WO2016095615A1 - 指纹识别系统及指纹识别方法及电子设备 - Google Patents

指纹识别系统及指纹识别方法及电子设备 Download PDF

Info

Publication number
WO2016095615A1
WO2016095615A1 PCT/CN2015/093728 CN2015093728W WO2016095615A1 WO 2016095615 A1 WO2016095615 A1 WO 2016095615A1 CN 2015093728 W CN2015093728 W CN 2015093728W WO 2016095615 A1 WO2016095615 A1 WO 2016095615A1
Authority
WO
WIPO (PCT)
Prior art keywords
fingerprint image
image
fingerprint
current frame
image portion
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/CN2015/093728
Other languages
English (en)
French (fr)
Inventor
陈桂兰
文启永
蔡铁军
何邦君
杨云
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.)
BYD Co Ltd
Original Assignee
BYD 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 BYD Co Ltd filed Critical BYD Co Ltd
Priority to US15/537,707 priority Critical patent/US10366274B2/en
Priority to EP15869125.3A priority patent/EP3236386A4/en
Publication of WO2016095615A1 publication Critical patent/WO2016095615A1/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
    • G06V40/1365—Matching; Classification
    • 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
    • G06V40/1335—Combining adjacent partial images (e.g. slices) to create a composite input or reference pattern; Tracking a sweeping finger movement
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/117—Identification of persons
    • A61B5/1171—Identification of persons based on the shapes or appearances of their bodies or parts thereof
    • A61B5/1172—Identification of persons based on the shapes or appearances of their bodies or parts thereof using fingerprinting
    • 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
    • G06V40/13—Sensors therefor
    • G06V40/1306—Sensors therefor non-optical, e.g. ultrasonic or capacitive sensing

Definitions

  • the present invention relates to the field of fingerprint recognition, and more particularly to a fingerprint recognition system, a fingerprint recognition method, and an electronic device.
  • the area-type fingerprint sensors adopt the pressing type input method.
  • the finger When entering, the finger is pressed on the fingerprint sensor to capture the fingerprint information of the pressed part at one time, without moving the finger, but because the fingerprint scanning module has a limited area, each The area of the fingerprint detected by one press is relatively small, and generally requires multiple entries to collect relatively complete fingerprint information.
  • the fingerprint scanning module of the fingerprint sensor is now developing in a smaller and smaller direction.
  • the fingerprint information that can be obtained by each pressing is less and less. It is necessary to press the input multiple times to ensure that enough feature points are collected for the later matching, which results in the fingerprint library entry process being very cumbersome and time consuming.
  • the present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention needs to provide a fingerprint identification system and identification method and an electronic device.
  • a fingerprint identification system includes a fingerprint sensor, a judging unit and a processing unit;
  • the fingerprint sensor is configured to collect a multi-frame fingerprint image that the user slides in;
  • the determining unit is configured to determine whether the current frame fingerprint image and the previous frame fingerprint image in the multi-frame fingerprint image have a first overlapping area
  • the determining unit is further configured to remove the first overlapping area in the current frame fingerprint image and superimpose the current frame fingerprint image after the first overlapping area is removed from the previous frame fingerprint image image to form an overlay fingerprint. image;
  • the determining unit is configured to remove the first overlapping area in the fingerprint image of the previous frame and remove the first The previous frame fingerprint image after an overlapping area is superimposed with the current frame fingerprint image to form the superimposed fingerprint image;
  • the determining unit is further configured to determine whether the fingerprint image of the next frame and the superimposed fingerprint image have a second overlapping area until the determination of the multi-frame fingerprint image is completed and a template fingerprint image is obtained;
  • the fingerprint sensor is used to re-acquire the multi-frame fingerprint image that the user slides into;
  • the processing unit is configured to extract and save feature points of the template fingerprint image
  • the fingerprint sensor is further configured to collect a fingerprint image to be recognized by the user, and the processing unit is configured to extract a feature point of the fingerprint image to be identified and determine whether the feature point of the fingerprint image to be recognized and the feature point of the template fingerprint image are match;
  • the processing unit is configured to identify the fingerprint image to be identified as a matching fingerprint image, and if not, the processing unit is configured to identify the fingerprint image to be recognized as a non-matching fingerprint image.
  • the fingerprint sensor when the template fingerprint database is established, the fingerprint sensor is used to collect the multi-frame fingerprint images that the user slides into, and the judging unit uses the image stitching technology to stitch the images collected by the sliding together. Therefore, the amount of information collected by each slide input is much larger than that of the conventional method.
  • the input efficiency is much higher than the existing method, and only the fingers such as the left side, the middle side, and the right side are separately performed.
  • the recording process can be completed in one acquisition, which facilitates the entry, avoids cumbersome operations, and improves the user experience.
  • the fingerprint sensor collects the fingerprint of the pressed part, and the processing unit
  • the fingerprint can be compared with the database, and the user may have a very regular angle when registering the fingerprint, and can still successfully recognize at various angles when matching.
  • the processing unit is configured to perform image filtering processing, binarization processing, and refinement processing on the template fingerprint image to extract the feature point of the template fingerprint image.
  • the previous frame fingerprint image includes a previous frame image portion
  • the current frame fingerprint image includes a plurality of current frame image portions
  • the determining unit is configured to calculate a first gray level of the image portion of the previous frame. And gradation differences of the plurality of second gradations of the plurality of current frame image portions to obtain a plurality of gradation differences, and comparing the plurality of gradation differences;
  • the determining unit is configured to determine the one of the gradations One of the current frame image portions corresponding to the two gray levels is the first overlapping area.
  • the previous frame fingerprint image includes a previous frame image portion
  • the current frame fingerprint image includes a plurality of current frame image portion combinations
  • each current frame image portion combination includes a first current frame image portion and a second a current frame image portion and a third current frame image portion
  • the determining unit is configured to calculate the first gray level of the image portion of the previous frame and the image portion of the same current frame respectively a first gray level of the first current frame image portion, a second gray level of the second current frame image portion, and a third gray level gray difference of the third current frame image portion to respectively obtain the first gray Calculating a gray level sum value of the first gray level difference, the second gray level difference, and the third gray level difference to obtain a plurality of gray levels and values, the degree difference, the second gray level difference, and the third gray level difference, Comparing the plurality of gray levels and values;
  • the determining unit is configured to compare the first gray level difference corresponding to the one of the current frame image portion combinations, a second gray scale difference and a third gray scale difference;
  • the determining unit is configured to determine that the current frame image portion corresponding to the one of the grayscale differences of the minimum value is the first overlap region.
  • a fingerprint identification method comprising the steps of:
  • the fingerprint sensor collects a multi-frame fingerprint image that the user slides into
  • step S2 the judging unit judges whether the current frame fingerprint image and the previous frame fingerprint image in the multi-frame fingerprint image have a first overlapping area, and if yes, proceeds to step S3, otherwise returns to step S1;
  • the determining unit removes the first overlapping area in the current frame fingerprint image and superimposes the current frame fingerprint image after the first overlapping area is removed, and superimposes the previous frame fingerprint image to form a superimposed fingerprint image, or The determining unit removes the first overlapping area in the fingerprint image of the previous frame and superimposes the previous frame fingerprint image after the first overlapping area is removed, and the current frame fingerprint image is superimposed to form the superimposed fingerprint image;
  • S4 the determining unit determines whether the fingerprint image of the next frame and the superimposed fingerprint image have a second overlapping area, until the determination of the multi-frame fingerprint image is completed and a template fingerprint image is obtained;
  • S5 the processing unit extracts and saves feature points of the template fingerprint image
  • the fingerprint sensor collects an image of the fingerprint to be recognized that is pressed by the user
  • step S7 the processing unit extracts the feature point of the fingerprint image to be identified and determines whether the feature point of the fingerprint image to be identified matches the feature point of the template fingerprint image, and if yes, proceeds to step S8, otherwise proceeds to step S9;
  • S8 the processing unit identifies the fingerprint image to be identified as a matching fingerprint image
  • the processing unit identifies the fingerprint image to be identified as a non-matching fingerprint image.
  • step S5 the processing unit performs image filtering processing, binarization processing, and refinement processing on the template fingerprint image to extract the feature points of the template fingerprint image.
  • the previous frame fingerprint image includes a previous frame image portion
  • the current frame fingerprint image includes a plurality of current frame image portions
  • the determining unit calculates the first image portion of the previous frame portion.
  • the gradation is respectively different from the gradation of the plurality of second gradations of the plurality of current frame image portions to obtain a plurality of gradation differences, and the plurality of gradation differences are compared;
  • the determining unit determines one of the second ash One of the current frame image portions corresponding to the degree is the first overlapping area.
  • the previous frame fingerprint image includes a previous frame image portion
  • the current frame fingerprint image includes a plurality of current frame image portion combinations
  • each current frame image portion combination includes a first current frame.
  • the judging unit calculates a first gradation of the image portion of the previous frame and a first gradation of the first current frame image portion and a second gradation of the second current frame image portion in a combination of the same current frame image portion, respectively And a third gray level of the image portion of the third current frame to respectively obtain a first gray level difference, a second gray level difference, and a third gray level difference, and calculate the first gray level difference, the second gray level difference, and the a grayscale sum value of the third grayscale difference to obtain a plurality of grayscale sum values, and comparing the plurality of grayscale sum values;
  • the determining unit compares the first gray level difference corresponding to the one of the current frame image part combinations, and the second Gray difference and third gray difference;
  • the determining unit determines that the current frame image portion corresponding to the gradation difference of the minimum value is the first overlapping region.
  • An electronic device includes a fingerprint identification system, the fingerprint identification system including a fingerprint sensor, a determining unit, and a processing unit;
  • the fingerprint sensor is configured to collect a multi-frame fingerprint image that the user slides in;
  • the determining unit is configured to determine whether the current frame fingerprint image and the previous frame fingerprint image in the multi-frame fingerprint image have a first overlapping area
  • the determining unit is further configured to remove the first overlapping area in the current frame fingerprint image and superimpose the current frame fingerprint image after the first overlapping area is overlapped with the previous frame fingerprint image to form a superimposed fingerprint image.
  • the determining unit is configured to remove the first overlapping area in the fingerprint image of the previous frame and superimpose the previous frame fingerprint image after removing the first overlapping area and the current frame fingerprint image to form the superimposed fingerprint image.
  • the determining unit is further configured to determine whether the fingerprint image of the next frame and the superimposed fingerprint image have a second overlapping area until the determination of the multi-frame fingerprint image is completed and obtain a template fingerprint image;
  • the processing unit is configured to extract and save feature points of the template fingerprint image
  • the fingerprint sensor is used to re-acquire the multi-frame fingerprint image that the user slides into;
  • the fingerprint sensor is further configured to collect an image of the fingerprint to be recognized that is pressed by the user;
  • the processing unit is configured to extract a feature point of the fingerprint image to be identified and determine whether a feature point of the fingerprint image to be identified matches a feature point of the template fingerprint image;
  • the processing unit is configured to identify the fingerprint image to be identified as a matching fingerprint image, and if not, the processing unit is configured to identify the fingerprint image to be recognized as a non-matching fingerprint image.
  • the processing unit is configured to perform image filtering processing, binarization processing, and refinement processing on the template fingerprint image to extract the feature point of the template fingerprint image.
  • the previous frame fingerprint image includes a previous frame image portion
  • the current frame fingerprint image includes a plurality of current frame image portions
  • the determining unit is configured to calculate a first gray level of the image portion of the previous frame. And gradation differences of the plurality of second gradations of the plurality of current frame image portions to obtain a plurality of gradation differences, and comparing the plurality of gradation differences;
  • the determining unit is configured to determine the one of the gradations One of the current frame image portions corresponding to the two gray levels is the first overlapping area.
  • the previous frame fingerprint image includes a previous frame image portion
  • the current frame fingerprint image includes a plurality of current frame image portion combinations
  • each current frame image portion combination includes a first current frame image portion and a second a current frame image portion and a third current frame image portion
  • the determining unit is configured to calculate a first gray level of the image portion of the previous frame and a first gray level of the first current frame image portion and a second portion of the second current frame image portion respectively in the same current frame image portion combination
  • the gray level and the gray level difference of the third gray level of the image portion of the third current frame are respectively corresponding to the first gray level difference, the second gray level difference, and the third gray level difference, and the first gray level difference is calculated.
  • a gray scale sum value of the second gray scale difference and the third gray scale difference to obtain a plurality of gray scale sum values, and comparing the plurality of gray scale sum values;
  • the determining unit is configured to compare the first gray level difference corresponding to the one of the current frame image portion combinations, a second gray scale difference and a third gray scale difference;
  • the determining unit is configured to determine that the current frame image portion corresponding to the one of the grayscale differences of the minimum value is the first overlap region.
  • FIG. 1 is a block diagram of a fingerprint identification system of a preferred embodiment.
  • FIG. 2 is a schematic diagram of a user entering a finger print on a fingerprint sensor.
  • FIG. 3 is a schematic diagram of a user entering a fingerprint of a different position of a finger on a fingerprint sensor.
  • FIG. 4 is a schematic diagram of the principle of a fingerprint identification system in accordance with a preferred embodiment of the present invention.
  • FIG. 5 is another schematic diagram of a fingerprint identification system according to a preferred embodiment of the present invention.
  • FIG. 6 is a schematic flow chart of a fingerprint identification method according to a preferred embodiment of the present invention.
  • FIG. 7 is a schematic structural diagram of an electronic device according to a preferred embodiment of the present invention.
  • first and second are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated.
  • features defining “first” or “second” may include one or more of the described features either explicitly or implicitly.
  • the meaning of "a plurality" is two or more unless specifically and specifically defined otherwise.
  • connection In the description of the present invention, it should be noted that the terms “installation”, “connected”, and “connected” are to be understood broadly, and may be fixed or detachable, for example, unless otherwise explicitly defined and defined. Connected, or integrally connected; may be mechanically connected, or may be electrically connected or may communicate with each other; may be directly connected or indirectly connected through an intermediate medium, may be internal communication of two elements or interaction of two elements relationship. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood on a case-by-case basis.
  • a fingerprint recognition system 10 includes a fingerprint sensor 102 , a determination unit 104 , and a processing unit 106 .
  • the fingerprint sensor 102 is configured to collect a multi-frame fingerprint image that the user slides in.
  • the fingerprint sensor 102 can be, for example, a planar capacitive fingerprint sensor having a size of about 4*8 mm, 508 dpi, and a resolution of 80*160.
  • the multi-frame fingerprint image is input by the user through a sliding input mode. Referring to FIG. 2, if the user slides the finger 100 through the detection panel of the fingerprint sensor 102, the fingerprint sensor 102 can collect the sliding fingerprint image sequence of many frame fingers at a time. .
  • the determining unit 104 is configured to determine whether the current frame fingerprint image and the previous frame fingerprint image in the multi-frame fingerprint image have a first overlapping area, and if so, the determining unit 102 is further configured to: in the current frame fingerprint image An overlapping area is removed and the current frame fingerprint image after the first overlapping area is removed is superimposed with the previous frame fingerprint image to form a superimposed fingerprint image. If not, the fingerprint sensor 102 is configured to reacquire the multi-frame of the user sliding input. The fingerprinting unit is further configured to determine whether the fingerprint image of the next frame and the superimposed fingerprint image have a second overlapping area until the determination of the multi-frame fingerprint image is completed and a template fingerprint image is obtained.
  • the determining unit 104 is further configured to remove the first overlapping area in the fingerprint image of the previous frame and remove the previous frame fingerprint image and the current frame fingerprint after the first overlapping area is removed. Image overlays form a superimposed fingerprint image.
  • the fingerprint sensor 102 Since the fingerprint sensor 102 has a small area and a large fingerprint area, the fingerprint sensor 102 collects a fingerprint image of one frame and one frame when the fingerprint is collected. When two adjacent frames of the fingerprint image have a part of the same area, the determining unit 104 can Splicing together into another frame of fingerprint image. Therefore, referring to FIG. 3, the user slides the left, middle, and right sides of the finger 100 on the detection panel of the fingerprint sensor 102, and each time the slide is entered, the determination unit 104 can collect the fingerprint sensor 102 and input it to the user. The multi-frame fingerprint image is spliced into a template fingerprint image, and then the three template fingerprint images are spliced to obtain the entire template fingerprint image of the finger.
  • the previous frame fingerprint image includes a previous frame image portion
  • the current frame fingerprint image includes a plurality of current frame image portion combinations
  • each current frame image portion combination includes a first current frame image portion.
  • the determining unit 104 is configured to calculate a first gradation of the image portion of the previous frame and a first gradation of the first current frame image portion in the combination of the same current frame image portion, and a second portion of the second current frame image portion Two gray levels and Calculating the first gray level difference and the second gray level by respectively obtaining a first gray level difference, a second gray level difference, and a third gray level difference corresponding to the third gray level difference of the third current frame image portion The difference between the gradation and the value of the third gradation difference is obtained to obtain a plurality of gradations and values, and the plurality of gradation sum values are compared.
  • the determining unit 104 is configured to compare the first gray level difference corresponding to the one of the current frame image portion combinations.
  • the second gradation difference and the third gradation difference are configured to compare the first gray level difference corresponding to the one of the current frame image portion combinations.
  • the determining unit 104 is configured to determine that the current frame image portion corresponding to the one of the grayscale differences of the minimum value is the first Overlapping area. If there is no less than the threshold, the determination unit 104 prompts the user to re-slide the fingerprint image.
  • the image portion A1 of the previous frame is located at the middle of the last two lines of the fingerprint image I1 of the previous frame, that is, the image portion A1 of the previous frame is the image of the 25th to 104th columns of the 7th to 8th rows of the previous frame fingerprint image I1. section.
  • Each current frame image portion combination Bn includes a first current frame image portion Bn1, a second current frame image portion Bn2, and a third current frame image portion Bn3.
  • the resolution of the first current frame image portion Bn1, the resolution of the second current frame image portion Bn2, and the resolution of the third current frame image portion Bn3 are both 2*80, and the second current frame image portion Bn2 is located in the current frame image portion.
  • the middle of the combination Bn is located in the middle of the current frame fingerprint image I2 in the middle of the resolution row direction, that is, the number of resolution columns between the leftmost side of the second current frame image portion Bn2 and the leftmost side of the current frame fingerprint image I2
  • the rightmost side of the second current frame image portion Bn2 is equal to the number of resolution columns between the rightmost sides of the current frame fingerprint image I2.
  • the first current frame image portion Bn1 is shifted left by 1 column from the second current frame image portion Bn2 in the row direction of the resolution
  • the third current frame image portion Bn3 is rightly offset from the second current frame image portion Bn2 in the row direction of the resolution. Move 1 column.
  • the image portion thus offset is taken into consideration when the user's finger 100 is slid into the fingerprint, and the factor of turning to the left and/or to the right is taken into consideration, so that the precision of the fingerprint splicing is higher.
  • the current frame image portion combination B1 includes a first current frame image portion B11, a second current frame image portion B12, and a third current frame image portion B13
  • the first current frame image portion B11 is current
  • the current frame image portion B13 is an image portion of the 26th to 105th columns of the first to second rows.
  • the current frame image portion combination B2 includes the first current frame image portion B21, second current frame image portion B22 and third current frame image portion B23, the first current frame image portion B21 is the image portion of the 24th to 103rd columns of the 2nd to 3rd rows, and the second current frame image portion B22 The image portion of the 25th to 104th columns of the 2nd to 3rd rows, the third current frame image portion B23 is the image portion of the 26th to 105th columns of the 2nd to 3rd rows.
  • the determining unit 104 is configured to calculate the first gray level G1 of the previous frame image portion A1 and the first gray level Gn1 and the second current of the first current frame image portion Bn1 in the same current frame image portion combination Bn.
  • the gradation difference of the second gradation Gn2 of the frame image portion Bn2 and the third gradation Gn3 of the third current frame image portion Bn3 to respectively obtain the first gradation difference Dn1, the second gradation difference Dn2, and the third gradation a difference Dn3, calculating a gradation sum value of the first gradation difference Dn1, the second gradation difference Dn2, and the third gradation difference Dn3 to obtain a plurality of gradations and values Sn, and comparing the plurality of gradations and values Sn.
  • the determining unit 104 is configured to compare the first one corresponding to the current frame image portion combination Bn The gradation difference Dn1, the second gradation difference Dn2, and the third gradation difference Dn3.
  • the determining unit 104 is configured to determine the current frame image corresponding to the gray level difference min_Dni of the minimum value.
  • Part Bni is the first overlapping area.
  • the determining unit 104 calculates the first gray level G11 of the first current frame image portion B11 and the second gray level G12 of the second current frame image portion B12 in the first gray level G1 and the current frame image portion combination B1.
  • the gradation difference of the third gradation G13 of the three current frame image portion B13 is obtained, and the first gradation difference D11, the second gradation difference D12, and the third gradation difference D13 are obtained, and the first gradation difference D11 and the second are calculated.
  • the gradation difference value D12 and the gradation difference value D13 of the third gradation difference D13 are calculated.
  • the determining unit 104 calculates the gradation sum value S2 corresponding to the current frame image portion combination B2, the gradation sum value S3 corresponding to the current frame image portion combination B3, and the gradation sum value S4 corresponding to the current frame image portion combination B4, The gradation sum value S5 corresponding to the current frame image portion combination B5, the gradation sum value S6 corresponding to the current frame image portion combination B6, and the gradation sum value S7 corresponding to the current frame image portion combination B7.
  • the judging unit 104 compares the seven gradations and the values S1, S2, ..., S7. If the gradation sum value S1 corresponding to the current frame image portion combination B1 is the minimum value among the seven gradation sum values, the judging unit 104 compares the current The frame image portion combines the first gradation difference D11, the second gradation difference D12, and the third gradation difference D13 corresponding to B1.
  • the determining unit 104 determines that the second current frame image portion B12 corresponding to the minimum gradation difference D12 is the first Overlapping area.
  • the determining unit 104 will remove the first overlapping area B12 in the current frame fingerprint image I2, and will remove the first
  • the current frame reference fingerprint image I2 of an overlap region B12 is spliced into the previous frame reference fingerprint image I1, so that the previous frame image portion A1 of the previous frame reference fingerprint image I1 is located at a position where the first overlap region B12 is removed, and further Get a superimposed fingerprint image.
  • the judging unit 104 completes the judgment of the remaining multi-frame fingerprint image and finally obtains a complete template fingerprint image.
  • the processing unit 106 is configured to extract and save feature points of the template fingerprint image.
  • the processing unit 106 thus establishes a fingerprint library for use as a fingerprint template in subsequent matching.
  • the fingerprint sensor 102 is also used to collect the fingerprint image to be recognized that the user presses to enter.
  • the processing unit 106 is configured to determine whether the feature point of the fingerprint image to be identified matches the feature point of the template fingerprint image. If yes, the processing unit 106 is configured to identify the fingerprint image to be recognized as a matching fingerprint image, and if not, the The processing unit 106 is configured to identify the fingerprint image to be identified as a non-matching fingerprint image.
  • the processing unit 106 collects, by the fingerprint sensor, the fingerprint image to be recognized that is pressed by the user, through filtering, binarization, refinement, etc., extracts feature point information, and matches the fingerprint library template information. When the acquired feature points of the fingerprint image to be identified match the feature points of the template fingerprint image, the matching can be successful.
  • the fingerprint identification system 10 uses the fingerprint sensor 102 to collect a multi-frame fingerprint image that the user slides in when the template fingerprint database is created, and the determining unit 104 uses the image stitching technology to stitch the images collected by the sliding together. Therefore, the amount of information collected by each slide input is much larger than that of the conventional method. The input efficiency is much higher than the existing method, and only the fingers such as the left side, the middle side, and the right side are separately performed. The recording process can be completed in one acquisition, which facilitates entry, avoids cumbersome operations, and improves the user experience.
  • the user is prompted by the fingerprint recognition system 10 to perform a sliding entry of the fingerprint of the corresponding position of the finger 100 through the user interface, such as through a user interface displayed on the display screen, such as fingerprint entry on the left side of the finger 100.
  • the user continues to complete the fingerprint entry in the middle and the right side of the finger 100 at the prompt of the fingerprint recognition system.
  • the user When the user subsequently matches, the user does not need to perform sliding input or splicing, and only needs to press the detection panel of the fingerprint sensor 102 to collect the fingerprint.
  • the fingerprint sensor 102 is pressed.
  • the fingerprint of the pressed portion is collected, and the processing unit 106 can compare the fingerprint with the database. Perhaps the user has a very regular angle when registering the fingerprint, and can still successfully recognize at various angles when matching.
  • the fingerprint identification system of the present embodiment is basically the same as the fingerprint identification system of the previous embodiment, and the difference is that in the fingerprint identification system of the present embodiment, the fingerprint image of the previous frame includes the image portion of the previous frame, and the current frame fingerprint image. Include a plurality of current frame image portions, the determining unit is configured to calculate a first gray level of the image portion of the previous frame and the plurality of current frame image portions respectively The gradation differences of the plurality of second gradations are obtained to obtain a plurality of gradation differences, and the plurality of gradation differences are compared.
  • the determining unit is configured to determine the one of the gradations One of the current frame image portions corresponding to the two gray levels is the first overlapping area. If there is no less than the threshold, the judging unit prompts the user to re-slide the fingerprint image.
  • the image portion P1 of the previous frame is located at the middle of the last two lines of the fingerprint image O1 of the previous frame, that is, the image portion P1 of the previous frame is the image of the 25th to 104th columns of the 7th to 8th rows of the previous frame fingerprint image O1. section.
  • the current frame image portion Qn is located in the middle of the current frame fingerprint image O2 along the resolution line direction, that is, the number of resolution columns between the leftmost side of the current frame image portion Qn and the leftmost frame of the current frame fingerprint image O2 and the current frame image.
  • the rightmost portion of the portion Qn is equal to the number of resolution columns between the rightmost sides of the current frame fingerprint image O2.
  • the current frame image portion Q1 is the image portion of the 25th to 104th columns of the 1st to 2nd lines of the current frame fingerprint image O2.
  • the current frame image portion Q2 is the image portion of the 25th to 104th columns of the 2nd to 3rd lines of the current frame fingerprint image O2. Other current frame image parts and so on.
  • the judging unit is configured to calculate a gradation difference between the first gradation Go of the image portion P1 of the previous frame and the seven second gradations Gn of the 7 current frame image portions Qn to obtain 7 gradation differences Dn, And compare the 7 gray scale differences Dn.
  • the determining unit is used for It is judged that one of the current frame image portions Qn corresponding to the one of the second gradations Gn is the first overlapping region.
  • the determination unit determines the current corresponding to the second gradation G2
  • the frame image portion Q2 is a first overlapping area.
  • the judging unit After the first overlapping area Q2 in the current frame fingerprint image O2 is removed, the judging unit splices the current frame fingerprint image O2 of the first overlapping area Q2 into the previous frame reference fingerprint image O1, so that the previous frame reference fingerprint is made.
  • the image portion P1 of the previous frame in the image O1 is located at a position where the first overlapping region Q2 is removed, thereby obtaining a superimposed fingerprint image.
  • the judging unit completes the judgment of the remaining multi-frame fingerprint image and finally obtains a complete template fingerprint image.
  • the finger when the user slides in the fingerprint, the finger does not rotate as much as possible, thereby improving the success rate of the recording.
  • a fingerprint identification method includes the following steps:
  • the fingerprint sensor collects a multi-frame fingerprint image that the user slides into
  • step S2 the judging unit judges whether the current frame fingerprint image and the previous frame fingerprint image in the multi-frame fingerprint image have a first overlapping area, and if yes, proceeds to step S3, otherwise returns to step S1;
  • the determining unit removes the first overlapping area in the current frame fingerprint image and superimposes the current frame fingerprint image after the first overlapping area is removed, and superimposes the previous frame fingerprint image to form a superimposed fingerprint image, or The determining unit removes the first overlapping area in the fingerprint image of the previous frame and superimposes the previous frame fingerprint image after the first overlapping area is removed, and the current frame fingerprint image is superimposed to form the superimposed fingerprint image;
  • S4 the determining unit determines whether the fingerprint image of the next frame and the superimposed fingerprint image have a second overlapping area until the determination of the multi-frame fingerprint image is completed and obtains a template fingerprint image;
  • S5 the processing unit extracts and saves feature points of the template fingerprint image
  • the fingerprint sensor collects an image of the fingerprint to be recognized that is pressed by the user
  • step S7 the processing unit extracts the feature point of the fingerprint image to be identified and determines whether the feature point of the fingerprint image to be identified matches the feature point of the template fingerprint image, and if yes, proceeds to step S8, otherwise proceeds to step S9;
  • S8 the processing unit identifies the fingerprint image to be identified as a matching fingerprint image
  • the processing unit identifies the fingerprint image to be identified as a non-matching fingerprint image.
  • the above fingerprint identification method can be implemented by the above fingerprint recognition system.
  • the above steps S3 and S4 can be understood as a splicing step of the fingerprint image.
  • step S5 the processing unit performs image filtering processing, binarization processing, and refinement processing on the template fingerprint image to extract the feature points of the template fingerprint image.
  • the previous frame fingerprint image includes a previous frame image portion
  • the current frame fingerprint image includes a plurality of current frame image portions
  • the determining unit calculates the first image portion of the previous frame portion.
  • the gradation is respectively different from the gradation of the plurality of second gradations of the plurality of current frame image portions to obtain a plurality of gradation differences, and the plurality of gradation differences are compared;
  • the determining unit determines one of the second ash One of the current frame image portions corresponding to the degree is the first overlapping area.
  • the previous frame fingerprint image includes a previous frame image portion
  • the image The current frame fingerprint image includes a plurality of current frame image portion combinations, and each current frame image portion combination includes a first current frame image portion, a second current frame image portion, and a third current frame image portion;
  • the judging unit calculates a first gradation of the image portion of the previous frame and a first gradation of the first current frame image portion and a second gradation of the second current frame image portion in a combination of the same current frame image portion, respectively And a third gray level of the image portion of the third current frame to respectively obtain a first gray level difference, a second gray level difference, and a third gray level difference, and calculate the first gray level difference, the second gray level difference, and the a grayscale sum value of the third grayscale difference to obtain a plurality of grayscale sum values, and comparing the plurality of grayscale sum values;
  • the determining unit compares the first gray level difference corresponding to the one of the current frame image part combinations, and the second Gray difference and third gray difference;
  • the determining unit determines that the current frame image portion corresponding to the gradation difference of the minimum value is the first overlapping region.
  • the fingerprint sensor when the template fingerprint database is established, the fingerprint sensor is used to collect the multi-frame fingerprint image that the user slides into, and the judging unit uses the image stitching technology to stitch the images collected by the sliding together. Therefore, the amount of information collected by each slide input is much larger than that of the conventional method.
  • the input efficiency is much higher than the existing method, and only the fingers such as the left side, the middle side, and the right side are separately performed.
  • the recording process can be completed in one acquisition, which facilitates the entry, avoids cumbersome operations, and improves the user experience.
  • the fingerprint sensor collects the fingerprint of the pressed part, and the processing unit
  • the fingerprint can be compared with the database, and the user may have a very regular angle when registering the fingerprint, and can still successfully recognize at various angles when matching.
  • an electronic device 20 includes the fingerprint identification system of any of the above embodiments.
  • the electronic device 20 can be a terminal device such as a mobile phone or a tablet computer.
  • the fingerprint recognition system is used in a mobile phone, as shown in FIG. 2, the fingerprint sensor 202 is located at a suitable position on the lower Home button of the electronic device 20, on the side of the mobile phone, or on the back of the mobile phone.
  • the user first uses please press the finger 100 on the fingerprint sensor 202 in conjunction with FIG. 3, and slide the fingerprint sensor 202 with the left, middle, and right sides of the finger 100, respectively, so that the entire finger can be recorded by sliding the fingerprint. 100 fingerprint feature points.
  • the finger 100 only needs to be pressed on the fingerprint sensor 202, and no angle can be recognized without sliding.
  • first and second are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated.
  • features defining “first” or “second” may include at least one of the features, either explicitly or implicitly.
  • the meaning of "a plurality” is at least two, such as two, three, etc., unless specifically defined otherwise.
  • a "computer-readable medium” can be any apparatus that can contain, store, communicate, propagate, or transport a program for use in an instruction execution system, apparatus, or device, or in conjunction with the instruction execution system, apparatus, or device.
  • computer readable media include the following: electrical connections (electronic devices) having one or more wires, portable computer disk cartridges (magnetic devices), random access memory (RAM), Read only memory (ROM), erasable editable read only memory (EPROM or flash memory), fiber optic devices, and portable compact disk read only memory (CDROM).
  • the computer readable medium may even be a paper or other suitable medium on which the program can be printed, as it may be optically scanned, for example by paper or other medium, followed by editing, interpretation or, if appropriate, other suitable The method is processed to obtain the program electronically and then stored in computer memory.
  • portions of the invention may be implemented in hardware, software, firmware or a combination thereof.
  • multiple steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system.
  • a suitable instruction execution system For example, if implemented in hardware, as in another embodiment, it can be implemented by any one or combination of the following techniques well known in the art: having logic gates for implementing logic functions on data signals. Discrete logic circuits, application specific integrated circuits with suitable combinational logic gates, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.
  • the programming may be performed by a related hardware, which may be stored in a computer readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiments.
  • each functional unit in each embodiment of the present invention may be integrated into one processing module, or each unit may exist physically separately, or two or more units may be integrated into one module.
  • the above integrated modules can be implemented in the form of hardware or in the form of software functional modules.
  • the integrated modules, if implemented in the form of software functional modules and sold or used as stand-alone products, may also be stored in a computer readable storage medium.
  • the above mentioned storage medium may be a read only memory, a magnetic disk or an optical disk or the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Human Computer Interaction (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Pathology (AREA)
  • Collating Specific Patterns (AREA)
  • Image Input (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

公开的指纹识别系统中，指纹传感器采集用户滑动录入的多帧指纹图像，判断单元判断当前帧指纹图像与前一帧指纹图像是否有重叠区域，若是，判断单元将当前帧指纹图像的重叠区域去掉并将当前帧指纹图像与前一帧指纹图像叠加形成叠加指纹图像，判断单元完成多帧指纹图像的判断并得到模板指纹图像，处理单元保存模板指纹图像的特征点。指纹传感器还采集用户按压录入的待识别指纹图像，处理单元判断待识别指纹图像的特征点与模板指纹图像的特征点是否匹配。上述指纹识别系统，在建立模板指纹库时，采集用户滑动录入的指纹及后续匹配时采集用户按压录入的指纹，因此，录入及识别效率相对现有的方法高很多。还公开指纹识别方法及电子设备。

Description

指纹识别系统及指纹识别方法及电子设备
优先权信息
本申请请求2014年12月19日向中国国家知识产权局提交的、专利申请号为201410799636.7的专利申请的优先权和权益，并且通过参照将其全文并入此处。
技术领域
本发明涉及于指纹识别领域，更具体而言，涉及一种指纹识别系统、一种指纹识别方法及一种电子设备。
背景技术
现在的面积式指纹传感器都是采用按压式录入方法，录入的时候，将手指按压在指纹传感器上面，一次性捕捉到按压部分的指纹信息，不需移动手指，但是由于指纹扫描模块面积有限，每一次按压所检测到指纹的面积比较小，一般需要进行多次录入才能采集到较为完整的指纹信息。
同时，因为结构的限制，或者是为了更为美观，现在指纹传感器的指纹扫描模块向着越来越小的方向发展，在录入指纹时，每次按压所能获取的指纹信息也越来越少，必须通过多次按压录入以确保采集到足够的特征点，才能进行后期的匹配，这样导致了指纹库的录入过程非常繁琐，也非常耗时。
发明内容
本发明旨在至少解决现有技术中存在的技术问题之一。为此，本发明需要提供一种指纹识别系统及识别方法及一种电子设备。
一种指纹识别系统，包括指纹传感器、判断单元及处理单元；
该指纹传感器用于采集用户滑动录入的多帧指纹图像；
该判断单元用于判断该多帧指纹图像中当前帧指纹图像与前一帧指纹图像是否有第一重叠区域；
若是，该判断单元还用于将在该当前帧指纹图像中的该第一重叠区域去掉并将去掉该第一重叠区域后的该当前帧指纹图像与该前一帧指纹图像像叠加形成叠加指纹图像；
或该判断单元用于将在该前一帧指纹图像中的该第一重叠区域去掉并将去掉该第 一重叠区域后的该前一帧指纹图像与该当前帧指纹图像叠加形成该叠加指纹图像；
该判断单元还用于判断后一帧指纹图像与该叠加指纹图像是否有第二重叠区域，直至完成该多帧指纹图像的判断并得到一幅模板指纹图像；
若否，该指纹传感器用于重新采集用户滑动录入的该多帧指纹图像；
该处理单元用于提取并保存该幅模板指纹图像的特征点；
该指纹传感器还用于采集用户按压录入的待识别指纹图像，该处理单元用于提取该待识别指纹图像的特征点并判断该待识别指纹图像的特征点与该幅模板指纹图像的特征点是否匹配；
若是，该处理单元用于识别该待识别指纹图像为匹配指纹图像，若否，该处理单元用于识别该待识别指纹图像为非匹配指纹图像。
上述指纹识别系统，在建立模板指纹库的时候，利用指纹传感器采集用户滑动录入的多帧指纹图像，判断单元利用图像拼接技术将滑动采集的图像拼接在一起。因此，每次滑动录入采集到的信息量比现有方法的按压式录入采集到的信息量大很多，录入效率相对现有的方法高很多，只需要手指例如左侧、中间及右侧分别进行一次采集就可以完成录入过程，录入方便，避免了繁琐的操作，提高了用户体验，在后续匹配过程中，用户手指按压在指纹传感器上，此时指纹传感器会采集按压部分的指纹，处理单元并能够将该指纹与数据库进行判断比对，也许用户在登记指纹时是很常规的角度，在匹配时依然能够在各种角度成功识别。
在一个实施方式中，该处理单元用于对该幅模板指纹图像进行图像滤波处理、二值化处理及细化处理后提取该幅模板指纹图像的该特征点。
在一个实施方式中，该前一帧指纹图像包括前一帧图像部分，该当前帧指纹图像包括多个当前帧图像部分，该判断单元用于计算该前一帧图像部分的第一灰度分别与该多个当前帧图像部分的多个第二灰度的灰度差以得到多个灰度差，并比较该多个灰度差；
若其中一个第二灰度与该第一灰度的灰度差为该多个灰度差中的最小值且最小值的该灰度差小于阈值，则该判断单元用于判断该其中一个第二灰度所对应的其中一个当前帧图像部分为该第一重叠区域。
在一个实施方式中，该前一帧指纹图像包括前一帧图像部分，该当前帧指纹图像包括多个当前帧图像部分组合，每个当前帧图像部分组合包括第一当前帧图像部分、第二当前帧图像部分及第三当前帧图像部分；
该判断单元用于计算该前一帧图像部分的第一灰度分别与在同一个当前帧图像部 分组合中的第一当前帧图像部分的第一灰度、第二当前帧图像部分的第二灰度及第三当前帧图像部分的第三灰度的灰度差以分别对应得到第一灰度差、第二灰度差及第三灰度差，计算该第一灰度差、该第二灰度差及该第三灰度差的灰度和值以得到多个灰度和值，比较该多个灰度和值；
若其中一个当前帧图像部分组合对应的灰度和值为该多个灰度和值中的最小值，则该判断单元用于比较该其中一个当前帧图像部分组合对应的第一灰度差、第二灰度差及第三灰度差；
若得到最小值的其中一个灰度差且最小值的该其中一个灰度差小于阈值，则该判断单元用于判断最小值的该其中一个灰度差对应的当前帧图像部分为该第一重叠区域。
一种指纹识别方法，包括步骤：
S1：指纹传感器采集用户滑动录入的多帧指纹图像；
S2：判断单元判断该多帧指纹图像中当前帧指纹图像与前一帧指纹图像是否有第一重叠区域，若是则进入步骤S3，若否则返回步骤S1；
S3：该判断单元将在该当前帧指纹图像中的该第一重叠区域去掉并将去掉该第一重叠区域后的该当前帧指纹图像与该前一帧指纹图像叠加形成叠加指纹图像，或该判断单元将在该前一帧指纹图像中的该第一重叠区域去掉并将去掉该第一重叠区域后的该前一帧指纹图像与该当前帧指纹图像叠加形成该叠加指纹图像；
S4：该判断单元判断后一帧指纹图像与该叠加指纹图像是否有第二重叠区域，直至完成该多帧指纹图像的判断并得到一幅模板指纹图像；
S5：处理单元提取并保存该幅模板指纹图像的特征点；
S6：该指纹传感器采集用户按压录入的待识别指纹图像；
S7：该处理单元提取该待识别指纹图像的特征点并判断该待识别指纹图像的特征点与该幅模板指纹图像的特征点是否匹配，若是则进入步骤S8，若否则进入步骤S9；
S8：该处理单元识别该待识别指纹图像为匹配指纹图像；
S9：该处理单元识别该待识别指纹图像为非匹配指纹图像。
在一个实施方式中，在步骤S5中，该处理单元对该幅模板指纹图像进行图像滤波处理、二值化处理及细化处理后提取该幅模板指纹图像的该特征点。
在一个实施方式中，在步骤S2中，该前一帧指纹图像包括前一帧图像部分，该当前帧指纹图像包括多个当前帧图像部分，该判断单元计算该前一帧图像部分的第一 灰度分别与该多个当前帧图像部分的多个第二灰度的灰度差以得到多个灰度差，并比较该多个灰度差；
若其中一个第二灰度与该第一灰度的灰度差为该多个灰度差中的最小值且最小值的该灰度差小于阈值，则该判断单元判断该其中一个第二灰度所对应的其中一个当前帧图像部分为该第一重叠区域。
在一个实施方式中，在步骤S2中，该前一帧指纹图像包括前一帧图像部分，该当前帧指纹图像包括多个当前帧图像部分组合，每个当前帧图像部分组合包括第一当前帧图像部分、第二当前帧图像部分及第三当前帧图像部分；
该判断单元计算该前一帧图像部分的第一灰度分别与在同一个当前帧图像部分组合中的第一当前帧图像部分的第一灰度、第二当前帧图像部分的第二灰度及第三当前帧图像部分的第三灰度以分别对应得到第一灰度差、第二灰度差及第三灰度差，计算该第一灰度差、该第二灰度差及该第三灰度差的灰度和值以得到多个灰度和值，比较该多个灰度和值；
若其中一个当前帧图像部分组合对应的灰度和值为该多个灰度和值中的最小值，则该判断单元比较该其中一个当前帧图像部分组合对应的第一灰度差、第二灰度差及第三灰度差；
若得到最小值的灰度差且最小值的该灰度差小于阈值，则该判断单元判断最小值的该灰度差对应的当前帧图像部分为该第一重叠区域。
一种电子设备，包括指纹识别系统，该指纹识别系统包括指纹传感器、判断单元及处理单元；
该指纹传感器用于采集用户滑动录入的多帧指纹图像；
该判断单元用于判断该多帧指纹图像中当前帧指纹图像与前一帧指纹图像是否有第一重叠区域；
若是，该判断单元还用于将在该当前帧指纹图像中的该第一重叠区域去掉并将去掉该第一重叠区域后的该当前帧指纹图像与该前一帧指纹图像叠加形成叠加指纹图像；
或该判断单元用于将在该前一帧指纹图像中的该第一重叠区域去掉并将去掉该第一重叠区域后的该前一帧指纹图像与该当前帧指纹图像叠加形成该叠加指纹图像；
该判断单元还用于判断后一帧指纹图像与该叠加指纹图像是否有第二重叠区域直至完成该多帧指纹图像的判断并得到一幅模板指纹图像；
该处理单元用于提取并保存该幅模板指纹图像的特征点；
若否，该指纹传感器用于重新采集用户滑动录入的该多帧指纹图像；
该指纹传感器还用于采集用户按压录入的待识别指纹图像；
该处理单元用于提取该待识别指纹图像的特征点并判断该待识别指纹图像的特征点与该幅模板指纹图像的特征点是否匹配；
若是，该处理单元用于识别该待识别指纹图像为匹配指纹图像，若否，该处理单元用于识别该待识别指纹图像为非匹配指纹图像。
在一个实施方式中，该处理单元用于对该幅模板指纹图像进行图像滤波处理、二值化处理及细化处理后提取该幅模板指纹图像的该特征点。
在一个实施方式中，该前一帧指纹图像包括前一帧图像部分，该当前帧指纹图像包括多个当前帧图像部分，该判断单元用于计算该前一帧图像部分的第一灰度分别与该多个当前帧图像部分的多个第二灰度的灰度差以得到多个灰度差，并比较该多个灰度差；
若其中一个第二灰度与该第一灰度的灰度差为该多个灰度差中的最小值且最小值的该灰度差小于阈值，则该判断单元用于判断该其中一个第二灰度所对应的其中一个当前帧图像部分为该第一重叠区域。
在一个实施方式中，该前一帧指纹图像包括前一帧图像部分，该当前帧指纹图像包括多个当前帧图像部分组合，每个当前帧图像部分组合包括第一当前帧图像部分、第二当前帧图像部分及第三当前帧图像部分；
该判断单元用于计算该前一帧图像部分的第一灰度分别与在同一个当前帧图像部分组合中的第一当前帧图像部分的第一灰度、第二当前帧图像部分的第二灰度及第三当前帧图像部分的第三灰度的灰度差以分别对应得到第一灰度差、第二灰度差及第三灰度差，计算该第一灰度差、该第二灰度差及该第三灰度差的灰度和值以得到多个灰度和值，比较该多个灰度和值；
若其中一个当前帧图像部分组合对应的灰度和值为该多个灰度和值中的最小值，则该判断单元用于比较该其中一个当前帧图像部分组合对应的第一灰度差、第二灰度差及第三灰度差；
若得到最小值的其中一个灰度差且最小值的该其中一个灰度差小于阈值，则该判断单元用于判断最小值的该其中一个灰度差对应的当前帧图像部分为该第一重叠区域。
本发明的附加方面和优点将在下面的描述中部分给出，部分将从下面的描述中变得明显，或通过本发明的实践了解到。
附图说明
本发明的上述和/或附加的方面和优点从结合下面附图对实施方式的描述中将变得明显和容易理解，其中：
图1是较佳实施方式的指纹识别系统的模块示意图。
图2是用户在指纹传感器上录入手指指纹的示意图。
图3是用户在指纹传感器上录入手指不同位置指纹的示意图。
图4是本发明较佳实施方式的指纹识别系统的原理示意图。
图5是本发明较佳实施方式的指纹识别系统的另一原理示意图。
图6是本发明较佳实施方式的指纹识别方法的流程示意图。
图7是本发明较佳实施方式的电子设备的结构示意图。
具体实施方式
下面详细描述本发明的实施方式，所述实施方式的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施方式是示例性的，仅用于解释本发明，而不能理解为对本发明的限制。
在本发明的描述中，需要理解的是，术语“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括一个或者更多个所述特征。在本发明的描述中，“多个”的含义是两个或两个以上，除非另有明确具体的限定。
在本发明的描述中，需要说明的是，除非另有明确的规定和限定，术语“安装”、“相连”、“连接”应做广义理解，例如，可以是固定连接，也可以是可拆卸连接，或一体地连接；可以是机械连接，也可以是电连接或可以相互通信；可以是直接相连，也可以通过中间媒介间接相连，可以是两个元件内部的连通或两个元件的相互作用关系。对于本领域的普通技术人员而言，可以根据具体情况理解上述术语在本发明中的具体含义。
下文的公开提供了许多不同的实施方式或例子用来实现本发明的不同结构。为了简化本发明的公开，下文中对特定例子的部件和设定进行描述。当然，它们仅仅为示例，并且目的不在于限制本发明。此外，本发明可以在不同例子中重复参考数字和/ 或参考字母，这种重复是为了简化和清楚的目的，其本身不指示所讨论各种实施方式和/或设定之间的关系。此外，本发明提供了的各种特定的工艺和材料的例子，但是本领域普通技术人员可以意识到其他工艺的应用和/或其他材料的使用。
请参阅图1，本发明较佳实施方式的纹识别系统10包括指纹传感器102、判断单元104及处理单元106。
该指纹传感器102用于采集用户滑动录入的多帧指纹图像。该指纹传感器102例如可采用面状电容式指纹传感器，尺寸约4*8mm，508dpi，分辨率为80*160。该多帧指纹图像通过滑动式录入方式由用户输入，请参图2，如用户将手指100滑动经过指纹传感器102的检测面板，指纹传感器102便能一次可以采集到很多帧手指的滑动指纹图像序列。
该判断单元104用于判断该多帧指纹图像中当前帧指纹图像与前一帧指纹图像是否有第一重叠区域，若是，该判断单元102还用于将在该当前帧指纹图像中的该第一重叠区域去掉并将去掉该第一重叠区域后的该当前帧指纹图像与该前一帧指纹图像叠加形成叠加指纹图像，若否，该指纹传感器102用于重新采集用户滑动录入的该多帧指纹图像，该判断单元104还用于判断后一帧指纹图像与该叠加指纹图像是否有第二重叠区域，直至完成该多帧指纹图像的判断并得到一幅模板指纹图像。
在其它实施方式中，该判断单元104还可用于将在该前一帧指纹图像中的该第一重叠区域去掉并将去掉该第一重叠区域后的该前一帧指纹图像与该当前帧指纹图像叠加形成叠加指纹图像。
由于指纹传感器102面积小，指纹面积大，在采集指纹时，指纹传感器102会采集到一帧一帧的指纹图像，当相邻两帧指纹图像具有一部分相同的区域，判断单元104就可以将他们拼接在一起成为另一帧指纹图像。所以，请参图3，用户将手指100左侧，中间及右侧分别在指纹传感器102的检测面板进行滑动录入，在每一次滑动录入时，判断单元104可将指纹传感器102采集到用户滑动录入的多帧指纹图像拼接为一幅的模板指纹图像，后将三幅的模板指纹图像拼接可以得到手指的整个模板指纹图像。
具体地，在本实施方式中，该前一帧指纹图像包括前一帧图像部分，该当前帧指纹图像包括多个当前帧图像部分组合，每个当前帧图像部分组合包括第一当前帧图像部分、第二当前帧图像部分及第三当前帧图像部分。
该判断单元104用于计算该前一帧图像部分的第一灰度分别与在同一个当前帧图像部分组合中的第一当前帧图像部分的第一灰度、第二当前帧图像部分的第二灰度及 第三当前帧图像部分的第三灰度的灰度差以分别对应得到第一灰度差、第二灰度差及第三灰度差，计算该第一灰度差、该第二灰度差及该第三灰度差的灰度和值以得到多个灰度和值，比较该多个灰度和值。
若其中一个当前帧图像部分组合对应的灰度和值为该多个灰度和值中的最小值，则该判断单元104用于比较该其中一个当前帧图像部分组合对应的第一灰度差、第二灰度差及第三灰度差。
若得到最小值的其中一个灰度差且最小值的该其中一个灰度差小于阈值，则该判断单元104用于判断最小值的该其中一个灰度差对应的当前帧图像部分为该第一重叠区域。若不存在小于阈值的情况，则判断单元104提示用户重新滑动录入指纹图像。
例如，请结合图4，该前一帧指纹图像I1(分辨率为8*128)包括前一帧图像部分A1(分辨率为2*80)，该当前帧指纹图像I2(分辨率为8*128)包括7个当前帧图像部分组合B1～B7(每个当前帧图像部分组合Bn的分辨率为2*82，n＝1、2、…、7)。
前一帧图像部分A1位于前一帧指纹图像I1最后两行的中间位置，即前一帧图像部分A1为前一帧指纹图像I1的第7至第8行的第25至第104列的图像部分。
每个当前帧图像部分组合Bn包括第一当前帧图像部分Bn1、第二当前帧图像部分Bn2及第三当前帧图像部分Bn3。第一当前帧图像部分Bn1的分辨率、第二当前帧图像部分Bn2的分辨率及第三当前帧图像部分Bn3的分辨率均为2*80，第二当前帧图像部分Bn2位于当前帧图像部分组合Bn的中间，且位于当前帧指纹图像I2沿分辨率行方向的中间，即第二当前帧图像部分Bn2的最左侧距当前帧指纹图像I2的最左侧之间的分辨率列数与第二当前帧图像部分Bn2的最右侧距当前帧指纹图像I2的最右侧之间的分辨率列数相等。第一当前帧图像部分Bn1沿分辨率的行方向从第二当前帧图像部分Bn2左偏移1列，第三当前帧图像部分Bn3沿分辨率的行方向从第二当前帧图像部分Bn2右偏移1列。如此取偏移的图像部分，是将用户手指100滑动录入指纹过程中有向左及/或向右转动的因素考虑进去，使得指纹拼接的精度更高。
例如，对于当前帧图像部分组合B1，当前帧图像部分组合B1包括第一当前帧图像部分B11、第二当前帧图像部分B12及第三当前帧图像部分B13，第一当前帧图像部分B11为当前帧参考指纹图像I2的第1至第2行的第24至第103列的图像部分，第二当前帧图像部分B12为第1至第2行的第25至第104列的图像部分，第三当前帧图像部分B13为第1至第2行的第26至第105列的图像部分。
对于当前帧图像部分组合B2，当前帧图像部分组合B2包括第一当前帧图像部分 B21、第二当前帧图像部分B22及第三当前帧图像部分B23，第一当前帧图像部分B21为第2至第3行的第24至第103列的图像部分，第二当前帧图像部分B22为第2至第3行的第25至第104列的图像部分，第三当前帧图像部分B23为第2至第3行的第26至第105列的图像部分。其它当前帧图像部分组合依此类推。
该判断单元104用于计算该前一帧图像部分A1的第一灰度G1分别与在同一个当前帧图像部分组合Bn中的第一当前帧图像部分Bn1的第一灰度Gn1、第二当前帧图像部分Bn2的第二灰度Gn2及第三当前帧图像部分Bn3的第三灰度Gn3的灰度差以分别对应得到第一灰度差Dn1、第二灰度差Dn2及第三灰度差Dn3，计算该第一灰度差Dn1、该第二灰度差Dn2及该第三灰度差Dn3的灰度和值以得到多个灰度和值Sn，比较该多个灰度和值Sn。
若其中一个当前帧图像部分组合Bn对应的灰度和值Sn为该多个灰度和值中的最小值，则该判断单元104用于比较该其中一个当前帧图像部分组合Bn对应的第一灰度差Dn1、第二灰度差Dn2及第三灰度差Dn3。
若得到最小值的灰度差min_Dni，i＝1，2，3且最小值的该灰度差min_Dni小于阈值，则该判断单元104用于判断最小值的该灰度差min_Dni对应的当前帧图像部分Bni为该第一重叠区域。
具体地，判断单元104计算第一灰度G1与当前帧图像部分组合B1中的第一当前帧图像部分B11的第一灰度G11、第二当前帧图像部分B12的第二灰度G12及第三当前帧图像部分B13的第三灰度G13的灰度差，得到第一灰度差D11、第二灰度差D12及第三灰度差D13，并计算第一灰度差D11、第二灰度差D12及第三灰度差D13的灰度和值S1。类似地，判断单元104计算得到当前帧图像部分组合B2对应的灰度和值S2、当前帧图像部分组合B3对应的灰度和值S3、当前帧图像部分组合B4对应的灰度和值S4、当前帧图像部分组合B5对应的灰度和值S5、当前帧图像部分组合B6对应的灰度和值S6及当前帧图像部分组合B7对应的灰度和值S7。
判断单元104比较7个灰度和值S1、S2、…、S7，若当前帧图像部分组合B1对应的灰度和值S1为该7个灰度和值中的最小值，判断单元104比较当前帧图像部分组合B1对应的第一灰度差D11、第二灰度差D12及第三灰度差D13。
若得到第二灰度差D12为最小值且最小值的第二灰度差D12小于阈值，则判断单元104判断最小值的第二灰度差D12对应的第二当前帧图像部分B12为第一重叠区域。
判断单元104将在当前帧指纹图像I2中的该第一重叠区域B12去掉后,将去掉第 一重叠区域B12的当前帧参考指纹图像I2拼接到前一帧参考指纹图像I1中，使前一帧参考指纹图像I1中的前一帧图像部分A1位于去掉该第一重叠区域B12的位置，进而得到一幅叠加指纹图像。判断单元104完成剩下的多帧指纹图像的判断并最终得到一幅完整的模板指纹图像。
处理单元106用于提取并保存该幅模板指纹图像的特征点。处理单元106以此建立指纹库，在后续匹配时作为指纹模板使用。
在后续匹配时，指纹传感器102还用于采集用户按压录入的待识别指纹图像。该处理单元106用于判断该待识别指纹图像的特征点与该幅模板指纹图像的特征点是否匹配，若是，该处理单元106用于识别该待识别指纹图像为匹配指纹图像，若否，该处理单元106用于识别该待识别指纹图像为非匹配指纹图像。处理单元106对指纹传感器采集到由用户按压录入的待识别指纹图像经过滤波、二值化、细化等处理，提取特征点信息，与指纹库模板信息进行匹配。当采集的待识别指纹图像的特征点与模板指纹图像的特征点相匹配就可以匹配成功。
上述指纹识别系统10，在建立模板指纹库的时候，利用指纹传感器102采集用户滑动录入的多帧指纹图像，判断单元104利用图像拼接技术将滑动采集的图像拼接在一起。因此，每次滑动录入采集到的信息量比现有方法的按压式录入采集到的信息量大很多，录入效率相对现有的方法高很多，只需要手指例如左侧、中间及右侧分别进行一次采集就可以完成录入过程，录入方便，避免了繁琐的操作，提高了用户体验。可以理解，用户是在指纹识别系统10通过用户界面，如通过显示在显示屏上的用户界面提示用户进行手指100相应位置指纹的滑动录入，例如手指100左侧的指纹录入。在该手指100左侧的指纹录入成功后，用户继续在指纹识别系统的提示下完成手指100中间及右侧的指纹录入。
用户在后续匹配的时候，不需要滑动录入，也不需要进行拼接，只需按压指纹传感器102的检测面板采集指纹，在后续匹配过程中，用户手指按压在指纹传感器102上，此时指纹传感器102会采集按压部分的指纹，处理单元106并能够将该指纹与数据库进行判断比对，也许用户在登记指纹时是很常规的角度，在匹配时依然能够在各种角度成功识别。
本发明另一实施方式提供了一种指纹识别系统。本实施方式的指纹识别系统与上一实施方式的指纹识别系统基本相同，其不同之处在于，本实施方式的指纹识别系统中，前一帧指纹图像包括前一帧图像部分，当前帧指纹图像包括多个当前帧图像部分，该判断单元用于计算该前一帧图像部分的第一灰度分别与该多个当前帧图像部分 的多个第二灰度的灰度差以得到多个灰度差，并比较该多个灰度差。
若其中一个第二灰度与该第一灰度的灰度差为该多个灰度差中的最小值且最小值的该灰度差小于阈值，则该判断单元用于判断该其中一个第二灰度所对应的其中一个当前帧图像部分为第一重叠区域。若不存在小于阈值的情况，则判断单元提示用户重新滑动录入指纹图像。
例如，请结合图5，该前一帧指纹图像O1(分辨率为8*128)包括前一帧图像部分P1(分辨率为2*80)，该当前帧指纹图像O2(分辨率为8*128)包括7个当前帧图像部分Qn(n＝1、2、…、7)。
前一帧图像部分P1位于前一帧指纹图像O1最后两行的中间位置，即前一帧图像部分P1为前一帧指纹图像O1的第7至第8行的第25至第104列的图像部分。
当前帧图像部分Qn位于当前帧指纹图像O2沿分辨率行方向的中间，即当前帧图像部分Qn的最左侧距当前帧指纹图像O2的最左侧之间的分辨率列数与当前帧图像部分Qn的最右侧距当前帧指纹图像O2的最右侧之间的分辨率列数相等。
例如，对于当前帧图像部分Q1，当前帧图像部分Q1为当前帧指纹图像O2的第1至第2行的第25至第104列的图像部分。
对于当前帧图像部分Q2，当前帧图像部分Q2为当前帧指纹图像O2的第2至第3行的第25至第104列的图像部分。其它当前帧图像部分依此类推。
该判断单元用于计算该前一帧图像部分P1的第一灰度Go分别与该7个当前帧图像部分Qn的7个第二灰度Gn的灰度差以得到7个灰度差Dn，并比较该7个灰度差Dn。
若其中一个第二灰度Gn与该第一灰度Go的灰度差Dn为该多个灰度差中的最小值min_Dn且最小值的该灰度差min_Dn小于阈值，则该判断单元用于判断该其中一个第二灰度Gn所对应的其中一个当前帧图像部分Qn为第一重叠区域。
例如，第二灰度G2与第一灰度Go的灰度差D2为该7个灰度差中的最小值，且灰度差D2小于阈值，则判断单元判断第二灰度G2对应的当前帧图像部分Q2为第一重叠区域。
判断单元将在当前帧指纹图像O2中的该第一重叠区域Q2去掉后,将去掉第一重叠区域Q2的当前帧指纹图像O2拼接到前一帧参考指纹图像O1中，使前一帧参考指纹图像O1中的前一帧图像部分P1位于去掉第一重叠区域Q2的位置，进而得到一幅叠加指纹图像。判断单元完成剩下的多帧指纹图像的判断并最终得到一幅完整的模板指纹图像。
本实施方式的指纹识别系统，要求用户滑动录入指纹时，手指尽量不转动，进而能提高录入成功率。
请参图6，本发明较佳实施方式的指纹识别方法，包括步骤：
S1：指纹传感器采集用户滑动录入的多帧指纹图像；
S2：判断单元判断该多帧指纹图像中当前帧指纹图像与前一帧指纹图像是否有第一重叠区域，若是则进入步骤S3，若否则返回步骤S1；
S3：该判断单元将在该当前帧指纹图像中的该第一重叠区域去掉并将去掉该第一重叠区域后的该当前帧指纹图像与该前一帧指纹图像叠加形成叠加指纹图像，或该判断单元将在该前一帧指纹图像中的该第一重叠区域去掉并将去掉该第一重叠区域后的该前一帧指纹图像与该当前帧指纹图像叠加形成该叠加指纹图像；
S4：该判断单元判断后一帧指纹图像与该叠加指纹图像是否有第二重叠区域直至完成该多帧指纹图像的判断并得到一幅模板指纹图像；
S5：处理单元提取并保存该幅模板指纹图像的特征点；
S6：该指纹传感器采集用户按压录入的待识别指纹图像；
S7：该处理单元提取该待识别指纹图像的特征点并判断该待识别指纹图像的特征点与该幅模板指纹图像的特征点是否匹配，若是则进入步骤S8，若否则进入步骤S9；
S8：该处理单元识别该待识别指纹图像为匹配指纹图像；
S9：该处理单元识别该待识别指纹图像为非匹配指纹图像。
可以理解，上述指纹识别方法可由以上指纹识别系统执行实现。上述步骤S3及S4可以理解为对指纹图像的拼接步骤。
在一个实施方式中，在步骤S5中，该处理单元对该幅模板指纹图像进行图像滤波处理、二值化处理及细化处理后提取该幅模板指纹图像的该特征点。
在一个实施方式中，在步骤S2中，该前一帧指纹图像包括前一帧图像部分，该当前帧指纹图像包括多个当前帧图像部分，该判断单元计算该前一帧图像部分的第一灰度分别与该多个当前帧图像部分的多个第二灰度的灰度差以得到多个灰度差，并比较该多个灰度差；
若其中一个第二灰度与该第一灰度的灰度差为该多个灰度差中的最小值且最小值的该灰度差小于阈值，则该判断单元判断该其中一个第二灰度所对应的其中一个当前帧图像部分为该第一重叠区域。
在一个实施方式中，在步骤S2中，该前一帧指纹图像包括前一帧图像部分，该 当前帧指纹图像包括多个当前帧图像部分组合，每个当前帧图像部分组合包括第一当前帧图像部分、第二当前帧图像部分及第三当前帧图像部分；
该判断单元计算该前一帧图像部分的第一灰度分别与在同一个当前帧图像部分组合中的第一当前帧图像部分的第一灰度、第二当前帧图像部分的第二灰度及第三当前帧图像部分的第三灰度以分别对应得到第一灰度差、第二灰度差及第三灰度差，计算该第一灰度差、该第二灰度差及该第三灰度差的灰度和值以得到多个灰度和值，比较该多个灰度和值；
若其中一个当前帧图像部分组合对应的灰度和值为该多个灰度和值中的最小值，则该判断单元比较该其中一个当前帧图像部分组合对应的第一灰度差、第二灰度差及第三灰度差；
若得到最小值的灰度差且最小值的该灰度差小于阈值，则该判断单元判断最小值的该灰度差对应的当前帧图像部分为该第一重叠区域。
上述指纹识别方法，在建立模板指纹库的时候，利用指纹传感器采集用户滑动录入的多帧指纹图像，判断单元利用图像拼接技术将滑动采集的图像拼接在一起。因此，每次滑动录入采集到的信息量比现有方法的按压式录入采集到的信息量大很多，录入效率相对现有的方法高很多，只需要手指例如左侧、中间及右侧分别进行一次采集就可以完成录入过程，录入方便，避免了繁琐的操作，提高了用户体验，在后续匹配过程中，用户手指按压在指纹传感器上，此时指纹传感器会采集按压部分的指纹，处理单元并能够将该指纹与数据库进行判断比对，也许用户在登记指纹时是很常规的角度，在匹配时依然能够在各种角度成功识别。
请参图7，本发明较佳实施方式的电子设备20包括以上任一实施方式的指纹识别系统。该电子设备20可为手机、平板电脑等终端设备。当指纹识别系统用于手机时，如图2所示，指纹传感器202位于电子设备20的下方Home键上、手机侧面上或者手机背面等合适的位置。在用户第一次使用时，请结合图3，将手指100按在指纹传感器202上，分别用手指100的左侧、中间、右侧滑过指纹传感器202，这样通过滑动录入指纹可以记录整个手指100的指纹特征点。用户以后使用设备解锁时只需将手指100按压在指纹传感器202上，不需滑动，任何角度都可以识别。
在本说明书的描述中，参考术语“一个实施方式”、“一些实施方式”、“示意性实施方式”、“示例”、“具体示例”、或“一些示例”等的描述意指结合所述实施方式或示例描述的具体特征、结构、材料或者特点包含于本发明的至少一个实施方式或示例中。在本说明书中，对上述术语的示意性表述不一定指的是相同的实施方式 或示例。而且，描述的具体特征、结构、材料或者特点可以在任何的一个或多个实施方式或示例中以合适的方式结合。
此外，术语“第一”、“第二”仅用于描述目的，而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此，限定有“第一”、“第二”的特征可以明示或者隐含地包括至少一个该特征。在本发明的描述中，“多个”的含义是至少两个，例如两个，三个等，除非另有明确具体的限定。
流程图中或在此以其他方式描述的任何过程或方法描述可以被理解为，表示包括一个或更多个用于实现特定逻辑功能或过程的步骤的可执行指令的代码的模块、片段或部分，并且本发明的优选实施方式的范围包括另外的实现，其中可以不按所示出或讨论的顺序，包括根据所涉及的功能按基本同时的方式或按相反的顺序，来执行功能，这应被本发明的实施例所属技术领域的技术人员所理解。
在流程图中表示或在此以其他方式描述的逻辑和/或步骤，例如，可以被认为是用于实现逻辑功能的可执行指令的定序列表，可以具体实现在任何计算机可读介质中，以供指令执行系统、装置或设备(如基于计算机的系统、包括处理器的系统或其他可以从指令执行系统、装置或设备取指令并执行指令的系统)使用，或结合这些指令执行系统、装置或设备而使用。就本说明书而言，"计算机可读介质"可以是任何可以包含、存储、通信、传播或传输程序以供指令执行系统、装置或设备或结合这些指令执行系统、装置或设备而使用的装置。计算机可读介质的更具体的示例(非穷尽性列表)包括以下：具有一个或多个布线的电连接部(电子装置)，便携式计算机盘盒(磁装置)，随机存取存储器(RAM)，只读存储器(ROM)，可擦除可编辑只读存储器(EPROM或闪速存储器)，光纤装置，以及便携式光盘只读存储器(CDROM)。另外，计算机可读介质甚至可以是可在其上打印所述程序的纸或其他合适的介质，因为可以例如通过对纸或其他介质进行光学扫描，接着进行编辑、解译或必要时以其他合适方式进行处理来以电子方式获得所述程序，然后将其存储在计算机存储器中。
应当理解，本发明的各部分可以用硬件、软件、固件或它们的组合来实现。在上述实施方式中，多个步骤或方法可以用存储在存储器中且由合适的指令执行系统执行的软件或固件来实现。例如，如果用硬件来实现，和在另一实施方式中一样，可用本领域公知的下列技术中的任一项或他们的组合来实现：具有用于对数据信号实现逻辑功能的逻辑门电路的离散逻辑电路，具有合适的组合逻辑门电路的专用集成电路，可编程门阵列(PGA)，现场可编程门阵列(FPGA)等。
本技术领域的普通技术人员可以理解实现上述实施例方法携带的全部或部分步骤 是可以通过程序来指令相关的硬件完成，所述的程序可以存储于一种计算机可读存储介质中，该程序在执行时，包括方法实施例的步骤之一或其组合。
此外，在本发明各个实施例中的各功能单元可以集成在一个处理模块中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。所述集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。上述提到的存储介质可以是只读存储器，磁盘或光盘等。
尽管上面已经示出和描述了本发明的实施例，可以理解的是，上述实施例是示例性的，不能理解为对本发明的限制，本领域的普通技术人员在本发明的范围内可以对上述实施例进行变化、修改、替换和变型。

Claims (12)

  1. 一种指纹识别系统，其特征在于，包括指纹传感器、判断单元及处理单元；
    该指纹传感器用于采集用户滑动录入的多帧指纹图像；
    该判断单元用于判断该多帧指纹图像中当前帧指纹图像与前一帧指纹图像是否有第一重叠区域；
    若是，该判断单元还用于将在该当前帧指纹图像中的该第一重叠区域去掉并将去掉该第一重叠区域后的该当前帧指纹图像与该前一帧指纹图像像叠加形成叠加指纹图像；
    或该判断单元用于将在该前一帧指纹图像中的该第一重叠区域去掉并将去掉该第一重叠区域后的该前一帧指纹图像与该当前帧指纹图像叠加形成该叠加指纹图像；
    该判断单元还用于判断后一帧指纹图像与该叠加指纹图像是否有第二重叠区域，直至完成该多帧指纹图像的判断并得到一幅模板指纹图像；
    若否，该指纹传感器用于重新采集用户滑动录入的该多帧指纹图像；
    该处理单元用于提取并保存该幅模板指纹图像的特征点；
    该指纹传感器还用于采集用户按压录入的待识别指纹图像，该处理单元用于提取该待识别指纹图像的特征点并判断该待识别指纹图像的特征点与该幅模板指纹图像的特征点是否匹配；
    若是，该处理单元用于识别该待识别指纹图像为匹配指纹图像，若否，该处理单元用于识别该待识别指纹图像为非匹配指纹图像。
  2. 如权利要求1所述的指纹识别系统，其特征在于，该处理单元用于对该幅模板指纹图像进行图像滤波处理、二值化处理及细化处理后提取该幅模板指纹图像的该特征点。
  3. 如权利要求1或权利要求2所述的指纹识别系统，其特征在于，该前一帧指纹图像包括前一帧图像部分，该当前帧指纹图像包括多个当前帧图像部分，该判断单元用于计算该前一帧图像部分的第一灰度分别与该多个当前帧图像部分的多个第二灰度的灰度差以得到多个灰度差，并比较该多个灰度差；
    若其中一个第二灰度与该第一灰度的灰度差为该多个灰度差中的最小值且最小值的该灰度差小于阈值，则该判断单元用于判断该其中一个第二灰度所对应的其中一个 当前帧图像部分为该第一重叠区域。
  4. 如权利要求1-3任意一项所述的指纹识别系统，其特征在于，该前一帧指纹图像包括前一帧图像部分，该当前帧指纹图像包括多个当前帧图像部分组合，每个当前帧图像部分组合包括第一当前帧图像部分、第二当前帧图像部分及第三当前帧图像部分；
    该判断单元用于计算该前一帧图像部分的第一灰度分别与在同一个当前帧图像部分组合中的第一当前帧图像部分的第一灰度、第二当前帧图像部分的第二灰度及第三当前帧图像部分的第三灰度的灰度差以分别对应得到第一灰度差、第二灰度差及第三灰度差，计算该第一灰度差、该第二灰度差及该第三灰度差的灰度和值以得到多个灰度和值，比较该多个灰度和值；
    若其中一个当前帧图像部分组合对应的灰度和值为该多个灰度和值中的最小值，则该判断单元用于比较该其中一个当前帧图像部分组合对应的第一灰度差、第二灰度差及第三灰度差；
    若得到最小值的其中一个灰度差且最小值的该其中一个灰度差小于阈值，则该判断单元用于判断最小值的该其中一个灰度差对应的当前帧图像部分为该第一重叠区域。
  5. 一种指纹识别方法，其特征在于，包括步骤：
    S1：指纹传感器采集用户滑动录入的多帧指纹图像；
    S2：判断单元判断该多帧指纹图像中当前帧指纹图像与前一帧指纹图像是否有第一重叠区域，若是则进入步骤S3，若否则返回步骤S1；
    S3：该判断单元将在该当前帧指纹图像中的该第一重叠区域去掉并将去掉该第一重叠区域后的该当前帧指纹图像与该前一帧指纹图像叠加形成叠加指纹图像，或该判断单元将在该前一帧指纹图像中的该第一重叠区域去掉并将去掉该第一重叠区域后的该前一帧指纹图像与该当前帧指纹图像叠加形成该叠加指纹图像；
    S4：该判断单元判断后一帧指纹图像与该叠加指纹图像是否有第二重叠区域，直至完成该多帧指纹图像的判断并得到一幅模板指纹图像；
    S5：处理单元提取并保存该幅模板指纹图像的特征点；
    S6：该指纹传感器采集用户按压录入的待识别指纹图像；
    S7：该处理单元提取该待识别指纹图像的特征点并判断该待识别指纹图像的特征 点与该幅模板指纹图像的特征点是否匹配，若是则进入步骤S8，若否则进入步骤S9；
    S8：该处理单元识别该待识别指纹图像为匹配指纹图像；
    S9：该处理单元识别该待识别指纹图像为非匹配指纹图像。
  6. 如权利要求5所述的指纹识别方法，其特征在于，在步骤S5中，该处理单元对该幅模板指纹图像进行图像滤波处理、二值化处理及细化处理后提取该幅模板指纹图像的该特征点。
  7. 如权利要求5或权利要求6所述的指纹识别方法，其特征在于，在步骤S2中，该前一帧指纹图像包括前一帧图像部分，该当前帧指纹图像包括多个当前帧图像部分，该判断单元计算该前一帧图像部分的第一灰度分别与该多个当前帧图像部分的多个第二灰度的灰度差以得到多个灰度差，并比较该多个灰度差；
    若其中一个第二灰度与该第一灰度的灰度差为该多个灰度差中的最小值且最小值的该灰度差小于阈值，则该判断单元判断该其中一个第二灰度所对应的其中一个当前帧图像部分为该第一重叠区域。
  8. 如权利要求5-7任意一项所述的指纹识别方法，其特征在于，在步骤S2中，该前一帧指纹图像包括前一帧图像部分，该当前帧指纹图像包括多个当前帧图像部分组合，每个当前帧图像部分组合包括第一当前帧图像部分、第二当前帧图像部分及第三当前帧图像部分；
    该判断单元计算该前一帧图像部分的第一灰度分别与在同一个当前帧图像部分组合中的第一当前帧图像部分的第一灰度、第二当前帧图像部分的第二灰度及第三当前帧图像部分的第三灰度以分别对应得到第一灰度差、第二灰度差及第三灰度差，计算该第一灰度差、该第二灰度差及该第三灰度差的灰度和值以得到多个灰度和值，比较该多个灰度和值；
    若其中一个当前帧图像部分组合对应的灰度和值为该多个灰度和值中的最小值，则该判断单元比较该其中一个当前帧图像部分组合对应的第一灰度差、第二灰度差及第三灰度差；
    若得到最小值的灰度差且最小值的该灰度差小于阈值，则该判断单元判断最小值的该灰度差对应的当前帧图像部分为该第一重叠区域。
  9. 一种电子设备，其特征在于，包括指纹识别系统，该指纹识别系统包括指纹传感器、判断单元及处理单元；
    该指纹传感器用于采集用户滑动录入的多帧指纹图像；
    该判断单元用于判断该多帧指纹图像中当前帧指纹图像与前一帧指纹图像是否有第一重叠区域；
    若是，该判断单元还用于将在该当前帧指纹图像中的该第一重叠区域去掉并将去掉该第一重叠区域后的该当前帧指纹图像与该前一帧指纹图像叠加形成叠加指纹图像；
    或该判断单元用于将在该前一帧指纹图像中的该第一重叠区域去掉并将去掉该第一重叠区域后的该前一帧指纹图像与该当前帧指纹图像叠加形成该叠加指纹图像；
    该判断单元还用于判断后一帧指纹图像与该叠加指纹图像是否有第二重叠区域直至完成该多帧指纹图像的判断并得到一幅模板指纹图像；
    该处理单元用于提取并保存该幅模板指纹图像的特征点；
    若否，该指纹传感器用于重新采集用户滑动录入的该多帧指纹图像；
    该指纹传感器还用于采集用户按压录入的待识别指纹图像；
    该处理单元用于提取该待识别指纹图像的特征点并判断该待识别指纹图像的特征点与该幅模板指纹图像的特征点是否匹配；
    若是，该处理单元用于识别该待识别指纹图像为匹配指纹图像，若否，该处理单元用于识别该待识别指纹图像为非匹配指纹图像。
  10. 如权利要求9所述的电子设备，其特征在于，该处理单元用于对该幅模板指纹图像进行图像滤波处理、二值化处理及细化处理后提取该幅模板指纹图像的该特征点。
  11. 如权利要求9或权利要求10所述的电子设备，其特征在于，该前一帧指纹图像包括前一帧图像部分，该当前帧指纹图像包括多个当前帧图像部分，该判断单元用于计算该前一帧图像部分的第一灰度分别与该多个当前帧图像部分的多个第二灰度的灰度差以得到多个灰度差，并比较该多个灰度差；
    若其中一个第二灰度与该第一灰度的灰度差为该多个灰度差中的最小值且最小值的该灰度差小于阈值，则该判断单元用于判断该其中一个第二灰度所对应的其中一个 当前帧图像部分为该第一重叠区域。
  12. 如权利要求9-11任意一项所述的电子设备，其特征在于，该前一帧指纹图像包括前一帧图像部分，该当前帧指纹图像包括多个当前帧图像部分组合，每个当前帧图像部分组合包括第一当前帧图像部分、第二当前帧图像部分及第三当前帧图像部分；
    该判断单元用于计算该前一帧图像部分的第一灰度分别与在同一个当前帧图像部分组合中的第一当前帧图像部分的第一灰度、第二当前帧图像部分的第二灰度及第三当前帧图像部分的第三灰度的灰度差以分别对应得到第一灰度差、第二灰度差及第三灰度差，计算该第一灰度差、该第二灰度差及该第三灰度差的灰度和值以得到多个灰度和值，比较该多个灰度和值；
    若其中一个当前帧图像部分组合对应的灰度和值为该多个灰度和值中的最小值，则该判断单元用于比较该其中一个当前帧图像部分组合对应的第一灰度差、第二灰度差及第三灰度差；
    若得到最小值的其中一个灰度差且最小值的该其中一个灰度差小于阈值，则该判断单元用于判断最小值的该其中一个灰度差对应的当前帧图像部分为该第一重叠区域。
PCT/CN2015/093728 2014-12-19 2015-11-03 指纹识别系统及指纹识别方法及电子设备 Ceased WO2016095615A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US15/537,707 US10366274B2 (en) 2014-12-19 2015-11-03 Fingerprint identification system, fingerprint identification method, and electronic equipment
EP15869125.3A EP3236386A4 (en) 2014-12-19 2015-11-03 Fingerprint recognition system and fingerprint recognition method and electronic device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410799636.7A CN105447436B (zh) 2014-12-19 2014-12-19 指纹识别系统及指纹识别方法及电子设备
CN201410799636.7 2014-12-19

Publications (1)

Publication Number Publication Date
WO2016095615A1 true WO2016095615A1 (zh) 2016-06-23

Family

ID=55557596

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/093728 Ceased WO2016095615A1 (zh) 2014-12-19 2015-11-03 指纹识别系统及指纹识别方法及电子设备

Country Status (5)

Country Link
US (1) US10366274B2 (zh)
EP (1) EP3236386A4 (zh)
CN (1) CN105447436B (zh)
TW (1) TWI591546B (zh)
WO (1) WO2016095615A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109740430A (zh) * 2018-11-27 2019-05-10 Oppo广东移动通信有限公司 指纹录入方法及相关设备

Families Citing this family (33)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10713466B2 (en) 2014-03-07 2020-07-14 Egis Technology Inc. Fingerprint recognition method and electronic device using the same
WO2017091933A1 (zh) * 2015-11-30 2017-06-08 宇龙计算机通信科技(深圳)有限公司 一种指纹采集方法、装置及电子设备
CN106062778B (zh) * 2016-04-01 2019-05-07 深圳市汇顶科技股份有限公司 指纹识别方法、装置和终端
WO2017214793A1 (zh) * 2016-06-13 2017-12-21 北京小米移动软件有限公司 指纹模板生成方法及装置
CN106201288B (zh) * 2016-07-04 2019-08-30 Oppo广东移动通信有限公司 一种指纹信息的存储方法、装置及移动终端
CN106355150A (zh) * 2016-08-31 2017-01-25 成都市和平科技有限责任公司 一种具备通用性的指纹识别系统及方法
CN106650569B (zh) * 2016-09-05 2019-08-16 北京小米移动软件有限公司 指纹录入方法及装置
EP3608809B1 (en) * 2017-04-26 2023-10-04 Huawei Technologies Co., Ltd. Device power-on method using power button integrated with fingerprint sensor
CN107550481A (zh) * 2017-08-24 2018-01-09 京东方科技集团股份有限公司 一种便携设备及血压测量方法
CN109543492A (zh) * 2017-09-21 2019-03-29 比亚迪股份有限公司 指纹录入方法和装置
TWI676911B (zh) * 2017-10-12 2019-11-11 神盾股份有限公司 指紋識別方法以及使用指紋識別方法的電子裝置
SE1751569A1 (en) * 2017-12-18 2019-06-19 Fingerprint Cards Ab Method and device for classifying fingerprint
CN108764127A (zh) 2018-05-25 2018-11-06 京东方科技集团股份有限公司 纹理识别方法及其装置
KR102656237B1 (ko) * 2018-09-21 2024-04-09 엘지디스플레이 주식회사 디스플레이를 이용한 이동 지문 인식 방법 및 장치
CN111259685B (zh) * 2018-11-30 2024-06-21 上海耕岩智能科技有限公司 一种指纹重建方法及存储介质
CN111259692B (zh) * 2018-11-30 2024-06-18 上海耕岩智能科技有限公司 一种生物特征分析方法、存储介质及神经网络
CN109543664A (zh) * 2019-01-16 2019-03-29 广州三星通信技术研究有限公司 指纹采集方法和设备
CN110020591B (zh) * 2019-02-01 2023-11-14 敦泰电子有限公司 基于滑动式采样的指纹模板注册方法及指纹识别装置
CN109993141B (zh) * 2019-04-10 2021-09-03 京东方科技集团股份有限公司 一种oled显示面板、指纹识别方法和显示装置
CN110717168A (zh) * 2019-09-23 2020-01-21 联想(北京)有限公司 一种生物信息录入方法、电子设备及计算机存储介质
TWI762007B (zh) * 2019-12-26 2022-04-21 神盾股份有限公司 手勢辨識系統以及手勢辨識方法
CN111209556A (zh) * 2020-01-14 2020-05-29 北京集创北方科技股份有限公司 鉴权装置及电子设备
EP4143740A4 (en) * 2020-04-30 2024-05-22 Fingerprint Cards Anacatum IP AB FINGERPRINT REGISTRATION METHOD AND SYSTEM
CN113971771A (zh) * 2020-07-22 2022-01-25 大金工业株式会社 故障识别与应对方法及系统
CN114724192B (zh) * 2021-01-05 2025-09-09 上海耕岩智能科技有限公司 指纹模组的成像方法和成像装置
CN113657262B (zh) * 2021-08-16 2024-07-12 深圳市利顺和科技有限公司 启动终端识别生物特征信息的方法、装置、终端及介质
US20230073477A1 (en) * 2021-09-03 2023-03-09 Egis Technology Inc. Method, device, mobile device, and computer-readable medium for fingerprint authentication
CN115841684A (zh) * 2022-10-19 2023-03-24 北京迈格威科技有限公司 指纹滑动录入方法、电子设备和计算机可读介质
CN117912064A (zh) * 2022-12-30 2024-04-19 华为技术有限公司 一种指纹录入方法及相关装置
CN116469134B (zh) * 2023-03-31 2026-01-09 天津极豪科技有限公司 指纹录入方法、电子设备及存储介质
CN119229485A (zh) * 2023-06-30 2024-12-31 荣耀终端有限公司 一种指纹录入方法及电子设备
CN117238000A (zh) * 2023-08-23 2023-12-15 北京集创北方科技股份有限公司 指纹识别方法、触摸数据处理装置及终端
CN119274242B (zh) * 2024-01-29 2025-11-14 荣耀终端股份有限公司 一种指纹图像处理方法和终端设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1172308A (zh) * 1996-06-14 1998-02-04 汤姆森-无线电报总公司 指纹读取系统
JP2003331269A (ja) * 2002-05-14 2003-11-21 Matsushita Electric Ind Co Ltd 画像処理装置、画像処理方法及びプログラム
CN1804862A (zh) * 2006-01-18 2006-07-19 北京飞天诚信科技有限公司 指纹图像片段的拼接方法
CN101079087A (zh) * 2006-05-26 2007-11-28 祥群科技股份有限公司 具有滑动式指纹感测芯片的计算机无线外围设备
CN101145198A (zh) * 2007-09-21 2008-03-19 清华大学 指纹识别中确定性编码方法与系统

Family Cites Families (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR2774793B1 (fr) * 1998-02-12 2002-08-30 Bull Cp8 Procede pour produire une image au moyen d'un objet portatif, objet portatif et dispositif pour mettre en oeuvre le procede
WO2002009034A1 (fr) * 2000-07-24 2002-01-31 Kabushiki Kaisha Dds Dispositif, procede et programme de collationnement d'empreintes digitales
AU2002316679A1 (en) * 2001-07-12 2003-01-29 Atrua Technologies, Inc. Method and system for biometric image assembly from multiple partial biometric frame scans
US20030123714A1 (en) * 2001-11-06 2003-07-03 O'gorman Lawrence Method and system for capturing fingerprints from multiple swipe images
EP1671260B1 (en) * 2003-10-01 2014-06-11 Authentec, Inc. Methods for finger biometric processing and associated finger biometric sensors
CN1299230C (zh) * 2003-11-10 2007-02-07 北京握奇数据系统有限公司 一种基于互信息的指纹特征匹配方法
US20060093192A1 (en) * 2004-11-03 2006-05-04 Bechtel J S Finger guide device
TW200625193A (en) * 2005-01-11 2006-07-16 Elecvision Inc Fingerprint detecting method
CA2598482C (en) * 2005-02-17 2012-04-17 Authentec, Inc. Finger sensor apparatus using image resampling and associated methods
CN101005353B (zh) * 2006-12-29 2010-06-23 北京飞天诚信科技有限公司 一种实现定位和导航功能的智能密钥设备
JP5040835B2 (ja) * 2008-07-04 2012-10-03 富士通株式会社 生体情報読取装置、生体情報読取方法および生体情報読取プログラム
US9477874B2 (en) * 2010-04-23 2016-10-25 Handscape Inc. Method using a touchpad for controlling a computerized system with epidermal print information
US20130076880A1 (en) * 2011-09-23 2013-03-28 Lite-On Singapore Pte. Ltd. Image processing method and image capturing system
JP5812109B2 (ja) * 2011-12-15 2015-11-11 富士通株式会社 生体情報処理装置、生体情報処理方法及び生体情報処理用コンピュータプログラム
KR20150034832A (ko) * 2013-09-24 2015-04-06 삼성전자주식회사 지문인식 센서를 포함하는 전자기기 및 지문인식 센서를 포함하는 전자기기의 사용자 인증 수행 및 사용자 지문 이미지 등록 방법, 및 이 방법을 실행하기 위한 프로그램이 기록되어 있는 비휘발성 기록매체
NO20140653A1 (no) * 2014-05-27 2015-11-30 Idex Asa Biometrisk sensor
CN104156709B (zh) * 2014-08-26 2019-07-16 南昌欧菲生物识别技术有限公司 指纹识别检测组件、终端设备及指纹验证方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1172308A (zh) * 1996-06-14 1998-02-04 汤姆森-无线电报总公司 指纹读取系统
JP2003331269A (ja) * 2002-05-14 2003-11-21 Matsushita Electric Ind Co Ltd 画像処理装置、画像処理方法及びプログラム
CN1804862A (zh) * 2006-01-18 2006-07-19 北京飞天诚信科技有限公司 指纹图像片段的拼接方法
CN101079087A (zh) * 2006-05-26 2007-11-28 祥群科技股份有限公司 具有滑动式指纹感测芯片的计算机无线外围设备
CN101145198A (zh) * 2007-09-21 2008-03-19 清华大学 指纹识别中确定性编码方法与系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3236386A4 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109740430A (zh) * 2018-11-27 2019-05-10 Oppo广东移动通信有限公司 指纹录入方法及相关设备
CN109740430B (zh) * 2018-11-27 2021-05-11 Oppo广东移动通信有限公司 指纹录入方法及相关设备

Also Published As

Publication number Publication date
EP3236386A1 (en) 2017-10-25
US20180005014A1 (en) 2018-01-04
TW201624348A (zh) 2016-07-01
TWI591546B (zh) 2017-07-11
CN105447436A (zh) 2016-03-30
US10366274B2 (en) 2019-07-30
EP3236386A4 (en) 2017-11-29
CN105447436B (zh) 2017-08-04

Similar Documents

Publication Publication Date Title
WO2016095615A1 (zh) 指纹识别系统及指纹识别方法及电子设备
TWI619080B (zh) 指紋重疊區域面積的計算方法及電子裝置
KR101909971B1 (ko) 지문 식별 방법 및 지문 식별 장치
US10558841B2 (en) Method and apparatus for recognizing fingerprint ridge point
CN102870135B (zh) 用于形状提取的方法和装置、尺寸测量装置和距离测量装置
KR20170061631A (ko) 영역 인식 방법 및 장치
WO2018058595A1 (zh) 目标检测方法、装置以及计算机系统
KR20170061630A (ko) 영역 추출 방법 및 장치
US11017552B2 (en) Measurement method and apparatus
CN105007422B (zh) 一种相位对焦方法及用户终端
CN111291601A (zh) 车道线识别方法和装置以及电子设备
CN115719521A (zh) 一种指纹图像录入的方法、存储介质及电子设备
US10248835B2 (en) Methods and apparatuses for authentication using biometric information
WO2017096930A1 (zh) 控制方法、控制装置及电子装置
US9204037B2 (en) Method and apparatus for photographing in portable terminal
WO2017185507A1 (zh) 一种多指纹的识别方法及装置
US20180349670A1 (en) Biometric information process device, biometric information process method, computer-readable non-transitory medium and distance detection device
CN105956535A (zh) 指纹识别控制方法、指纹识别控制装置及电子装置
KR101541384B1 (ko) 영상 인식 장치 및 방법
US9286682B1 (en) Aligning multi-view scans
EP2887261B1 (en) Information processing device, information processing method, and program
CN103227864B (zh) 一种检测图像边缘的方法和移动终端
KR101660596B1 (ko) 안면 형상 기울기 보정 방법 및 보정 시스템
JP6554820B2 (ja) 画像処理プログラム、画像処理装置、及び画像処理方法
WO2017113735A1 (zh) 一种视频格式区分方法及系统

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: 15869125

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 15537707

Country of ref document: US

REEP Request for entry into the european phase

Ref document number: 2015869125

Country of ref document: EP