WO2020051792A1 - 指纹识别方法、装置、设备及存储介质 - Google Patents

指纹识别方法、装置、设备及存储介质 Download PDF

Info

Publication number
WO2020051792A1
WO2020051792A1 PCT/CN2018/105188 CN2018105188W WO2020051792A1 WO 2020051792 A1 WO2020051792 A1 WO 2020051792A1 CN 2018105188 W CN2018105188 W CN 2018105188W WO 2020051792 A1 WO2020051792 A1 WO 2020051792A1
Authority
WO
WIPO (PCT)
Prior art keywords
area
image
fingerprint
residual
binarized image
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/CN2018/105188
Other languages
English (en)
French (fr)
Inventor
冉耕
王信亮
李洪生
李丹
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Goodix Technology Co Ltd
Original Assignee
Shenzhen Goodix Technology Co Ltd
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 Shenzhen Goodix Technology Co Ltd filed Critical Shenzhen Goodix Technology Co Ltd
Priority to PCT/CN2018/105188 priority Critical patent/WO2020051792A1/zh
Priority to CN201880001576.6A priority patent/CN109313705B/zh
Publication of WO2020051792A1 publication Critical patent/WO2020051792A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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

Definitions

  • the present invention relates to the technical field of fingerprint identification, and in particular, to a fingerprint identification method, device, device, and storage medium.
  • fingerprint recognition technology has developed rapidly in the field of terminal equipment.
  • a large number of terminal equipment have functions such as fingerprint unlocking and fingerprint payment.
  • fingerprint unlocking and fingerprint payment With the increasing frequency of fingerprint unlocking and fingerprint payment, security issues have become increasingly prominent.
  • the invention provides a fingerprint recognition method, device, device and storage medium, thereby improving the security of the fingerprint recognition process.
  • an embodiment of the present invention provides a fingerprint recognition method, including: acquiring N frames of fingerprint images, where N is an integer greater than 1, determining whether there are fixed residual areas in the N frame fingerprint images; and if there are fixed residual areas in the N frame fingerprint images , Determine at least one influence factor of the fingerprint recognition process caused by the fixed residual area on the last frame fingerprint image in the N frame fingerprint images; if the at least one influence factor is greater than the respective corresponding preset threshold value, determine that the last frame fingerprint image cannot be Trigger normal fingerprint recognition results.
  • the last frame fingerprint image is the currently collected fingerprint image.
  • the method provided by the embodiment of the present invention prevents the fingerprint image of the last frame from triggering a normal fingerprint recognition result. This improves the security of the fingerprint recognition process.
  • the last frame of the fingerprint image is a legitimate user fingerprint image, because in this case, the fixed residual area does not exist, or its corresponding impact factor is less than or equal to the corresponding Pre-set thresholds, so normal fingerprint recognition results can still be triggered. Thereby, a normal fingerprint recognition process can be guaranteed.
  • determining whether there are fixed residual areas in the N-frame fingerprint images includes: binarizing the N-frame fingerprint images separately to obtain N groups of first binarized images, and each group of the first binarized images includes the first Black binarized image and first white binarized image; AND operation is performed on the pixel values of each pixel in the first black binarized image of N frames to obtain a second black binarized image, and AND operation is performed on the pixel values of each pixel in a white binarized image to obtain a second white binarized image; the pixel values of each pixel in the second black binarized image and the second white binarized image Perform the OR operation on the pixel values of the corresponding pixels in the image to obtain a second binarized image; if the second binarized image includes at least one connected region that meets a preset condition, determine that there are fixed residues in the N-frame fingerprint image A region, where the fixed residual region is composed of at least one connected region; wherein the preset condition is that the sum of the areas of the at
  • an AND operation is performed on the pixel values of each pixel point in the first black binarized image in N frames to obtain a second black binarized image, and each pixel in the first white binarized image in N frames
  • the method further includes: deleting the connected area with an area smaller than the second preset area in the first black binarized image, and deleting the first white binarized image.
  • a connected area having a middle area smaller than the third preset area That is, using the connected area area filtering method to achieve the effect of filtering noise.
  • an OR operation is performed on the pixel value of each pixel point in the second black binarized image and the pixel value of each pixel point in the second white binarized image to obtain a second binarized image.
  • the method further includes: deleting the connected area having an area smaller than the fourth preset area in the second black binarized image, and deleting the connected area having an area smaller than the third preset area in the second white binarized image. That is, using the connected area area filtering method to achieve the effect of filtering noise.
  • determining at least one influence factor of the fingerprint recognition process caused by the fixed residual area on the fingerprint image of the last frame in the N-frame fingerprint images includes: obtaining geometric transformation vector information corresponding to the fingerprint image of the last frame; the second binary value The image is used as the residual texture template and the residual texture sample; the relative positions of the residual texture template and the residual texture sample are adjusted according to the geometric transformation vector information; the similarity between the residual texture template and the residual texture sample after the relative position adjustment is calculated, and the similarity is calculated.
  • This method can effectively determine the impact factor.
  • the geometric transformation vector information includes at least one of the following: translation, rotation, scaling, symmetry, miscutting, and non-linear deformation information.
  • calculating the similarity between the residual texture template and the residual texture sample after the relative position adjustment includes: determining an overlapping area of the residual texture template and the residual texture sample after the relative position adjustment; determining the first set and the second set And the third set, and determine the proportion of the elements in the first set to the total elements in the first set, the second set, and the third set, and use the proportion as the similarity; where each element in the first set is located in an overlap Region, and the element is a white pixel in the residual texture template after the relative position adjustment, and a black pixel in the residual texture sample after the relative position adjustment; each element in the second set is located in the overlapping area And the element is a black pixel in the residual texture template after the relative position adjustment, and a white pixel in the residual texture sample after the relative position adjustment; each element in the third set is located in the overlapping area, and This element is a white pixel in the residual texture template after the relative position adjustment. Lines of white pixel points remaining samples after the position adjustment.
  • obtaining the geometric transformation vector information corresponding to the fingerprint image of the last frame includes: obtaining the geometric transformation vector information corresponding to the fingerprint image of the last frame according to the fingerprint image of the last frame and the existing fingerprint image template.
  • determining at least one influencing factor of the fingerprint recognition process caused by the fixed residual area on the fingerprint image of the last frame in the N-frame fingerprint image includes: determining feature points in the fingerprint image of the last frame that satisfy the geometric transformation vector information constraint The set of feature points; calculate the proportion of feature points in the feature point set that falls into the second white binarized image, and use the proportion as an influence factor. This method can effectively determine the impact factor.
  • a terminal device a fingerprint identification device, a storage medium, and a computer program product will be provided below.
  • the effect can be referred to the method section, which is not limited below.
  • an embodiment of the present invention provides a terminal device, including: a processor and a memory for storing execution instructions of the processor, so that the processor is configured to: obtain N frames of fingerprint images, where N is an integer greater than 1; Whether there is a fixed residual area in the N frame fingerprint image; if there is a fixed residual area in the N frame fingerprint image, determine at least one influence factor of the fixed residual area on the fingerprint recognition process caused by the last frame fingerprint image in the N frame fingerprint image; if at least If an impact factor is greater than a corresponding preset threshold, it is determined that the fingerprint image of the last frame cannot trigger a normal fingerprint recognition result, wherein the fingerprint image of the last frame is the currently collected fingerprint image.
  • an embodiment of the present invention provides a fingerprint identification device, including: an acquisition module, a judgment module, a first determination module, and a second determination module.
  • the obtaining module is configured to obtain N frames of fingerprint images, and N is an integer greater than 1.
  • the determination module is used to determine whether there are fixed residual areas in the N frames of fingerprint images; and the first determining module is used to fix fixed residual areas in the N frames of fingerprint images.
  • the second determination module is configured to determine that if the at least one influence factor is greater than the corresponding preset threshold, the last fingerprint image in the N frame fingerprint images cannot trigger normally
  • an embodiment of the present invention provides a computer storage medium, where the storage medium includes computer instructions, and when the instructions are executed by a computer, the computer implements the method of the first aspect or an optional manner of the first aspect.
  • an embodiment of the present invention provides a computer program product, including computer instructions.
  • the instructions When the instructions are executed by a computer, the computer enables the computer to implement the method of the first aspect or an optional manner of the first aspect.
  • An embodiment of the present invention provides a fingerprint identification method, device, device, and storage medium, including: obtaining N frames of fingerprint images, where N is an integer greater than 1, determining whether there are fixed residual areas in the N frames of fingerprint images; and if N frames of fingerprint images exist Fixed residual area, determine at least one influence factor of the fingerprint recognition process caused by the fixed residual area on the fingerprint image of the last frame in the N-frame fingerprint image; if the at least one impact factor is greater than the corresponding preset threshold, determine the last frame The fingerprint image cannot trigger normal fingerprint recognition results. If the fingerprint image of the last frame is an illegal fingerprint image mixed with a residual texture, the method provided in the embodiment of the present invention prevents the fingerprint image of the last frame from triggering a normal fingerprint recognition result. This improves the security of the fingerprint recognition process.
  • FIG. 1 is a flowchart of a fingerprint recognition method according to an embodiment of the present invention
  • FIG. 2 is a flowchart of a fingerprint recognition method according to another embodiment of the present invention.
  • 3A is a schematic diagram of an original first white binarized image according to an embodiment of the present invention.
  • 3B is a schematic diagram of a first white binary image after deletion according to an embodiment of the present invention.
  • 4A is a schematic diagram of a storage manner of a first black binary image of N frames provided by an embodiment of the present invention
  • 4B is a schematic diagram of a storage manner of a first white binary image of N frames provided by an embodiment of the present invention
  • FIG. 5 is a flowchart of a fingerprint identification method according to another embodiment of the present invention.
  • 6A to 6C are schematic diagrams of a residual texture template and a residual texture sample according to an embodiment of the present invention.
  • FIG. 7 is a schematic diagram of a first set, a second set, a third set, and an overlapping area according to an embodiment of the present invention
  • FIG. 8 is a flowchart of a fingerprint recognition method according to another embodiment of the present invention.
  • FIG. 9 is a schematic structural diagram of a fingerprint recognition device according to an embodiment of the present invention.
  • FIG. 10 is a schematic structural diagram of a terminal device according to an embodiment of the present invention.
  • embodiments of the present invention provide a fingerprint identification method, device, device, and storage medium.
  • the main idea of the embodiment of the present invention is: determining a fixed residual area in the N frame fingerprint image according to the N (N is an integer greater than 1) frame fingerprint image, and secondly, determining that the fixed residual area is the last frame in the N frame fingerprint image.
  • the impact factor of the fingerprint recognition process caused by the fingerprint image When the impact factor is greater than a preset threshold, it is determined that the last frame of the fingerprint image cannot trigger normal fingerprint recognition results, such as fingerprint unlocking or fingerprint payment. For example, when the fingerprint of the terminal device When there are scratches on the sensor, for the N frame fingerprint images, there are fixed residual areas corresponding to the scratches.
  • the normal fingerprint recognition result will still be triggered, but if the last frame of the fingerprint image is an illegal fingerprint image mixed with residual lines, when there is a fixed residual Area, the normal fingerprint recognition result cannot be triggered at this time, so it is necessary to determine the fixed residual area for N frames Factor fingerprint identification process, a final fingerprint image pattern image caused when the impact factor than a preset threshold value, it is determined that a fingerprint image can not be finally triggered normal fingerprint recognition result.
  • the fixed residual area has a larger impact factor on the fingerprint recognition process caused by the last frame of the fingerprint image in N frames of fingerprint images.
  • the fixed residual area has an impact on N
  • the impact factor of the fingerprint recognition process caused by the last frame fingerprint image in the frame fingerprint image is smaller than the impact factor of the fingerprint portion of the user's fingerprint that is not covered by scratches or the like.
  • the embodiments of the present invention can be applied to user fingerprint registration, user unlocking, and fingerprint payment processes.
  • the user is usually required to input the user fingerprint multiple times.
  • the terminal device will generate a fingerprint template with a fixed residual area (due to scratches, cracks, imageable substances, etc.).
  • the illegal fingerprint mixed with the residual texture can easily crack the user's fingerprint, thereby achieving fingerprint unlocking or fingerprint payment.
  • the terminal device will generate a fingerprint template with a fixed residual area. These images with fixed residual texture have the opportunity to learn to enter the fingerprint template.
  • the terminal device obtains an illegal fingerprint mixed with residual texture, there is also a fixed residual area in the fingerprint image corresponding to the illegal fingerprint mixed with residual texture. Therefore, in this case, the illegal fingerprint mixed with the residual texture can easily crack the terminal device, thereby achieving fingerprint unlocking or fingerprint payment.
  • the embodiments of the present invention are not limited to the foregoing application scenarios.
  • FIG. 1 is a flowchart of a fingerprint recognition method provided by an embodiment of the present invention.
  • the method is executed by a part or all of a terminal device, such as a terminal device or a processor in the terminal device.
  • the fingerprint identification method will be described below by taking the execution subject of the method as a terminal device as an example.
  • the terminal device may be a terminal having a fingerprint recognition function, such as a mobile phone, a PAD, and a notebook computer, which is not limited in this embodiment of the present invention.
  • the fingerprint identification method includes the following processes:
  • Step S11 The terminal device acquires N frames of fingerprint images, where N is an integer greater than 1.
  • Step S12 The terminal device determines whether there is a fixed residual area in the N-frame fingerprint image.
  • Step S13 if there is a fixed residual area in the N-frame fingerprint image, determine at least one influencing factor of the fingerprint recognition process caused by the fixed residual area on the last frame fingerprint image in the N-frame fingerprint image.
  • Step S14 if the at least one impact factor is greater than a corresponding preset threshold, it is determined that the fingerprint image of the last frame cannot trigger a normal fingerprint recognition result.
  • step S12 The description of step S12:
  • the so-called fixed residual area refers to an area in which all N-frame fingerprint images exist.
  • the area is composed of at least one connected area, and the total area of these connected areas is larger than the first preset area.
  • the first preset area may be set according to an actual situation, which is not limited in the embodiment of the present invention.
  • the above-mentioned fixed residual area exists. Based on this, the above-mentioned fixed residual area may be caused by scratches, cracks, or imageable substances on the fingerprint sensor of the terminal device.
  • Step S13 and step S14 are described:
  • the last frame fingerprint image is a fingerprint image currently collected by the terminal device.
  • the fingerprint recognition process caused by the last frame fingerprint image is obtained by matching the last frame fingerprint image with the fingerprint recognition template, and the last frame fingerprint image includes fingerprints of other parts in addition to the fixed residual area, so the impact here
  • the factor refers to the influence factor of the fixed residual area on the fingerprint recognition process caused by the last frame fingerprint image in the N frame fingerprint images.
  • the larger the influence factor it indicates that the last frame fingerprint image is an illegal fingerprint image mixed with residual lines.
  • the impact factor of the fixed residual area on the fingerprint recognition process caused by the last frame of the fingerprint image in the N-frame fingerprint image is relative to the impact factor of the user's fingerprint that is not covered by scratches and other parts small.
  • step S14 if the at least one impact factor is greater than the respective corresponding preset threshold, it is determined that the fingerprint image of the last frame cannot trigger a normal fingerprint recognition result; on the contrary, if one of the at least one impact factor is If at least one is less than or equal to a corresponding preset threshold, it is determined that the fingerprint image of the last frame can trigger a normal fingerprint recognition result.
  • the normal fingerprint recognition result may be fingerprint unlocking or fingerprint payment, etc., which are not limited in the embodiment of the present invention.
  • An embodiment of the present invention provides a fingerprint recognition method, wherein if there is a fixed residual area in an N-frame fingerprint image, determining at least one influence factor of the fixed residual area on the fingerprint recognition process caused by the last frame fingerprint image in the N-frame fingerprint image . If the at least one impact factor is greater than a respective preset threshold, it is determined that the fingerprint image of the last frame cannot trigger a normal fingerprint recognition result. Based on this, on the one hand, if the last frame fingerprint image is an illegal fingerprint image with residual texture, the method provided by the embodiment of the present invention makes the last frame fingerprint image unable to trigger a normal fingerprint recognition result. This improves the security of the fingerprint recognition process.
  • the impact factor corresponding to the fixed residual area is less than or equal to the corresponding preset threshold , which can trigger normal fingerprint recognition results. Thereby, a normal fingerprint recognition process can be guaranteed.
  • step S12 is described as follows:
  • the terminal device determines pixels with the same pixel values at corresponding positions in the N-frame fingerprint image.
  • the so-called corresponding position refers to placing the N-frame fingerprint image in the same coordinate system, and the four corner pixels of the N-frame image are aligned.
  • the so-called four corner pixels include: the upper left pixel, the lower left pixel, the upper right pixel, and the lower right pixel. Based on this, a certain pixel point in each frame of fingerprint image has a corresponding pixel point in other N-1 frame fingerprint images, for example, the center points in N frame fingerprint images all correspond to each other.
  • the terminal device determines pixels with the same pixel value in the corresponding position in the N-frame fingerprint image
  • the terminal device determines at least one connected area formed by these pixels. It should be noted that the connected areas are not connected. If the total area of the at least one connected area is larger than the first preset area, the terminal device determines that the at least one connected area is a fixed residual area.
  • FIG. 2 is a flowchart of a fingerprint recognition method according to another embodiment of the present invention. As shown in FIG. 2, the above step S12 includes:
  • Step S121 The terminal device binarizes the N-frame fingerprint images respectively to obtain N groups of first binarized images, and each group of the first binarized images includes a first black binarized image and a first white binarized image. image.
  • Step S122 The terminal device performs an AND operation on the pixel values of each pixel point in the first black binarized image in N frames to obtain a second black binarized image, and applies the same to the first white binarized image in N frames. AND operation is performed on the pixel values of each pixel point to obtain a second white binary image.
  • Step S123 The terminal device performs an OR operation on the pixel value of each pixel point in the second black binarized image and the pixel value of each pixel point in the second white binarized image to obtain a second binarized image.
  • Step S124 If the second binarized image includes at least one connected area that satisfies a preset condition, the terminal device determines that a fixed residual area exists in the N-frame fingerprint image, where the fixed residual area is composed of the at least one connected area.
  • the preset condition is that a total area of the at least one connected area is greater than a first preset area.
  • step S121 The following describes step S121:
  • a (x, y) represents the grayscale pixel value of the pixel point (x, y)
  • M is a statistical value of the grayscale pixel value of all the pixel points in the neighborhood window, including but not limited to mean, medium Value, maximum inter-class variance value, etc., this embodiment of the present invention does not limit this.
  • neighborhood window is a rectangular window.
  • the neighborhood window may also be a circle, other polygons, etc. This embodiment of the present invention does not limit this.
  • the method further includes: deleting, by the terminal device, a connected area having an area smaller than a second preset area in the first black binarized image, and deleting the area smaller than the first area in the first white binarized image.
  • a connected area having an area smaller than a second preset area in the first black binarized image
  • deleting the area smaller than the first area in the first white binarized image Three preset areas of connected areas.
  • the second preset area may be the same as the third preset area, or may be different.
  • FIG. 3A is a schematic diagram of an original first black binarized image according to an embodiment of the present invention
  • FIG. 3B is a schematic diagram of a deleted first black binarized image according to an embodiment of the present invention, as shown in FIG. 3A
  • the original first black binarized image includes: six connected areas, which are connected area 1 to connected area 6, respectively, assuming that the areas of connected area 1, connected area 5, and connected area 6 are all smaller than the second preset area
  • the terminal device can delete the connected area 1, the connected area 5, and the connected area 6.
  • the first black binarized image after deletion is shown in FIG. 3B, and only connected area 2, connected area 3, and connected area 4 remain.
  • the method for deleting the first white binarized image is the same as the method for deleting the first black binarized image, which is not repeatedly described in this embodiment of the present invention.
  • FIG. 4A is a schematic diagram of a storage method of a first black binary image of N frames according to an embodiment of the present invention.
  • the first black binary image of N frames is stored according to queue 40A, and the first of the last frame is first The black binarized image is at the end of the line.
  • the first black binarized image in the last frame enters the queue, the first black binarized image in the Nth frame before the last black binarized image in the last frame is dequeued. To ensure that there are N frames of first black binarized images in the queue.
  • the number of first black binarized images in the queue is less than N frames, for example, the number of first black binarized images in the queue is N-1, and N-1 frames can be
  • the first black binarized image is similar to the method in step S122, and no operation is required.
  • FIG. 4B is a schematic diagram of a storage method of the first white binarized image of N frames according to an embodiment of the present invention.
  • the first white binarized image of N frames is stored according to the queue 40B, and the first of the last frame is first.
  • the white binarized image is located at the end of the line.
  • the first white binarized image in the last frame enters the queue, the first white binarized image in the Nth frame before the first white binarized image in the last frame is dequeued. To ensure that there are N frames of first white binarized images in the queue.
  • the number of first white binarized images in the queue is less than N frames, for example, the number of first white binarized images in the queue is N-1, and N-1 frames can be A method similar to step S122 is performed on the first white binarized image, and no operation is required.
  • the terminal device performs AND operation on the pixel values of each pixel point in the first black binarized image in N frames to obtain a second black binarized image.
  • B bc B b1 & B b2 ... B bN , where B bc is the second black binary image. & Indicates AND operation.
  • the terminal device performs an AND operation on the pixel values of each pixel in the first white binarized image in the N frames to obtain a second white binarized image.
  • B wc B w1 & B w2 ... B wN , where B wc is the second white binarized image. & Indicates AND operation.
  • the method further includes: deleting, by the terminal device, a connected area having an area smaller than a fourth preset area in the second black binarized image, and deleting the area smaller than the first white binarized image.
  • a connected area having an area smaller than a fourth preset area in the second black binarized image
  • deleting the area smaller than the first white binarized image Three preset areas of connected areas.
  • the fourth preset area may be the same as or different from the fourth preset area.
  • the terminal device deletes the connected area with an area smaller than the fourth preset area in the second black binarized image, and deletes the connected area with an area smaller than the third preset area in the second white binarized image.
  • Region method and the terminal device deletes the connected area with an area smaller than a second preset area in the first black binarized image, and deletes the connected area with an area smaller than a third preset area in the first white binarized image
  • the regional method is similar, which is not repeated in the embodiment of the present invention.
  • the terminal device After the terminal device determines the second black binary image and the second white binary image, the terminal device compares the pixel value of each pixel point in the second black binary image with the corresponding value in the second white binary image. Perform the OR operation on the pixel values of each pixel point to obtain a second binarized image.
  • B mask B wc
  • the first preset area may be set according to an actual situation, which is not limited in the embodiment of the present invention.
  • both methods for determining the fixed residual area are provided. Both methods can accurately determine the fixed residual area. Wherein, the larger N in the embodiment of the present invention, the more accurate the fixed residual area is determined.
  • Step S13 can be implemented by the following third or fourth embodiment:
  • FIG. 5 is a flowchart of a fingerprint identification method according to another embodiment of the present invention. As shown in FIG. 5, the above step S13 includes:
  • Step S131a If there is a fixed residual area in the N-frame fingerprint image, the terminal device obtains geometric transformation vector information corresponding to the last frame of fingerprint image.
  • Step S132a The terminal device uses the second binarized image as a residual texture template and a residual texture sample.
  • Step S133a The terminal device adjusts the relative positions of the residual texture template and the residual texture sample according to the geometric transformation vector information.
  • Step S134a The terminal device calculates the similarity between the residual texture template and the residual texture sample after the relative position adjustment, and uses the similarity as an influence factor.
  • the terminal device may obtain the geometric transformation vector information H corresponding to the fingerprint image of the last frame according to the fingerprint image of the last frame and the existing fingerprint image template.
  • the fingerprint image template may be a fingerprint image template formed by a fingerprint of a legitimate user, or may be a fingerprint image template of a legitimate user mixed with a residual pattern.
  • how to generate the geometric transformation vector information H may adopt a method in the prior art, and the geometric transformation vector information H is used to adjust the relative positions of the residual texture template and the residual texture sample.
  • the geometric transformation vector information is preset geometric transformation vector information, as long as it can adjust the relative positions of the residual texture template and the residual texture sample, which is not limited in this embodiment of the present invention.
  • the residual texture template may be denoted as T, and the residual texture sample may be denoted as S.
  • the manner in which the terminal device adjusts the relative positions of the residual texture template and the residual texture sample according to the geometric transformation vector information may adopt the prior art, which is not limited in the embodiment of the present invention.
  • the relative position of the residual texture template and the residual texture sample is adjusted by keeping the position of the residual texture template unchanged and adjusting the position of the residual texture sample, or by keeping the position of the residual texture sample unchanged and adjusting the position of the residual texture template. position.
  • the relative positions of the residual grain template and the residual grain sample include at least one of the following: relative displacement, relative rotation angle, and scale-up of the residual grain template and the residual grain sample.
  • FIG. 6A to 6C are schematic diagrams of a residual texture template and a residual texture sample according to an embodiment of the present invention.
  • FIG. 6A the relative displacement and symmetrical changes in the horizontal direction of the residual texture template and the residual texture sample occur.
  • FIG. 6B the residual grain template and the residual grain sample undergo relative displacement and 180 ° rotation in the horizontal and vertical directions.
  • FIG. 6C the residual grain template and the residual grain sample are relatively rotated.
  • the method is still applicable to this scenario.
  • the fingerprint image of the last frame is the same as the residual texture sample, and the translation and symmetric changes occur with respect to the residual texture template.
  • the impact factor determined by the method will be greater than the corresponding preset threshold, so that the residual texture template cannot trigger a normal fingerprint recognition result.
  • the terminal device uses the second binarized image as a residual texture template and a residual texture sample.
  • the terminal device may also use only the second binarized image as the residual texture sample, and the residual texture template used in calculating the impact factor may be the second binary image of the fingerprint image template described above. There are no restrictions.
  • Step S134a the terminal device determines the overlapping area of the residual texture template and the residual texture sample after the relative position adjustment; determines the first set, the second set, and the third set, and determines the first set
  • the proportion of the elements in the first set, the second set, and the third set is the proportion of the total elements in the first set, and the proportion is used as the similarity; wherein each of the first set The element is located in the overlapping area, and the element is a white pixel in the residual texture template after the relative position adjustment, and a black pixel in the residual texture sample after the relative position adjustment; Each element is located in the overlapping area, and the element is a black pixel point in the residual texture template after the relative position adjustment, and a white pixel point in the residual texture sample after the relative position adjustment; the third set Each element in is located in the overlapping area, and the element is a white image in the residual texture template after the relative position adjustment Point, the white pixel lines remaining samples after adjusting the relative position of the.
  • FIG. 7 is a schematic diagram of a first set, a second set, a third set, and an overlapping area provided by an embodiment of the present invention.
  • an area in a virtual circle is an overlapping area O
  • the first set is used for O 01 represents that the second set is represented by O 10 and the third set is represented by O 11 .
  • && means and.
  • a method for determining at least one influence factor of a fingerprint recognition process caused by a fixed residual area on a fingerprint image of the last frame in an N-frame fingerprint image is provided, and the influence factor can be effectively determined by this method.
  • FIG. 8 is a flowchart of a fingerprint recognition method according to another embodiment of the present invention. As shown in FIG. 8, the above step S13 includes:
  • Step S131b If there is a fixed residual area in the N-frame fingerprint image, the terminal device determines a feature point set formed by the feature points in the last frame of the fingerprint image that satisfy the geometric transformation vector information constraint.
  • Step S132b The terminal device calculates a feature point ratio of the feature point set that falls in the second white binarized image, and uses the ratio as one of the influence factors.
  • the geometric transformation vector information includes at least one of the following: translation, rotation, scaling, symmetry, miscutting, and nonlinear degeneration information.
  • the terminal device determines a feature point set K composed of feature points satisfying the geometric transformation vector information constraint in the last frame of the fingerprint image.
  • Embodiment 4 and Embodiment 3 can be combined, that is, at least one influencing factor of the fingerprint recognition process caused by the fixed residual area on the last frame fingerprint image in the N frame fingerprint images includes: determined in Embodiment 3 And the impact factor determined in the fourth embodiment.
  • the preset threshold corresponding to the impact factor determined in the third embodiment and the preset threshold corresponding to the impact factor determined in the fourth embodiment may be the same or different, which is not limited in the embodiment of the present invention.
  • a method for determining at least one influence factor of a fingerprint recognition process caused by a fixed residual area on a fingerprint image of the last frame in an N-frame fingerprint image is provided, and the influence factor can be effectively determined by this method.
  • FIG. 9 is a schematic structural diagram of a fingerprint identification device according to an embodiment of the present invention, where the device may be part or all of a terminal device, for example, the device may be a terminal device or a processor in the terminal device, optionally The terminal device may be a terminal having a fingerprint recognition function, such as a mobile phone, a PAD, and a notebook computer, which is not limited in the embodiment of the present invention.
  • the device includes:
  • the obtaining module 91 is configured to obtain N frames of fingerprint images, where N is an integer greater than 1.
  • the judging module 92 is configured to judge whether a fixed residual area exists in the N-frame fingerprint image.
  • a first determining module 93 is configured to determine at least one influence factor of the fixed residual area on a fingerprint recognition process if the fixed residual area exists in the N-frame fingerprint image.
  • the second determining module 94 is configured to determine that if the at least one impact factor is greater than a corresponding preset threshold, the last fingerprint image in the N-frame fingerprint image cannot trigger a normal fingerprint recognition result.
  • the last fingerprint image is the fingerprint image currently collected.
  • the judging module 92 is specifically configured to perform binarization processing on the N-frame fingerprint images to obtain N groups of first binarized images, and each group of the first binarized images includes a first black binary image.
  • the apparatus further includes: a first deletion module 95, configured to perform an AND operation on pixel values of each pixel in the first black binary image in N frames to obtain a second black binary image And perform an AND operation on the pixel values of each pixel in the first white binarized image in N frames to obtain a second white binarized image, before deleting the first black binarized image with an area smaller than the first A connected area of two preset areas, and the connected area with an area smaller than a third preset area in the first white binarized image is deleted.
  • a first deletion module 95 configured to perform an AND operation on pixel values of each pixel in the first black binary image in N frames to obtain a second black binary image
  • an AND operation on the pixel values of each pixel in the first white binarized image in N frames to obtain a second white binarized image, before deleting the first black binarized image with an area smaller than the first A connected area of two preset areas, and the connected area with an area smaller than a third preset area in the first white binarized
  • the device further includes: a second deleting module 96, configured to perform a pixel value on each pixel in the second black binarized image and a corresponding one in the second white binarized image. Perform an OR operation on the pixel values of the pixels to obtain a second binarized image, delete the connected area with an area smaller than a fourth preset area in the second black binarized image, and delete the second white binarized image. A connected region having an area smaller than a third preset area in the image.
  • the first determining module 93 is specifically configured to: obtain geometric transformation vector information corresponding to the last frame fingerprint image; use the second binarized image as a residual texture template and a residual texture sample; according to the geometry
  • the transformation vector information adjusts the relative position of the residual texture template and the residual texture sample; calculates the similarity between the residual texture template and the residual texture sample after the relative position adjustment is performed, and uses the similarity as one of the influence factors.
  • the first determining module 93 is specifically configured to determine an overlapping area of the residual texture template and the residual texture sample after the relative position adjustment; determine the first set, the second set, and the third set, and determine the first set The ratio of the elements in the set to the total elements in the first set, the second set, and the third set, and the ratio is used as the similarity; wherein each of the first set The element is located in the overlapping area, and the element is a white pixel in the residual texture template after the relative position adjustment, and a black pixel in the residual texture sample after the relative position adjustment; Each element is located in the overlapping area, and the element is a black pixel point in the residual texture template after the relative position adjustment, and a white pixel point in the residual texture sample after the relative position adjustment; the third set Each element in is located in the overlapping area, and the residual grain template of the element after the relative position adjustment is a white pixel, in White pixel lines remaining after the sample had a relative position adjustment.
  • the first determining module 93 is specifically configured to obtain geometric transformation vector information corresponding to the last frame fingerprint image according to the last frame fingerprint image and an existing fingerprint image template.
  • the second determining module 94 is specifically configured to: determine a feature point in the fingerprint image of the last frame; calculate a ratio of white pixel points in the second binarized image to the feature point, and The ratio is used as one of the impact factors.
  • the fingerprint recognition device provided by the embodiment of the present invention may be used to execute the above-mentioned fingerprint recognition method, and its content and effects may refer to the above method part, which is not repeatedly described in the embodiment of the present invention.
  • FIG. 10 is a schematic structural diagram of a terminal device according to an embodiment of the present invention.
  • the terminal device may be a terminal having a fingerprint recognition function, such as a mobile phone, a PAD, and a notebook computer, which is not limited in the embodiment of the present invention.
  • the device includes: a processor 101, a transceiver 102, and a memory 103, where the transceiver 102 is used to implement communication with other devices, and the memory 103 is used to store execution instructions of the processor 101,
  • the processor 101 For the processor 101 to implement the above-mentioned fingerprint identification method, its content and effects can be referred to the above-mentioned method part, which will not be described in detail in the embodiment of the present invention.
  • An embodiment of the present invention further provides a computer storage medium, where the storage medium includes computer instructions, and when the instructions are executed by a computer, the computer is enabled to implement the fingerprint identification method as described above.
  • the storage medium includes computer instructions, and when the instructions are executed by a computer, the computer is enabled to implement the fingerprint identification method as described above.
  • An embodiment of the present invention further provides a computer program product, including computer instructions, when the instructions are executed by a computer, causing the computer to implement the fingerprint identification method as described above.
  • a computer program product including computer instructions, when the instructions are executed by a computer, causing the computer to implement the fingerprint identification method as described above.
  • a person of ordinary skill in the art may understand that all or part of the steps of implementing the foregoing method embodiments may be implemented by a program instructing related hardware.
  • the aforementioned program may be stored in a computer-readable storage medium.
  • the steps including the foregoing method embodiments are executed; and the foregoing storage medium includes: various media that can store program codes, such as a ROM, a RAM, a magnetic disk, or an optical disc.

Landscapes

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

Abstract

一种指纹识别方法、装置、设备及存储介质，包括：终端设备获取N帧指纹图像，N为大于1的整数（S11）；终端设备判断N帧指纹图像是否存在固定残留区域（S12）；若所述N帧指纹图像存在固定残留区域，则确定固定残留区域对N帧指纹图像中的最后一帧指纹图像引起的指纹识别过程的至少一个影响因子（S13）；若所述至少一个影响因子大于各自对应的预设阈值，则确定最后一帧指纹图像无法触发正常的指纹识别结果（S14）。该方法可以提高指纹识别过程的安全性。

Description

指纹识别方法、装置、设备及存储介质 技术领域
本发明涉及指纹识别技术领域，尤其涉及一种指纹识别方法、装置、设备及存储介质。
背景技术
近年，指纹识别技术在终端设备领域发展迅速，大量的终端设备拥有指纹解锁、指纹支付等功能。随着指纹解锁、指纹支付的使用频率越来越大，安全问题也越来越突出。
例如：当终端设备的指纹传感器表面存在划痕、开裂，恶意或无意粘贴可成像物质等时，虽然肉眼可察觉，但由于一般不影响指纹解锁或者指纹支付等，导致用户往往容易忽略上述异常，继续使用终端设备。随着用户使用次数增加，终端设备的指纹识别系统中将生成越来越多的混有残留纹路的模板，使得混有残留纹路的非法指纹能够与混有残留纹路的模板匹配，从而实现非法指纹对终端设备的解锁或者完成指纹支付等，因此，现有的指纹识别技术存在一定的安全隐患。
发明内容
本发明提供一种指纹识别方法、装置、设备及存储介质，从而提高指纹识别过程的安全性。
第一方面，本发明实施例提供一种指纹识别方法，包括：获取N帧指纹图像，N为大于1的整数；判断N帧指纹图像是否存在固定残留区域；若N帧指纹图像存在固定残留区域，则确定固定残留区域对N帧指纹图像中的最后一帧指纹图像引起的指纹识别过程的至少一个影响因子；若至少一个影响因子大于各自对应的预设阈值，则确定最后一帧指纹图像无法触发正常的指纹识别结果。其中，最后一帧指纹图像为当前采集到的指纹图像。
基于此，一方面，若最后一帧指纹图像是混有残留纹路的非法指纹图像 时，本发明实施例提供的方法使得该最后一帧指纹图像无法触发正常的指纹识别结果。从而提高指纹识别过程的安全性，另一方面，若最后一帧指纹图像是合法的用户指纹图像时，由于这种情况下，固定残留区域不存在，或者其对应的影响因子小于或等于对应的预设阈值，因此仍然可以触发正常的指纹识别结果。从而可以保证正常的指纹识别过程。
可选地，判断N帧指纹图像是否存在固定残留区域，包括：对N帧指纹图像分别进行二值化处理，得到N组第一二值化图像，每组第一二值化图像包括第一黑色二值化图像和第一白色二值化图像；对N帧第一黑色二值化图像中的各像素点的像素值进行与操作，得到第二黑色二值化图像，并对N帧第一白色二值化图像中的各像素点的像素值进行与操作，得到第二白色二值化图像；对第二黑色二值化图像中的各像素点的像素值和第二白色二值化图像中对应的各像素点的像素值进行或操作，得到第二二值化图像；若第二二值化图像中包括满足预设条件的至少一个连通区域，则确定N帧指纹图像存在固定残留区域，其中固定残留区域由至少一个连通区域组成；其中，预设条件为至少一个连通区域的面积总和大于第一预设面积。基于此，通过该方法可以准确的确定固定残留区域。
可选地，对N帧第一黑色二值化图像中的各像素点的像素值进行与操作，得到第二黑色二值化图像，并对N帧第一白色二值化图像中的各像素点的像素值进行与操作，得到第二白色二值化图像之前，还包括：删除第一黑色二值化图像中面积小于第二预设面积的连通区域，并删除第一白色二值化图像中面积小于第三预设面积的连通区域。即使用连通区域面积过滤法实现滤除噪声的作用。
可选地，对第二黑色二值化图像中的各像素点的像素值和第二白色二值化图像中对应的各像素点的像素值进行或操作，得到第二二值化图像之前，还包括：删除第二黑色二值化图像中面积小于第四预设面积的连通区域，并删除第二白色二值化图像中面积小于第三预设面积的连通区域。即使用连通区域面积过滤法实现滤除噪声的作用。
可选地，确定固定残留区域对N帧指纹图像中的最后一帧指纹图像引起的指纹识别过程的至少一个影响因子，包括：获取最后一帧指纹图像对应的几何变换矢量信息；第二二值化图像作为残留纹路模板和残留纹路样本；根 据几何变换矢量信息调整残留纹路模板和残留纹路样本的相对位置；计算经过相对位置调整之后的残留纹路模板和残留纹路样本的相似度，并将相似度作为一个影响因子。通过该方法可以有效的确定影响因子。
可选地，几何变换矢量信息包括以下至少一项：平移、旋转、缩放、对称、错切、非线性变形信息。
可选地，计算经过相对位置调整之后的残留纹路模板和残留纹路样本的相似度，包括：确定经过相对位置调整之后的残留纹路模板和残留纹路样本的重叠区域；确定第一集合、第二集合和第三集合，并确定第一集合中的元素占第一集合、第二集合和第三集合中的总元素的比例，将比例作为相似度；其中，第一集合中的每个元素位于重叠区域中，且该元素在经过相对位置调整之后的残留纹路模板中是白色像素点，在经过相对位置调整之后的残留纹路样本中的黑色像素点；第二集合中的每个元素位于重叠区域中，且该元素在经过相对位置调整之后的残留纹路模板中是黑色像素点，在经过相对位置调整之后的残留纹路样本中的白色像素点；第三集合中的每个元素位于重叠区域中，且该元素在经过相对位置调整之后的残留纹路模板中是白色像素点，在经过相对位置调整之后的残留纹路样本中的白色像素点。
可选地，获取最后一帧指纹图像对应的几何变换矢量信息，包括：根据最后一帧指纹图像和已存在的指纹图像模板，得到最后一帧指纹图像对应的几何变换矢量信息。
可选地，确定固定残留区域对N帧指纹图像中的最后一帧指纹图像引起的指纹识别过程的至少一个影响因子，包括：确定最后一帧指纹图像中满足几何变换矢量信息约束的特征点所构成的特征点集合；计算特征点集合中落入第二白色二值化图像的特征点比例，并将所述比例作为一个影响因子。通过该方法可以有效的确定影响因子。
下面将提供一种终端设备、指纹识别装置、存储介质及计算机程序产品。其效果可参考方法部分，下面对此不做限制。
第二方面，本发明实施例提供一种终端设备，包括：处理器和用于存储处理器的执行指令的存储器，以使处理器用于：获取N帧指纹图像，N为大于1的整数；判断N帧指纹图像是否存在固定残留区域；若N帧指纹图像存在固定残留区域，则确定固定残留区域对N帧指纹图像中的最后一帧指纹图 像引起的指纹识别过程的至少一个影响因子；若至少一个影响因子大于各自对应的预设阈值，则确定最后一帧指纹图像无法触发正常的指纹识别结果，其中，所述最后一帧指纹图像为当前采集到的指纹图像。
第三方面，本发明实施例提供一种指纹识别装置，包括：获取模块、判断模块、第一确定模块和第二确定模块。其中，获取模块用于获取N帧指纹图像，N为大于1的整数；判断模块用于判断N帧指纹图像是否存在固定残留区域；第一确定模块用于若N帧指纹图像存在固定残留区域，则确定固定残留区域对指纹识别过程的至少一个影响因子；第二确定模块用于若至少一个影响因子大于各自对应的预设阈值，则确定N帧指纹图像中的最后一帧指纹图像无法触发正常的指纹识别结果，其中，所述最后一帧指纹图像为当前采集到的指纹图像。
第四方面，本发明实施例提供一种计算机存储介质，存储介质包括计算机指令，当指令被计算机执行时，使得计算机实现如第一方面或第一方面的可选方式的方法。
第五方面，本发明实施例提供一种计算机程序产品，包括计算机指令，当指令被计算机执行时，使得计算机实现如第一方面或第一方面的可选方式的方法。
本发明实施例提供一种指纹识别方法、装置、设备及存储介质，包括：获取N帧指纹图像，N为大于1的整数；判断N帧指纹图像是否存在固定残留区域；若N帧指纹图像存在固定残留区域，则确定固定残留区域对N帧指纹图像中的最后一帧指纹图像引起的指纹识别过程的至少一个影响因子；若至少一个影响因子大于各自对应的预设阈值，则确定最后一帧指纹图像无法触发正常的指纹识别结果。若最后一帧指纹图像是混有残留纹路的非法指纹图像时，本发明实施例提供的方法使得该最后一帧指纹图像无法触发正常的指纹识别结果。从而提高指纹识别过程的安全性。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作一简单地介绍，显而易见地，下面描述中的附图是本发明的一些实施例，对于本领域普通技术人员来讲，在 不付出创造性劳动性的前提下，还可以根据这些附图获得其他的附图。
图1为本发明一实施例提供的指纹识别方法的流程图；
图2为本发明另一实施例提供的指纹识别方法的流程图；
图3A为本发明一实施例提供的原始的第一白色二值化图像的示意图；
图3B为本发明一实施例提供的删除之后的第一白色二值化图像的示意图；
图4A为本发明一实施例提供的N帧第一黑色二值化图像的存储方式的示意图；
图4B为本发明一实施例提供的N帧第一白色二值化图像的存储方式的示意图；
图5为本发明再一实施例提供的指纹识别方法的流程图；
图6A至图6C为本发明一实施例提供的残留纹路模板和残留纹路样本的示意图；
图7为本发明一实施例提供的第一集合、第二集合、第三集合以及重叠区域的示意图；
图8为本发明又一实施例提供的指纹识别方法的流程图；
图9为本发明一实施例提供的一种指纹识别装置的结构示意图；
图10为本发明一实施例提供的一种终端设备的结构示意图。
具体实施方式
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
本发明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数据在适当情况下可以互换，以便这里描述的本发明的实施例，例如能够以除了在这里图示或描述的那些以外的顺序实施。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。
如上所述，当终端设备的指纹传感器表面存在划痕、开裂，恶意或无意粘贴可成像物质等时，虽然肉眼可察觉，但由于一般不影响指纹解锁或者指纹支付等，导致用户往往容易忽略上述异常，继续使用终端设备。随着用户使用次数增加，终端设备的指纹识别系统中将生成越来越多的带有残留纹路的模板，使得混有残留纹路的非法指纹图像能够与混有残留纹路的模板匹配，从而实现非法指纹对终端设备的解锁或者完成指纹支付等，因此，现有的指纹识别技术存在一定的安全隐患。为了解决这个技术问题，本发明实施例提供一种指纹识别方法、装置、设备及存储介质。
本发明实施例的主旨思想是：根据N(N为大于1的整数)帧指纹图像确定N帧指纹图像中的固定残留区域，其次，确定该固定残留区域对N帧指纹图像中的最后一帧指纹图像引起的指纹识别过程的影响因子，当影响因子大于预设阈值时，则确定最后一帧指纹图像无法触发正常的指纹识别结果，如指纹解锁或者指纹支付等，例如：当终端设备的指纹传感器上存在划痕等时，对于N帧指纹图像来讲，它们中均存在该划痕所对应的固定残留区域，然而如果最后一帧指纹图像是合法的用户指纹(本发明实施例所述的用户指纹均指合法的用户指纹)时，即使存在固定残留区域，这时还是要触发正常的指纹识别结果，但是如果最后一帧指纹图像是混有残留纹路的非法指纹图像时，当存在固定残留区域，这时不能触发正常的指纹识别结果，因此需要确定该固定残留区域对N帧指纹图像中的最后一帧指纹图像引起的指纹识别过程的影响因子，当影响因子大于预设阈值时，则确定最后一帧指纹图像无法触发正常的指纹识别结果。例如：对于混有残留纹路的非法指纹图像，固定残留区域对N帧指纹图像中的最后一帧指纹图像引起的指纹识别过程的影响因子一定较大，对于合法的用户指纹，固定残留区域对N帧指纹图像中的最后一帧指纹图像引起的指纹识别过程的影响因子相对于用户指纹中未被划痕等遮挡的指纹部分的影响因子要小。
本发明实施例的应用场景为：本发明实施例可应用于用户指纹注册、用户解锁、指纹支付过程，例如：在用户指纹注册过程中，通常需要用户多次 输入用户指纹，如果终端设备的指纹传感器上存在划痕、开裂，粘贴可成像物质等时，终端设备将生成具有固定残留区域(由于划痕、开裂，可成像物质等造成的)的指纹模板，这时当终端设备获取到混有残留纹路的非法指纹时，由于该指纹图像模板中中也存在固定残留区域，因此这种情况下，该混有残留纹路的非法指纹很容易破解用户指纹，从而实现指纹解锁或者指纹支付等。类似地，在用户指纹解锁、支付中，通常需要用户输入用户指纹，如果终端设备的指纹传感器上存在划痕、开裂，粘贴可成像物质等时，终端设备将生成具有固定残留区域的指纹模板，这些具有固定残留纹路的图像有机会学习进入指纹模板中，这时当终端设备获取到混有残留纹路的非法指纹时，由于该混有残留纹路的非法指纹对应的指纹图像中也存在固定残留区域，因此这种情况下，该混有残留纹路的非法指纹很容易破解终端设备，从而实现指纹解锁或者指纹支付等。需要说明的是，本发明实施例不限于上述应用场景。
实施例一
图1为本发明一实施例提供的指纹识别方法的流程图，该方法的执行主体为终端设备的部分或全部，如可以是终端设备或者终端设备中的处理器。下面以该方法的执行主体是终端设备为例对指纹识别方法进行说明。可选地，该终端设备可以是手机、PAD、笔记本电脑等具有指纹识别功能的终端，本发明实施例对此不做限定。如图1所示，该指纹识别方法包括如下流程：
步骤S11：终端设备获取N帧指纹图像，N为大于1的整数。
步骤S12：终端设备判断所述N帧指纹图像是否存在固定残留区域。
步骤S13：若所述N帧指纹图像存在固定残留区域，则确定固定残留区域对N帧指纹图像中的最后一帧指纹图像引起的指纹识别过程的至少一个影响因子。
步骤S14：若所述至少一个影响因子大于各自对应的预设阈值，则确定最后一帧指纹图像无法触发正常的指纹识别结果。
针对步骤S12进行说明：
所谓固定残留区域是指N帧指纹图像均存在的区域，其该区域是由至少一个连通区域构成，这些连通区域的面积总和大于第一预设面积。可选地，该第一预设面积可以根据实际情况设置，本发明实施例对此不做限制。
其中，正常情况下，即终端设备的指纹传感器上不存在划痕、开裂，或可成像物质等时，用户输入N次指纹时，每次输入的指纹位置随机，因此N帧指纹图像中很难存在上述固定残留区域。基于此，上述固定残留区域可能是由终端设备的指纹传感器上划痕、开裂，或可成像物质等造成的。
针对步骤S13和步骤S14进行说明：
所述最后一帧指纹图像为终端设备当前采集到的指纹图像。由于最后一帧指纹图像引起指纹识别过程是通过对最后一帧指纹图像和指纹识别模板匹配得到的，而最后一帧指纹图像中除了包括固定残留区域，还包括其他部分的指纹，因此这里的影响因子是指固定残留区域对N帧指纹图像中的最后一帧指纹图像引起的指纹识别过程的影响因子，影响因子越大，则表示最后一帧指纹图像是混有残留纹路的非法指纹图像的可能性越大，相反，影响因子越小，则表示最后一帧指纹图像是混有残留纹路的非法指纹图像的可能性越小，例如：最后一帧图像是合法的用户图像时，对于最后一帧指纹图像引起指纹识别过程来讲，固定残留区域对N帧指纹图像中的最后一帧指纹图像引起的指纹识别过程的影响因子相对于用户指纹中未被划痕等遮挡的指纹部分的影响因子要小。基于此，在步骤S14中：若所述至少一个影响因子大于各自对应的预设阈值，则确定最后一帧指纹图像无法触发正常的指纹识别结果，相反地，若所述至少一个影响因子中的至少一个小于或等于对应的预设阈值，则确定最后一帧指纹图像可以触发正常的指纹识别结果。其中该正常的指纹识别结果可以是指纹解锁或者指纹支付等，本发明实施例对此不做限制。
本发明实施例提供一种指纹识别方法，其中，若N帧指纹图像存在固定残留区域，则确定固定残留区域对N帧指纹图像中的最后一帧指纹图像引起的指纹识别过程的至少一个影响因子。若所述至少一个影响因子大于各自对应的预设阈值，则确定最后一帧指纹图像无法触发正常的指纹识别结果。基于此，一方面，若最后一帧指纹图像是混有残留纹路的非法指纹图像时，本发明实施例提供的方法使得该最后一帧指纹图像无法触发正常的指纹识别结果。从而提高指纹识别过程的安全性，另一方面，若最后一帧指纹图像是合法的用户指纹图像时，由于这种情况下，所述固定残留区域对应的影响因子小于或等于对应的预设阈值，因此可以触发正常的指纹识别结果。从而可以保证正常的指纹识别过程。
实施例二
针对上述步骤S12进行如下说明：
一种可实现方式：终端设备确定N帧指纹图像中对应位置像素值相同的像素点，所谓对应位置是指将N帧指纹图像放在同一坐标系下，N帧图像的四个角像素点对齐，所谓四个角像素点包括：左上角像素点、左下角像素点、右上角像素点和右下角像素点。基于此，每帧指纹图像中的某一个像素点均在其他N‐1帧指纹图像中存在对应的像素点，例如：N帧指纹图像中的中心点均是相互对应的。在终端设备确定N帧指纹图像中对应位置像素值相同的像素点之后，终端设备确定这些像素点所构成的至少一个连通区域，需要说明的是，连通区域之间是不连通的。如果所述至少一个连通区域的面积总和大于第一预设面积时，终端设备确定所述至少一个连通区域为固定残留区域。
另一种可实现方式：图2为本发明另一实施例提供的指纹识别方法的流程图，如图2所示，上述步骤S12包括：
步骤S121：终端设备对N帧指纹图像分别进行二值化处理，得到N组第一二值化图像，每组第一二值化图像包括第一黑色二值化图像和第一白色二值化图像。
步骤S122：终端设备对N帧第一黑色二值化图像中的各像素点的像素值进行与操作，得到第二黑色二值化图像，并对N帧所述第一白色二值化图像中的各像素点的像素值进行与操作，得到第二白色二值化图像。
步骤S123：终端设备对第二黑色二值化图像中的各像素点的像素值和第二白色二值化图像中对应的各像素点的像素值进行或操作，得到第二二值化图像。
步骤S124：若所述第二二值化图像中包括满足预设条件的至少一个连通区域，则终端设备确定N帧指纹图像存在固定残留区域，其中固定残留区域由所述至少一个连通区域组成。其中，预设条件为所述至少一个连通区域的面积总和大于第一预设面积。
针对步骤S121进行说明：
针对第i帧指纹图像中的任一个像素点(x,y)，i＝1,2…N，确定以该像素点(x,y)为中心，大小为Wi*Wi的邻域窗口，根据该邻域窗口对该像素点进行二值化。例如：针对像素点(x,y)，其在对应的第一白色二值化图像B wi的二值化 像素值为：
Figure PCTCN2018105188-appb-000001
像素点(x,y)，其在第一黑色二值化图像B bi的二值化像素值为：
B bi(x,y)＝255-B wi(x,y)
其中，A(x,y)表示像素点(x,y)的灰度像素值，M为所述邻域窗口中的所有像素点的灰度像素值的统计值，包括但不限于均值、中值、最大类间方差值等，本发明实施例对此不做限制。
需要说明的是，上述邻域窗口为矩形窗口，实际上，该邻域窗口还可以是圆形、其他多边形等，本发明实施例对此不做限制。
可选地，在步骤S122之前还包括：终端设备删除所述第一黑色二值化图像中面积小于第二预设面积的连通区域，并删除所述第一白色二值化图像中面积小于第三预设面积的连通区域。该第二预设面积可以和第三预设面积相同，也可以不同。
例如：图3A为本发明一实施例提供的原始的第一黑色二值化图像的示意图，图3B为本发明一实施例提供的删除之后的第一黑色二值化图像的示意图，如图3A所示，原始的第一黑色二值化图像包括：六个连通区域，分别为连通区域1至连通区域6，假设连通区域1、连通区域5和连通区域6的面积均小于第二预设面积，这种情况下，终端设备可以删除连通区域1、连通区域5和连通区域6。删除之后的第一黑色二值化图像如图3B所示，仅剩下连通区域2、连通区域3和连通区域4。
对于第一白色二值化图像的删除方法与对第一黑色二值化图像的删除方法相同，本发明实施例对此不再赘述。
针对步骤S122和步骤S123进行说明：
图4A为本发明一实施例提供的N帧第一黑色二值化图像的存储方式的示意图，如图4A所示，N帧第一黑色二值化图像按照队列40A存储，最后一帧第一黑色二值化图像位于队尾，当最后一帧第一黑色二值化图像进入该队列时，最后一帧第一黑色二值化图像之前的第N帧第一黑色二值化图像出队，以保证该队列中存在N帧第一黑色二值化图像。需要说明的是，当该队列中的第一黑色二值化图像的数量不足N帧时，例如：该队列中的第一黑色二值化图像的数量为N‐1，可以对N‐1帧第一黑色二值化图像进行类似于步骤S122 的方法，也可以不做任何操作。
图4B为本发明一实施例提供的N帧第一白色二值化图像的存储方式的示意图，如图4B所示，N帧第一白色二值化图像按照队列40B存储，最后一帧第一白色二值化图像位于队尾，当最后一帧第一白色二值化图像进入该队列时，最后一帧第一白色二值化图像之前的第N帧第一白色二值化图像出队，以保证该队列中存在N帧第一白色二值化图像。需要说明的是，当该队列中的第一白色二值化图像的数量不足N帧时，例如：该队列中的第一白色二值化图像的数量为N‐1，可以对N‐1帧第一白色二值化图像进行类似于步骤S122的方法，也可以不做任何操作。
终端设备对N帧第一黑色二值化图像中的各像素点的像素值进行与操作，得到第二黑色二值化图像。具体地，B bc＝B b1&B b2…B bN，其中B bc为第二黑色二值化图像。&表示与操作。
终端设备对N帧第一白色二值化图像中的各像素点的像素值进行与操作，得到第二白色二值化图像。具体地，B wc＝B w1&B w2…B wN，其中B wc为第二白色二值化图像。&表示与操作。
可选地，在步骤S123之前还包括：终端设备删除所述第二黑色二值化图像中面积小于第四预设面积的连通区域，并删除所述第二白色二值化图像中面积小于第三预设面积的连通区域。该第四预设面积可以和第四预设面积相同，也可以不同。
需要说明的是，终端设备删除所述第二黑色二值化图像中面积小于第四预设面积的连通区域，并删除所述第二白色二值化图像中面积小于第三预设面积的连通区域的方法，与终端设备删除所述第一黑色二值化图像中面积小于第二预设面积的连通区域，并删除所述第一白色二值化图像中面积小于第三预设面积的连通区域的方法类似，本发明实施例对此不再赘述。
在终端设备确定了第二黑色二值化图像和第二白色二值化图像之后，终端设备对第二黑色二值化图像中的各像素点的像素值和第二白色二值化图像中对应的各像素点的像素值进行或操作，得到第二二值化图像。具体地，B mask＝B wc|B bc，其中B mask表示第二二值化图像，|表示或操作。
在步骤S124中，所述第一预设面积可以根据实际情况设置，本发明实施例对此不做限制。
在本发明实施例中，提供了两种确定固定残留区域的方法，通过两种方法均能准确的确定固定残留区域。其中，本发明实施例中的N越大，则确定的固定残留区域越准确。
步骤S13可以通过以下实施例三或实施例四实现：
实施例三
在实施例一或实施例二的基础上，图5为本发明再一实施例提供的指纹识别方法的流程图，如图5所示，上述步骤S13包括：
步骤S131a：若N帧指纹图像存在固定残留区域，则终端设备获取最后一帧指纹图像对应的几何变换矢量信息。
步骤S132a：终端设备将第二二值化图像作为残留纹路模板和残留纹路样本。
步骤S133a：终端设备根据几何变换矢量信息调整残留纹路模板和残留纹路样本的相对位置。
步骤S134a：终端设备计算经过相对位置调整之后的残留纹路模板和残留纹路样本的相似度，并将相似度作为一个影响因子。
针对步骤S131a至步骤S133a进行说明：
可选地，终端设备可以根据最后一帧指纹图像和已存在的指纹图像模板，得到最后一帧指纹图像对应的几何变换矢量信息H。其中，该指纹图像模板可以完全是合法用户指纹所形成的指纹图像模板，也有可能是混有残留纹路的合法用户指纹图像模板。其中，如何生成几何变换矢量信息H可以采用现有技术的方式，该几何变换矢量信息H用于调整残留纹路模板和残留纹路样本的相对位置。
或者，几何变换矢量信息为预设的几何变换矢量信息，只要它能调整残留纹路模板和残留纹路样本的相对位置即可，本发明实施例对此不做限制。
为了区别残留纹路模板和残留纹路样本，可以将残留纹路模板记为T，将残留纹路样本记为S。
进一步地，终端设备根据几何变换矢量信息调整残留纹路模板和残留纹路样本的相对位置的方式可以采用现有技术，本发明实施例对此不做限制。
其中，通常调整残留纹路模板和残留纹路样本的相对位置的方式是：保持残留纹路模板的位置不变，调整残留纹路样本的位置，或者，保持残留纹 路样本的位置不变，调整残留纹路模板的位置。
所谓残留纹路模板和残留纹路样本的相对位置包括以下至少一项：残留纹路模板和残留纹路样本的相对位移、相对旋转角度、尺度拉升等。
图6A至图6C为本发明一实施例提供的残留纹路模板和残留纹路样本的示意图，如图6A所示，残留纹路模板和残留纹路样本发生了水平方向上的相对位移与对称变化。如图6B所示，残留纹路模板和残留纹路样本发生了水平和竖直方向上的相对位移和180°旋转。如图6C所示，残留纹路模板和残留纹路样本发生了相对旋转。进一步地，在本发明实施例中，如果最后一帧指纹图像相对于残留纹路模板发生了平移、旋转、对称、缩放、错切、非线性变形及其复合等时，本发明实施例所提供的方法依然适用这种场景，比如：图6A所示的，假设最后一帧指纹图像和所述残留纹路样本相同，其相对于残留纹路模板发生了平移和对称变化，但是依据本发明实施例提供的方法确定的影响因子会大于对应的预设阈值，从而使得残留纹路模板无法触发正常的指纹识别结果。
需要说明的是，在步骤S132a中，终端设备将第二二值化图像作为残留纹路模板和残留纹路样本。实际上，终端设备还可以仅将第二二值化图像作为残留纹路样本，而在计算影响因子时采用的残留纹路模板可以是上述指纹图像模板的第二二值化图像，本发明实施例对此不做限制。
针对步骤S134a进行说明：可选地，终端设备确定经过相对位置调整之后的残留纹路模板和残留纹路样本的重叠区域；确定第一集合、第二集合和第三集合，并确定所述第一集合中的元素更占所述第一集合、所述第二集合和所述第三集合中的总元素的比例，将所述比例作为所述相似度；其中，所述第一集合中的每个元素位于所述重叠区域中，且该元素在经过相对位置调整之后的残留纹路模板中是白色像素点，在经过相对位置调整之后的残留纹路样本中的黑色像素点；所述第二集合中的每个元素位于所述重叠区域中，且该元素在经过相对位置调整之后的残留纹路模板中是黑色像素点，在经过相对位置调整之后的残留纹路样本中的白色像素点；所述第三集合中的每个元素位于所述重叠区域中，且该元素在经过相对位置调整之后的残留纹路模板中是白色像素点，在经过相对位置调整之后的残留纹路样本中的白色像素点。
具体地，图7为本发明一实施例提供的第一集合、第二集合、第三集合以及重叠区域的示意图，如图7所示，虚线圈中的区域为重叠区域O，第一集合用O 01表示，第二集合用O 10表示，第三集合用O 11表示。
O 01＝{(x,y)|S(x,y)＝255&&T(x,y)＝0&&(x,y)∈O}
O 10＝{(x,y)|S(x,y)＝0&&T(x,y)＝255&&(x,y)∈O}
O 11＝{(x,y)|S(x,y)＝255&&T(x,y)＝255&&(x,y)∈O}
其中，&&表示并且的意思。
相似度
Figure PCTCN2018105188-appb-000002
L()表示求个数。
在本发明实施例中，提供了如何确定固定残留区域对N帧指纹图像中的最后一帧指纹图像引起的指纹识别过程的至少一个影响因子的方法，通过该方法可以有效的确定影响因子。
实施例四
在实施例一、实施例二或实施例三的基础上，图8为本发明又一实施例提供的指纹识别方法的流程图，如图8所示，上述步骤S13包括：
步骤S131b：若N帧指纹图像存在固定残留区域，则终端设备确定最后一帧指纹图像中满足几何变换矢量信息约束的特征点所构成的特征点集合。
步骤S132b：终端设备计算特征点集合中落入第二白色二值化图像的特征点比例，并将所述比例作为一个所述影响因子。
可选地，几何变换矢量信息包括以下至少一项：平移、旋转、缩放、对称、错切和非线性变性信息。
如上所述，终端设备确定最后一帧指纹图像中满足几何变换矢量信息约束的特征点所构成的特征点集合K。
其中，特征点集合中落入第二白色二值化图像的特征点比例
Figure PCTCN2018105188-appb-000003
∩表示取交集，＝＝表示恒等于。
值得一提的是，实施例四和实施例三可以结合，即固定残留区域对N帧指纹图像中的最后一帧指纹图像引起的指纹识别过程的至少一个影响因子包括：实施例三中所确定的影响因子，以及，实施例四中所确定的影响因子。其中，实施例三中所确定的影响因子对应的预设阈值和实施例四所确定的影响因子对应的预设阈值可以相同，也可以不同，本发明实施例对此不做限制。
在本发明实施例中，提供了如何确定固定残留区域对N帧指纹图像中的最后一帧指纹图像引起的指纹识别过程的至少一个影响因子的方法，通过该方法可以有效的确定影响因子。
实施例五
图9为本发明一实施例提供的一种指纹识别装置的结构示意图，其中该装置可以是终端设备的部分或全部，例如：该装置可以是终端设备或者终端设备中的处理器，可选地，该终端设备可以是手机、PAD、笔记本电脑等具有指纹识别功能的终端，本发明实施例对此不做限定。如图9所示，该装置包括：
获取模块91，用于获取N帧指纹图像，N为大于1的整数。
判断模块92，用于判断所述N帧指纹图像是否存在固定残留区域。
第一确定模块93，用于若所述N帧指纹图像存在固定残留区域，则确定所述固定残留区域对指纹识别过程的至少一个影响因子。
第二确定模块94，用于若所述至少一个影响因子大于各自对应的预设阈值，则确定所述N帧指纹图像中的最后一帧指纹图像无法触发正常的指纹识别结果，其中，所述最后一帧指纹图像为当前采集到的指纹图像。
可选地，判断模块92具体用于：对所述N帧指纹图像分别进行二值化处理，得到N组第一二值化图像，每组所述第一二值化图像包括第一黑色二值化图像和第一白色二值化图像；对N帧所述第一黑色二值化图像中的各像素点的像素值进行与操作，得到第二黑色二值化图像，并对N帧所述第一白色二值化图像中的各像素点的像素值进行与操作，得到第二白色二值化图像；对所述第二黑色二值化图像中的各像素点的像素值和所述第二白色二值化图像中对应的各像素点的像素值进行或操作，得到第二二值化图像；若所述第二二值化图像中包括满足预设条件的至少一个连通区域，则确定所述N帧指纹图像存在所述固定残留区域，其中所述固定残留区域由所述至少一个连通区域组成；其中，所述预设条件为所述至少一个连通区域的面积总和大于第一预设面积。
可选地，该装置还包括：第一删除模块95，用于在对N帧所述第一黑色二值化图像中的各像素点的像素值进行与操作，得到第二黑色二值化图像，并对N帧所述第一白色二值化图像中的各像素点的像素值进行与操作，得到 第二白色二值化图像之前，删除所述第一黑色二值化图像中面积小于第二预设面积的连通区域，并删除所述第一白色二值化图像中面积小于第三预设面积的连通区域。
可选地，该装置还包括：第二删除模块96，用于在对所述第二黑色二值化图像中的各像素点的像素值和所述第二白色二值化图像中对应的各像素点的像素值进行或操作，得到第二二值化图像之前，删除所述第二黑色二值化图像中面积小于第四预设面积的连通区域，并删除所述第二白色二值化图像中面积小于第三预设面积的连通区域。
可选地，第一确定模块93具体用于：获取所述最后一帧指纹图像对应的几何变换矢量信息；将所述第二二值化图像作为残留纹路模板和残留纹路样本；根据所述几何变换矢量信息调整所述残留纹路模板和所述残留纹路样本的相对位置；计算经过相对位置调整之后的残留纹路模板和残留纹路样本的相似度，并将所述相似度作为一个所述影响因子。
可选地，第一确定模块93具体用于：确定经过相对位置调整之后的残留纹路模板和残留纹路样本的重叠区域；确定第一集合、第二集合和第三集合，并确定所述第一集合中的元素占所述第一集合、所述第二集合和所述第三集合中的总元素的比例，将所述比例作为所述相似度；其中，所述第一集合中的每个元素位于所述重叠区域中，且该元素在经过相对位置调整之后的残留纹路模板中是白色像素点，在经过相对位置调整之后的残留纹路样本中的黑色像素点；所述第二集合中的每个元素位于所述重叠区域中，且该元素在经过相对位置调整之后的残留纹路模板中是黑色像素点，在经过相对位置调整之后的残留纹路样本中的白色像素点；所述第三集合中的每个元素位于所述重叠区域中，且该元素在经过相对位置调整之后的残留纹路模板中是白色像素点，在经过相对位置调整之后的残留纹路样本中的白色像素点。
可选地，第一确定模块93具体用于：根据所述最后一帧指纹图像和已存在的指纹图像模板，得到所述最后一帧指纹图像对应的几何变换矢量信息。
可选地，第二确定模块94具体用于：确定所述最后一帧指纹图像中的特征点；计算所述第二二值化图像中白色像素点占所述特征点的比例，并将所述比例作为一个所述影响因子。
本发明实施例提供的指纹识别装置可用于执行上述的指纹识别方法，其 内容和效果可参照上述方法部分，本发明实施例对此不再赘述。
实施例六
图10为本发明一实施例提供的一种终端设备的结构示意图，该终端设备可以是手机、PAD、笔记本电脑等具有指纹识别功能的终端，本发明实施例对此不做限定。如图10所示，该设备包括：处理器101、收发器102和存储器103，其中收发器102用于实现与其他设备之间的通信，存储器103用于存储所述处理器101的执行指令，以使处理器101实现上述的指纹识别方法，其内容和效果可参考上述方法部分，本发明实施例对此不再赘述。
实施例七
本发明实施例还提供一种计算机存储介质，所述存储介质包括计算机指令，当所述指令被计算机执行时，使得所述计算机实现如上述的指纹识别方法。其内容和效果可参考上述方法部分，本发明实施例对此不再赘述。
实施例八
本发明实施例还提供一种计算机程序产品，包括计算机指令，当所述指令被计算机执行时，使得所述计算机实现如上述的指纹识别方法。其内容和效果可参考上述方法部分，本发明实施例对此不再赘述。
本领域普通技术人员可以理解：实现上述各方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成。前述的程序可以存储于一计算机可读取存储介质中。该程序在执行时，执行包括上述各方法实施例的步骤；而前述的存储介质包括：ROM、RAM、磁碟或者光盘等各种可以存储程序代码的介质。
最后应说明的是：以上各实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述各实施例对本发明进行了详细的说明，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，或者对其中部分或者全部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发明各实施例技术方案的范围。

Claims (18)

  1. 一种指纹识别方法，其特征在于，包括：
    获取N帧指纹图像，N为大于1的整数；
    判断所述N帧指纹图像是否存在固定残留区域；
    若所述N帧指纹图像存在固定残留区域，则确定所述固定残留区域对所述N帧指纹图像中的最后一帧指纹图像引起的指纹识别过程的至少一个影响因子；
    若所述至少一个影响因子大于各自对应的预设阈值，则确定所述最后一帧指纹图像无法触发正常的指纹识别结果，其中，所述最后一帧指纹图像为当前采集到的指纹图像。
  2. 根据权利要求1所述的方法，其特征在于，所述判断所述N帧指纹图像是否存在固定残留区域，包括：
    对所述N帧指纹图像分别进行二值化处理，得到N组第一二值化图像，每组所述第一二值化图像包括第一黑色二值化图像和第一白色二值化图像；
    对N帧所述第一黑色二值化图像中的各像素点的像素值进行与操作，得到第二黑色二值化图像，并对N帧所述第一白色二值化图像中的各像素点的像素值进行与操作，得到第二白色二值化图像；
    对所述第二黑色二值化图像中的各像素点的像素值和所述第二白色二值化图像中对应的各像素点的像素值进行或操作，得到第二二值化图像；
    若所述第二二值化图像中包括满足预设条件的至少一个连通区域，则确定所述N帧指纹图像存在所述固定残留区域，其中所述固定残留区域由所述至少一个连通区域组成；
    其中，所述预设条件为所述至少一个连通区域的面积总和大于第一预设面积。
  3. 根据权利要求2所述的方法，其特征在于，所述对N帧所述第一黑色二值化图像中的各像素点的像素值进行与操作，得到第二黑色二值化图像，并对N帧所述第一白色二值化图像中的各像素点的像素值进行与操作，得到第二白色二值化图像之前，还包括：
    删除所述第一黑色二值化图像中面积小于第二预设面积的连通区域，并删除所述第一白色二值化图像中面积小于第三预设面积的连通区域。
  4. 根据权利要求2所述的方法，其特征在于，所述对所述第二黑色二值化图像中的各像素点的像素值和所述第二白色二值化图像中对应的各像素点的像素值进行或操作，得到第二二值化图像之前，还包括：
    删除所述第二黑色二值化图像中面积小于第四预设面积的连通区域，并删除所述第二白色二值化图像中面积小于第三预设面积的连通区域。
  5. 根据权利要求2所述的方法，其特征在于，所述确定所述固定残留区域对所述N帧指纹图像中的最后一帧指纹图像引起的指纹识别过程的至少一个影响因子，包括：
    获取所述最后一帧指纹图像对应的几何变换矢量信息；
    将所述第二二值化图像作为残留纹路模板和残留纹路样本；
    根据所述几何变换矢量信息调整所述残留纹路模板和所述残留纹路样本的相对位置；
    计算经过相对位置调整之后的残留纹路模板和残留纹路样本的相似度，并将所述相似度作为一个所述影响因子。
  6. 根据权利要求5所述的方法，其特征在于，所述计算经过相对位置调整之后的残留纹路模板和残留纹路样本的相似度，包括：
    确定经过相对位置调整之后的残留纹路模板和残留纹路样本的重叠区域；
    确定第一集合、第二集合和第三集合，并确定所述第一集合中的元素占所述第一集合、所述第二集合和所述第三集合中的总元素的比例，将所述比例作为所述相似度；
    其中，所述第一集合中的每个元素位于所述重叠区域中，且该元素在经过相对位置调整之后的残留纹路模板中是白色像素点，在经过相对位置调整之后的残留纹路样本中的黑色像素点；所述第二集合中的每个元素位于所述重叠区域中，且该元素在经过相对位置调整之后的残留纹路模板中是黑色像素点，在经过相对位置调整之后的残留纹路样本中的白色像素点；所述第三集合中的每个元素位于所述重叠区域中，且该元素在经过相对位置调整之后的残留纹路模板中是白色像素点，在经过相对位置调整之后的残留纹路样本中的白色像素点。
  7. 根据权利要求5所述的方法，其特征在于，所述获取所述最后一帧指纹图像对应的几何变换矢量信息，包括：
    根据所述最后一帧指纹图像和已存在的指纹图像模板，得到所述最后一帧指纹图像对应的几何变换矢量信息。
  8. 根据权利要求2‐7任一项所述的方法，其特征在于，所述确定所述固定残留区域对所述N帧指纹图像中的最后一帧指纹图像引起的指纹识别过程的至少一个影响因子，包括：
    确定所述最后一帧指纹图像中满足几何变换矢量信息约束的特征点所构成的特征点集合；
    计算所述特征点集合中落入所述第二白色二值化图像的特征点比例，并将所述比例作为一个所述影响因子。
  9. 一种终端设备，其特征在于，包括：
    处理器和用于存储所述处理器的执行指令的存储器，以使所述处理器用于：
    获取N帧指纹图像，N为大于1的整数；
    判断所述N帧指纹图像是否存在固定残留区域；
    若所述N帧指纹图像存在固定残留区域，则确定所述固定残留区域对所述N帧指纹图像中的最后一帧指纹图像引起的指纹识别过程的至少一个影响因子；
    若所述至少一个影响因子大于各自对应的预设阈值，则确定所述最后一帧指纹图像无法触发正常的指纹识别结果，其中，所述最后一帧指纹图像为当前采集到的指纹图像。
  10. 根据权利要求9所述的设备，其特征在于，所述处理器具体用于：
    对所述N帧指纹图像分别进行二值化处理，得到N组第一二值化图像，每组所述第一二值化图像包括第一黑色二值化图像和第一白色二值化图像；
    对N帧所述第一黑色二值化图像中的各像素点的像素值进行与操作，得到第二黑色二值化图像，并对N帧所述第一白色二值化图像中的各像素点的像素值进行与操作，得到第二白色二值化图像；
    对所述第二黑色二值化图像中的各像素点的像素值和所述第二白色二值化图像中对应的各像素点的像素值进行或操作，得到第二二值化图像；
    若所述第二二值化图像中包括满足预设条件的至少一个连通区域，则确定所述N帧指纹图像存在所述固定残留区域，其中所述固定残留区域由所述 至少一个连通区域组成；
    其中，所述预设条件为所述至少一个连通区域的面积总和大于第一预设面积。
  11. 根据权利要求10所述的设备，其特征在于，所述处理器还用于：
    在对N帧所述第一黑色二值化图像中的各像素点的像素值进行与操作，得到第二黑色二值化图像，并对N帧所述第一白色二值化图像中的各像素点的像素值进行与操作，得到第二白色二值化图像之前，删除所述第一黑色二值化图像中面积小于第二预设面积的连通区域，并删除所述第一白色二值化图像中面积小于第三预设面积的连通区域。
  12. 根据权利要求10所述的设备，其特征在于，所述处理器还用于：
    在对所述第二黑色二值化图像中的各像素点的像素值和所述第二白色二值化图像中对应的各像素点的像素值进行或操作，得到第二二值化图像之前，删除所述第二黑色二值化图像中面积小于第四预设面积的连通区域，并删除所述第二白色二值化图像中面积小于第三预设面积的连通区域。
  13. 根据权利要求10所述的设备，其特征在于，所述处理器具体用于：
    获取所述最后一帧指纹图像对应的几何变换矢量信息；
    将所述第二二值化图像作为残留纹路模板和残留纹路样本；
    根据所述几何变换矢量信息调整所述残留纹路模板和所述残留纹路样本的相对位置；
    计算经过相对位置调整之后的残留纹路模板和残留纹路样本的相似度，并将所述相似度作为一个所述影响因子。
  14. 根据权利要求13所述的设备，其特征在于，所述处理器具体用于：
    确定经过相对位置调整之后的残留纹路模板和残留纹路样本的重叠区域；
    确定第一集合、第二集合和第三集合，并确定所述第一集合中的元素占所述第一集合、所述第二集合和所述第三集合中的总元素的比例，将所述比例作为所述相似度；
    其中，所述第一集合中的每个元素位于所述重叠区域中，且该元素在经过相对位置调整之后的残留纹路模板中是白色像素点，在经过相对位置调整之后的残留纹路样本中的黑色像素点；所述第二集合中的每个元素位于所述重叠区域中，且该元素在经过相对位置调整之后的残留纹路模板中是黑色像 素点，在经过相对位置调整之后的残留纹路样本中的白色像素点；所述第三集合中的每个元素位于所述重叠区域中，且该元素在经过相对位置调整之后的残留纹路模板中是白色像素点，在经过相对位置调整之后的残留纹路样本中的白色像素点。
  15. 根据权利要求13所述的设备，其特征在于，所述处理器具体用于：
    根据所述最后一帧指纹图像和已存在的指纹图像模板，得到所述最后一帧指纹图像对应的几何变换矢量信息。
  16. 根据权利要求10‐15任一项所述的设备，其特征在于，所述处理器具体用于：
    确定所述最后一帧指纹图像中满足几何变换矢量信息约束的特征点所构成的特征点集合；
    计算所述特征点集合中落入所述第二白色二值化图像的特征点比例，并将所述比例作为一个所述影响因子。
  17. 一种指纹识别装置，其特征在于，包括：
    获取模块，用于获取N帧指纹图像，N为大于1的整数；
    判断模块，用于判断所述N帧指纹图像是否存在固定残留区域；
    第一确定模块，用于若所述N帧指纹图像存在固定残留区域，则确定所述固定残留区域对指纹识别过程的至少一个影响因子；
    第二确定模块，用于若所述至少一个影响因子大于各自对应的预设阈值，则确定所述N帧指纹图像中的最后一帧指纹图像无法触发正常的指纹识别结果，其中，所述最后一帧指纹图像为当前采集到的指纹图像。
  18. 一种计算机存储介质，其特征在于，所述存储介质包括计算机指令，当所述指令被计算机执行时，使得所述计算机实现如权利要求1至8中任一项权利要求所述的方法。
PCT/CN2018/105188 2018-09-12 2018-09-12 指纹识别方法、装置、设备及存储介质 Ceased WO2020051792A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2018/105188 WO2020051792A1 (zh) 2018-09-12 2018-09-12 指纹识别方法、装置、设备及存储介质
CN201880001576.6A CN109313705B (zh) 2018-09-12 2018-09-12 指纹识别方法、装置、设备及存储介质

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2018/105188 WO2020051792A1 (zh) 2018-09-12 2018-09-12 指纹识别方法、装置、设备及存储介质

Publications (1)

Publication Number Publication Date
WO2020051792A1 true WO2020051792A1 (zh) 2020-03-19

Family

ID=65221685

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/105188 Ceased WO2020051792A1 (zh) 2018-09-12 2018-09-12 指纹识别方法、装置、设备及存储介质

Country Status (2)

Country Link
CN (1) CN109313705B (zh)
WO (1) WO2020051792A1 (zh)

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109977883B (zh) 2019-03-29 2021-05-18 联想(北京)有限公司 指纹采集方法及电子设备
CN110110697B (zh) * 2019-05-17 2021-03-12 山东省计算中心（国家超级计算济南中心） 基于方向矫正的多指纹分割提取方法、系统、设备及介质
CN111242111B (zh) * 2020-04-29 2020-09-25 深圳市汇顶科技股份有限公司 指纹识别方法、装置和电子设备
CN117649684A (zh) * 2022-09-02 2024-03-05 荣耀终端有限公司 指纹识别方法和电子设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101833649A (zh) * 2009-03-09 2010-09-15 杭州晟元芯片技术有限公司 一种指纹残留甄别方法
CN102208021A (zh) * 2011-07-21 2011-10-05 中国人民解放军国防科学技术大学 一种指纹图像分割方法
CN107368816A (zh) * 2017-07-26 2017-11-21 北京集创北方科技股份有限公司 生物特征识别方法、生物特征识别装置和检测系统
CN107408208A (zh) * 2016-02-02 2017-11-28 指纹卡有限公司 用于对用户的生物测量进行分析的方法和指纹感测系统

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1238809C (zh) * 2002-09-04 2006-01-25 长春鸿达光电子与生物统计识别技术有限公司 指纹识别方法、以及指纹控制方法和系统
CN105095719B (zh) * 2015-08-05 2017-12-12 刘奇 一种指纹解锁方法及其系统和具有该系统的电子设备
SE1551641A1 (en) * 2015-12-14 2017-06-15 Fingerprint Cards Ab Method and fingerprint sensing system for acquiring a fingerprint image
CN105631443B (zh) * 2016-03-11 2019-03-22 Oppo广东移动通信有限公司 指纹模板的更新方法及终端设备
CN105956553B (zh) * 2016-04-28 2019-12-06 Oppo广东移动通信有限公司 一种解锁方法及移动终端
CN106022072B (zh) * 2016-06-03 2019-03-15 北京小米移动软件有限公司 实现指纹解锁的方法及装置、电子设备
CN106326869B (zh) * 2016-08-26 2021-01-12 Oppo广东移动通信有限公司 指纹识别方法、装置和移动终端
CN106599858B (zh) * 2016-12-20 2020-06-02 北京小米移动软件有限公司 指纹识别方法、装置和电子设备
CN106909893B (zh) * 2017-02-09 2020-12-29 北京小米移动软件有限公司 指纹识别方法及装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101833649A (zh) * 2009-03-09 2010-09-15 杭州晟元芯片技术有限公司 一种指纹残留甄别方法
CN102208021A (zh) * 2011-07-21 2011-10-05 中国人民解放军国防科学技术大学 一种指纹图像分割方法
CN107408208A (zh) * 2016-02-02 2017-11-28 指纹卡有限公司 用于对用户的生物测量进行分析的方法和指纹感测系统
CN107368816A (zh) * 2017-07-26 2017-11-21 北京集创北方科技股份有限公司 生物特征识别方法、生物特征识别装置和检测系统

Also Published As

Publication number Publication date
CN109313705A (zh) 2019-02-05
CN109313705B (zh) 2021-10-08

Similar Documents

Publication Publication Date Title
US11087407B2 (en) Systems and methods for mobile image capture and processing
US10699146B2 (en) Mobile document detection and orientation based on reference object characteristics
US9946954B2 (en) Determining distance between an object and a capture device based on captured image data
EP2883190B1 (en) Texture features for biometric authentication
CN102279926B (zh) 识别原始字符集的字符的方法与系统
CN112396050B (zh) 图像的处理方法、设备以及存储介质
CN113781406B (zh) 电子元器件的划痕检测方法、装置及计算机设备
CN109313705B (zh) 指纹识别方法、装置、设备及存储介质
CN105631449A (zh) 一种图片分割方法、装置及设备
CN108665495B (zh) 图像处理方法及装置、移动终端
CN110008943B (zh) 一种图像处理方法及装置、一种计算设备及存储介质
CN111695410A (zh) 违章举报方法、装置、计算机设备及存储介质
US10275888B2 (en) Algorithmic method for detection of documents in images
CN108205641B (zh) 手势图像处理方法及装置
WO2023028947A1 (zh) 掌静脉非接触式三维建模方法、装置及认证方法
CN108491843B (zh) 一种图像处理方法、装置及存储介质
CN117635404A (zh) 一种图像加密方法及装置

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: 18933199

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: 18933199

Country of ref document: EP

Kind code of ref document: A1