNums达到预设阈值thr之后,可以根据有效数据在本地生成背景数据base。
S2:采集原始指纹图像,并获取原始指纹图像数据;
在手指按压光学指纹传感器之后,光学指纹传感器可以基于采集到光电信号生成原始指纹图像数据。
S3:判断effcNums是否大于阈值thr;
若有效数据数量effcNums<thr,则对原始指纹图像数据进行自解析。其中自解析过程为:对原始指纹图像数据data连续进行至少两次均值滤波,记录第一次均值滤波得到的第一图像数据和最后一次均值滤波得到的第二图像数据;对第一图像数据和第二图像数据中行列数相同元素的像素值进行减法或除法运算得到指纹图像数据。
若effcNums≥thr,执行S4。
S4:采用背景数据对原始指纹图像数据进行解析,得到解析后的指纹图像数据;
若effcNums≥thr,有效数据数量effcNums比较后大于阈值thr,可以根据有效数据在本地生成背景数据base,然后基于base数据和指纹图像数据得到解析后的指纹图像数据。
S5:根据原始指纹图像数据及解析后的指纹图像数据计算代表图像品质的结果参数;
实际应用中,可以基于使用场景对预设条件进行合理设置,此处不做限定。基于指纹图像的图像方差、图像对比度和图像一致性可以组合映射得到图像质量quality参数,若quality<thr_quality(预设的quality参数阈值),则指纹图像数据对应的图像参数不符合预设标准,不支持背景数据更新。基于图像方差、图像纹理信息等信息可以计算图像有效区域area,若area<thr_area(预设的area参数阈值)则指纹图像数据对应的图像参数不符合预设标准,不支持背景数据更新。基于图像局部标准差和图像整体标准差可以判断指纹图像是否存在漏光区域,若存在漏光区域,则指纹图像数据对应的图像参数不符合预设标准,不支持背景数据更新。基于当前获取到的最新的指纹图像数据对应的图像与已存的指纹图像的旋转角度、水平平移量、竖直平移量,可以计算最新的指纹图像的图像匹配度,若图像匹配度低于阈值,则对应的指纹图像数据对应的图像参数不符合预设标准,不支持背景数据更新。
S6:判断是否对背景数据进行更新;
若不存在上述S5中所示的不支持背景数据更新的场景,则执行base数据 更新,执行S7;
S7:对背景数据进行更新。
若已存在背景数据base,更新背景数据的具体过程可以包括:根据公式base ij=data ij*ratio+base ij*(1-ratio)更新背景数据中各个元素,其中base ij为背景数据中第i行j列的元素,data ij为指纹图像数据中第i行j列的元素,ratio为0至1之间的常数。
本申请实施例还提供了一种指纹芯片,可包括:
采集模块,用于采集原始指纹图像,并获取原始指纹图像数据;
第一判断模块,用于判断是否存储有背景数据;
第一计算模块,若存储有背景数据,则对所述背景数据和所述原始指纹图像数据进行预设运算得到指纹图像数据;
第二判断模块,判断所述原始指纹图像数据以及所述指纹图像数据是否满足预设条件,若满足预设条件,则触发更新模块;
更新模块,用于根据所述原始指纹图像数据更新背景数据。
可选的,作为一种可能的实施方式,本申请的第二判断模块,可以包括:
第一判断单元,用于判断所述原始指纹图像数据是否为真实手指按压数据;
第二判断单元,用于判断所述指纹图像数据对应的图像参数是否符合预设标准,所述图像参数包括图像方差、图像对比度、图像一致性、图像局部标准差、图像整体标准差、图像有效区域、图像匹配度中的一种或多种。
可选的,作为一种可能的实施方式,本申请的更新模块可以包括:
更新单元,若已存在背景数据base,则根据公式base ij=data ij*ratio+base ij*(1-ratio)更新背景数据中各个元素,其中base ij为背景数据中第i行j列的元素,data ij为原始指纹图像数据中第i行j列的元素,ratio为0至1之间的常数。
可选的,作为一种可能的实施方式,本申请的第一计算模块,可以包括:
第一计算单元,对所述背景数据和所述原始指纹图像数据中行列数相同元素的像素值进行减法运算得到指纹图像数据。
可选的,作为一种可能的实施方式,本申请的第一计算模块,可以包括:
第二计算单元,用于对所述背景数据和所述原始指纹图像数据中行列数相 同元素的像素值进行除法运算得到指纹图像数据。
可选的,作为一种可能的实施方式,本申请的指纹芯片,还可以包括:
滤波模块,对所述原始指纹图像数据连续进行至少两次均值滤波,记录第一次均值滤波得到的第一图像数据和最后一次均值滤波得到的第二图像数据;
第三计算模块,用于对所述第一图像数据和所述第二图像数据进行预设运算得到指纹图像数据。
可选的,作为一种可能的实施方式,本申请中的指纹芯片,还可以包括:
生成模块,用于根据至少两个满足预设条件的原始指纹图像数据组合生成背景数据。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的指纹芯片,装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
本申请提供了包含上述指纹芯片的电子设备。该电子设备1可以用于实现上述图1或图2所示的指纹图像处理方法实施例中的步骤,例如图1所示的步骤101至105。或者,处理器执行计算机程序时实现上述各装置实施例中各模块或单元的功能。
以上所述,以上实施例仅用以说明本申请的技术方案,而非对其限制;尽管参照前述实施例对本申请进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。

Claims (10)

  1. 一种指纹图像处理方法,其特征在于,包括:
    采集原始指纹图像,并获取原始指纹图像数据;
    判断是否存储有背景数据;
    若存储有背景数据,则对所述背景数据和所述原始指纹图像数据进行预设运算得到指纹图像数据;
    判断所述原始指纹图像数据以及所述指纹图像数据是否满足预设条件,若满足预设条件,根据所述原始指纹图像数据更新背景数据。
  2. 根据权利要求1所述的方法,其特征在于,判断所述原始指纹图像数据以及所述指纹图像数据是否满足预设条件,包括:
    判断所述原始指纹图像数据是否为真实手指按压数据;
    判断所述指纹图像数据对应的图像参数是否符合预设标准,所述图像参数包括图像方差、图像对比度、图像一致性、图像局部标准差、图像整体标准差、图像有效区域、图像匹配度中的一种或多种。
  3. 根据权利要求2所述的方法,其特征在于,所述根据所述原始指纹图像数据更新背景数据,包括:
    若已存在背景数据base,则根据公式base ij=data ij*ratio+base ij*(1-ratio)更新背景数据中各个元素,其中base ij为背景数据中第i行j列的元素,data ij为原始指纹图像数据中第i行j列的元素,ratio为0至1之间的常数。
  4. 根据权利要求3所述的方法,其特征在于,对所述背景数据和所述原始指纹图像数据进行预设运算得到指纹图像数据,包括:
    对所述背景数据和所述原始指纹图像数据中行列数相同元素的像素值进行减法运算得到指纹图像数据。
  5. 根据权利要求3所述的方法,其特征在于,对所述背景数据和所述原始指纹图像数据进行预设运算得到指纹图像数据,包括:
    对所述背景数据和所述原始指纹图像数据中行列数相同元素的像素值进行除法运算得到指纹图像数据。
  6. 根据权利要求1至5中任一项所述的方法,其特征在于,若没有存储背景数据,所述方法还包括:
    对所述原始指纹图像数据连续进行至少两次均值滤波,记录第一次均值滤波得到的第一图像数据和最后一次均值滤波得到的第二图像数据;
    对所述第一图像数据和所述第二图像数据进行预设图像运算得到指纹图像数据。
  7. 根据权利要求1至5中任一项所述的方法,其特征在于,若没有存储背景数据,所述方法还包括:
    根据至少两个满足预设条件的原始指纹图像数据组合生成背景数据。
  8. 一种指纹芯片,其特征在于,包括:
    采集模块,用于采集原始指纹图像,并获取原始指纹图像数据;
    第一判断模块,用于判断是否存储有背景数据;
    第一计算模块,若存储有背景数据,则对所述背景数据和所述原始指纹图像数据进行预设运算得到指纹图像数据;
    第二判断模块,判断所述原始指纹图像数据以及预设运算得到的所述指纹图像数据是否满足预设条件,若满足预设条件,则触发更新模块;
    更新模块,用于根据所述原始指纹图像数据更新背景数据。
  9. 根据权利要求8所述的指纹芯片,其特征在于,所述第二判断模块包括:
    第一判断单元,用于判断所述原始指纹图像数据是否为真实手指按压数据;
    第二判断单元,用于判断所述指纹图像数据对应的图像参数是否符合预设标准,所述图像参数包括图像方差、图像对比度、图像一致性、图像局部标准差、图像整体标准差、图像有效区域、图像匹配度中的一种或多种。
  10. 一种电子设备,其特征在于,所述电子设备包括如权利要求8至9中任一项所述的指纹芯片。
PCT/CN2021/080425 2021-03-12 2021-03-12 一种指纹图像处理方法、指纹芯片及电子设备 WO2022188141A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
PCT/CN2021/080425 WO2022188141A1 (zh) 2021-03-12 2021-03-12 一种指纹图像处理方法、指纹芯片及电子设备
CN202180001794.1A CN113272819A (zh) 2021-03-12 2021-03-12 一种指纹图像处理方法、指纹芯片及电子设备
TW110133876A TWI779825B (zh) 2021-03-12 2021-09-10 指紋圖像處理方法、指紋晶片及電子設備

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/080425 WO2022188141A1 (zh) 2021-03-12 2021-03-12 一种指纹图像处理方法、指纹芯片及电子设备

Publications (1)

Publication Number Publication Date
WO2022188141A1 true WO2022188141A1 (zh) 2022-09-15

Family

ID=77236891

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/080425 WO2022188141A1 (zh) 2021-03-12 2021-03-12 一种指纹图像处理方法、指纹芯片及电子设备

Country Status (3)

Country Link
CN (1) CN113272819A (zh)
TW (1) TWI779825B (zh)
WO (1) WO2022188141A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114120376A (zh) * 2021-11-18 2022-03-01 黑龙江大学 一种多模态图像采集装置及系统

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090123040A1 (en) * 2005-06-30 2009-05-14 Nec Corporation Fingerprint image background detection apparatus and detection method
CN111126147A (zh) * 2019-11-22 2020-05-08 北京迈格威科技有限公司 图像处理方法、装置和电子系统
CN111209898A (zh) * 2020-03-12 2020-05-29 敦泰电子(深圳)有限公司 一种光学指纹图像背景的去除方法及装置

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI460666B (zh) * 2008-05-07 2014-11-11 Han Pang Huang 防偽指紋辨識系統
CN106203365B (zh) * 2016-07-14 2019-02-12 浙江赢视科技有限公司 增益调节处理的指纹成像方法
WO2019015623A1 (en) * 2017-07-18 2019-01-24 Shenzhen GOODIX Technology Co., Ltd. ANTI-MYSTIFICATION DETECTION FOR REJECTING PATTERNS OF DIGITAL FINGERPRINTS IN OPTICAL SENSOR MODULE SUB-SCREEN FOR DETECTION OF DIGITAL PRINTS ON SCREEN
CN110147751A (zh) * 2019-05-16 2019-08-20 Oppo广东移动通信有限公司 一种指纹检测的方法及装置
CN110187806B (zh) * 2019-05-22 2023-04-18 Oppo广东移动通信有限公司 指纹模板录入方法及相关装置
CN111079626B (zh) * 2019-12-11 2023-08-01 深圳市迪安杰智能识别科技有限公司 一种活体指纹识别方法、电子设备及计算机可读存储介质

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20090123040A1 (en) * 2005-06-30 2009-05-14 Nec Corporation Fingerprint image background detection apparatus and detection method
CN111126147A (zh) * 2019-11-22 2020-05-08 北京迈格威科技有限公司 图像处理方法、装置和电子系统
CN111209898A (zh) * 2020-03-12 2020-05-29 敦泰电子(深圳)有限公司 一种光学指纹图像背景的去除方法及装置

Also Published As

Publication number Publication date
CN113272819A (zh) 2021-08-17
TW202236155A (zh) 2022-09-16
TWI779825B (zh) 2022-10-01

Similar Documents

Publication Publication Date Title
EP3296922B1 (en) Fingerprint identification method and terminal
CN111144337B (zh) 火灾检测方法、装置及终端设备
CN109377457B (zh) 药丸包衣图像处理方法、装置、计算机设备和存储介质
CN113781406B (zh) 电子元器件的划痕检测方法、装置及计算机设备
CN110602485B (zh) 故障检测方法及相关产品
WO2022188141A1 (zh) 一种指纹图像处理方法、指纹芯片及电子设备
CN113034525A (zh) 图像边缘检测方法、装置及设备
JP5669572B2 (ja) 指紋認証装置
US9704015B2 (en) Fingerprint image processing method and device
CN115496976A (zh) 多源异构数据融合的视觉处理方法、装置、设备及介质
CN111126147B (zh) 图像处理方法、装置和电子系统
CN111080665A (zh) 图像边框识别方法、装置、设备和计算机存储介质
CN114387548A (zh) 视频及活体检测方法、系统、设备、存储介质及程序产品
CN113888438A (zh) 图像处理方法、装置及存储介质
CN112507917A (zh) 一种光学指纹识别方法、装置、电子设备及存储介质
CN109711308B (zh) 指纹组件、电子设备及其指纹信号处理方法
WO2015168893A1 (zh) 一种视频质量检测的方法及装置
CN108805883B (zh) 一种图像分割方法、图像分割装置及电子设备
CN110751623A (zh) 基于联合特征的缺陷检测方法、装置、设备及存储介质
CN109902569B (zh) 指纹图像的转换方法、装置和指纹识别方法
TWI788952B (zh) 指紋圖像處理方法、指紋晶片及電子設備
KR101180854B1 (ko) 회전 지문 영상 획득장치 및 그 방법
CN114463792B (zh) 一种多光谱识别方法、装置、设备及可读存储介质
Vidhya et al. Fingerprint image enhancement using wavelet over Gabor filters
CN114677615A (zh) 一种环境检测方法和检测系统

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: 21929616

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE