WO2016127736A1 - 指纹重叠区域面积的计算方法及电子装置 - Google Patents

指纹重叠区域面积的计算方法及电子装置 Download PDF

Info

Publication number
WO2016127736A1
WO2016127736A1 PCT/CN2016/070193 CN2016070193W WO2016127736A1 WO 2016127736 A1 WO2016127736 A1 WO 2016127736A1 CN 2016070193 W CN2016070193 W CN 2016070193W WO 2016127736 A1 WO2016127736 A1 WO 2016127736A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
fingerprint image
matched
overlapping area
area
Prior art date
Application number
PCT/CN2016/070193
Other languages
English (en)
French (fr)
Inventor
雷磊
徐坤平
杨云
Original Assignee
比亚迪股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 比亚迪股份有限公司 filed Critical 比亚迪股份有限公司
Priority to KR1020177022459A priority Critical patent/KR101912420B1/ko
Priority to EP16748537.4A priority patent/EP3258416A4/en
Priority to JP2017542174A priority patent/JP6511149B2/ja
Priority to US15/549,121 priority patent/US20180018499A1/en
Publication of WO2016127736A1 publication Critical patent/WO2016127736A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12—Fingerprints or palmprints
    • G06V40/1335—Combining adjacent partial images (e.g. slices) to create a composite input or reference pattern; Tracking a sweeping finger movement
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/60—Analysis of geometric attributes
    • G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
    • G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12—Fingerprints or palmprints
    • G06V40/1347—Preprocessing; Feature extraction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12—Fingerprints or palmprints
    • G06V40/1365—Matching; Classification

Definitions

  • the present invention relates to the field of fingerprint recognition, and more particularly to a method for calculating the area of a fingerprint overlapping area and an electronic device.
  • the fingerprint of the entire finger may not be recorded during the fingerprint entry phase.
  • the fingerprints collected during the subsequent use process only partially coincide with the fingerprints entered.
  • the probability that a fingerprint fingerprint of a different person's finger is similar is one in 7 billion, but if it is only a small part of the entire fingerprint, different fingerprints have a high probability of local similarity.
  • the matching feature points are not only a small number, but also the distance is too close, the matching reliability is very low, and it is easy to be misunderstood. Therefore, it is necessary to calculate the overlapping area to judge the feature. Whether the point matching is reliable.
  • the area obtained by the above method is affected by the distribution of feature points.
  • the area obtained by the above method is close to the true overlapping area.
  • the area obtained by the above method is much smaller than the overlap area.
  • the area obtained by the above method may be larger than the real overlapping area.
  • the fingerprint image has a certain rotation angle, and the acquired fingerprint and the rectangular area taken by the entered fingerprint may be too different, and the obtained area is not accurate.
  • 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 method for calculating the area of the overlapping area of the fingerprint and an electronic device.
  • a method for calculating the area of a fingerprint overlapping area includes the following steps:
  • the area of the overlapping area of an arbitrary shape can be calculated, and the obtained area is accurate to the pixel. Level, the obtained area is more accurate, which is convenient for later calculation, which makes the fingerprint matching more accurate and improves the user experience.
  • the step of searching for a plurality of pairs of matching feature points in the fingerprint image to be matched and the preset template fingerprint image includes the following steps:
  • the image offset includes at least one of a rotation angle and a translation amount.
  • the step of calculating the number of image pixel points in the overlapping area and calculating the area of the overlapping area according to the number of image pixel points in the overlapping area comprises: according to the preset template fingerprint The image establishes a coordinate system; determining that image pixel points in the fingerprint image to be matched within the coordinate range of the preset template fingerprint image belong to image pixel points in the overlapping area; and counting the number of image pixel points in the overlapping area, Calculating a ratio of the number of image pixel points in the overlapping area to the number of image pixel points in the preset template fingerprint image, and calculating an area of the overlapping area according to the ratio.
  • the step of determining that an image pixel in the fingerprint image to be matched in the preset template fingerprint image coordinate belongs to an image pixel in the overlapping region is specifically determined to satisfy X1 ⁇
  • the image pixel points in the to-be-matched fingerprint image of X ⁇ X2 and Y1 ⁇ Y ⁇ Y2 belong to image pixel points in the overlapping area, where X is the horizontal of the image pixel point in the to-be-matched fingerprint image in the coordinate system Coordinate, Y is the ordinate of the image pixel in the fingerprint image to be matched in the coordinate system, X1 ⁇ X2 is the preset template fingerprint image in the horizontal coordinate range of the coordinate system, Y1 ⁇ Y2 is the preset template fingerprint The image is in the ordinate range of the coordinate system, and
  • is the image resolution of the preset template fingerprint image.
  • S is the area of the overlap region
  • Sa is the area of the preset template fingerprint image
  • N is the overlap region.
  • the number of image pixels within the image, Ns is the number of image pixels in the preset template fingerprint image.
  • An electronic device includes an acquisition module and a processing module.
  • the acquisition module is configured to collect a fingerprint to be matched and obtain a fingerprint image to be matched.
  • the processing module is configured to search for a plurality of pairs of matched feature points in the to-be-matched fingerprint image and the preset template fingerprint image, and obtain an image offset of the fingerprint image to be matched according to the plurality of pairs of matched feature points, and use the image Offset, adjusting a position of the fingerprint image to be matched, obtaining an overlapping area of the fingerprint image to be matched and the preset template fingerprint image, and counting the number of image pixel points in the overlapping area, and according to the overlapping area The number of image pixels calculates the area of the overlap region.
  • the processing module is specifically configured to: after performing filtering enhancement, binarization, and refinement operations on the to-be-matched fingerprint image, extracting a plurality of first feature points; and in the preset template fingerprint image A plurality of second feature points respectively matching the plurality of first feature points are found in the feature points.
  • the image offset includes at least one of a rotation angle and a translation amount.
  • the processing module is configured to establish a coordinate system according to the preset template fingerprint image, and determine that image pixel points in the to-be-matched fingerprint image that are located in the preset template fingerprint image coordinate range belong to the overlapping region.
  • the processing module is further configured to determine that image pixel points in the to-be-matched fingerprint image satisfying X1 ⁇ X ⁇ X2 and Y1 ⁇ Y ⁇ Y2 belong to image pixel points in the overlapping area, where X The pixel of the image in the fingerprint image to be matched is in the abscissa of the coordinate system, Y is the image pixel point in the fingerprint image to be matched in the coordinate coordinate of the coordinate system, and X1 to X2 are the fingerprint image of the preset template.
  • the abscissa range of the coordinate system, Y1 ⁇ Y2 is the ordinate coordinate of the preset template fingerprint image in the coordinate system, and
  • is the image resolution of the preset template fingerprint image.
  • S is the area of the overlap region
  • Sa is the area of the preset template fingerprint image
  • N is the overlap region.
  • the number of image pixels within the image, Ns is the number of image pixels in the preset template fingerprint image.
  • FIG. 1 is a schematic flow chart of a method for calculating an area of a fingerprint overlapping area according to a preferred embodiment of the present invention
  • FIG. 2 is another schematic flowchart of a method for calculating an area of a fingerprint overlapping area according to a preferred embodiment of the present invention
  • FIG. 3 is a schematic diagram showing the principle of calculating a fingerprint overlap area according to a preferred embodiment of the present invention.
  • FIG. 4 is a schematic diagram of a fingerprint image used in a method for calculating an area of a fingerprint overlapping area according to a preferred embodiment of the present invention
  • FIG. 5 is a schematic diagram of a method for calculating a coordinate area of a fingerprint overlapping area according to a preferred embodiment of the present invention
  • FIG. 6 is a schematic block diagram of an electronic device according to a preferred embodiment of the present invention.
  • FIG. 7 is a schematic plan view of an electronic device in accordance with 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 method for calculating an area of a fingerprint overlapping area includes the following steps:
  • S11 collecting a fingerprint to be matched and obtaining a fingerprint image to be matched
  • S12 Searching for a plurality of pairs of matching feature points in the to-be-matched fingerprint image and the preset template fingerprint image;
  • S15 Count the number of image pixel points in the overlapping area, and calculate the area of the overlapping area according to the number of image pixel points in the overlapping area.
  • the finger may be pressed on the fingerprint sensor according to the prompt.
  • the fingerprint sensor may be installed on an electronic device such as a mobile phone, a tablet computer, an audio player or a video player, and the fingerprint sensor.
  • the collection window can be set at the front, side or back of the electronic device.
  • the preset template fingerprint image 102 may be, for example, pre-stored in the electronic device before being acquired.
  • the template fingerprint is pre-recorded by the fingerprint sensor of the electronic device.
  • a plurality of preset template fingerprint images 102 are formed. In the subsequent fingerprint matching, only the fingerprint matching the preset template fingerprint image 102 can enable the corresponding function. In particular, if there are multiple preset template fingerprint images, each of the preset template fingerprint images may be respectively matched.
  • step S12 includes the following steps:
  • S21 Filtering, binarizing, and refining the to-be-matched fingerprint image to extract a plurality of first feature points; wherein, the plurality of first feature points refers to at least two first feature points.
  • S22 Search for, in the feature points of the preset template fingerprint image, a plurality of second feature points respectively matching the plurality of first feature points according to the first feature point.
  • the plurality of second feature points refers to at least two second feature points.
  • the binarization process generally refers to setting the ridge line gradation of the fingerprint image to 0 and the valley line to 255 by a series of image processes to form an image having only two kinds of gradation values.
  • the fingerprint image is collected as a related art in the field of fingerprint recognition, and will not be developed in detail here.
  • the feature parts of some fingerprints are extracted as feature points.
  • These feature points can be, for example, the ridge end points and the bifurcation points of the fingerprint.
  • the selection of feature points can consider the following factors: 1) feature points have special characteristics different from general features; 2) feature points have relative stability; 3) select feature points as much as possible.
  • step S22 a plurality of second feature points respectively matching the plurality of first feature points are searched for in the feature points of the preset template fingerprint image according to the plurality of first feature points.
  • any feature point is selected as a local center point for both the preset template fingerprint image and the fingerprint image to be matched.
  • the white point Z is a local center point, which obtains three vectors [d, ⁇ , ⁇ ] respectively from the surrounding feature points A, B, and C, and d is the distance between two feature points, and ⁇ represents It is the angle difference between the two feature point directions, and ⁇ represents the angle between the line point direction of the feature point A and the local center point Z and the direction of the feature point A, wherein the feature point direction refers to the tangential direction of the ridge line at the position where the feature point is located.
  • the feature point mutual relationship refers to information such as the distance between the feature points and the angle difference.
  • the feature point Mi in the preset template fingerprint image is taken as a local center point, and the correlation vector with the surrounding feature points is calculated.
  • the feature point Nj in the fingerprint image to be matched is taken as a local center point, and the correlation vector with the surrounding feature points is calculated.
  • i and j are feature point numbers.
  • a relationship vector between Mi and surrounding feature points A1, B1, and C1 is obtained, which are respectively recorded as V MiA1 , V MiB1 , and V MiC1 ;
  • the relationship vectors between Nj and the surrounding feature points A2, B2, and C2 are obtained, and are respectively recorded as V NjA2 , V NjB2 , and V NjC2 .
  • the feature point Mi and the feature point Nj are considered to be a pair of matched feature points.
  • Nj is a matching feature point of the fingerprint image 100 to be matched.
  • the logarithm of the matched feature points can be determined according to actual requirements, for example, 10 pairs.
  • the image shift amount is obtained from the angle difference between the matching feature point directions and the distance between the feature points.
  • the image offset includes at least one of a rotation angle and a translation amount.
  • the position of the preset template fingerprint image 102 can be fixed, and the position of the fingerprint image 100 to be matched is adjusted.
  • the to-be-matched fingerprint image 100 has a rotation offset and a translation offset relative to the preset template fingerprint image 102, and the image offset includes the rotation angle and the translation amount.
  • the image offset includes a rotation angle; if the fingerprint image 100 to be matched is relative to the preset template fingerprint image There is only a translation offset of 102, then the image offset includes the translation amount; in a few cases, if the fingerprint image 100 to be matched does not have an offset with respect to the preset template fingerprint image 102, the image offset is zero.
  • step S14 according to the rotation angle and the translation amount calculated in step S13, the same rotation translation is performed on the fingerprint image 100 to be matched, so that the matching fingerprint image 100 coincides with the matching feature points in the preset template fingerprint image 102.
  • the fingerprint image with lighter color is the preset template fingerprint image 102
  • the fingerprint image with darker color is the fingerprint image 100 to be matched.
  • the matching fingerprint image 100 is adjusted to position the matching feature points in the two fingerprint images, the overlapping regions 104 of the two images are irregularly shaped (the area enclosed by the solid line in FIG. 4).
  • step S15 as can be seen from Fig. 4, the overlapping region 104 has an irregular shape, and the accurate area cannot be obtained by geometric methods.
  • Step S15 can determine whether it is in the overlap region 104 by the coordinates of the image pixel point of the fingerprint image, and then count the number of image pixel points in the overlap region 104.
  • the resolution of the preset template fingerprint image 102 is equal to the resolution of the fingerprint image 100 to be matched.
  • a coordinate system is established according to the preset template fingerprint image 102.
  • the lower left corner of the preset template fingerprint image 102 is taken as the origin, and the boundary of the adjacent two connections is the axis to establish a coordinate system, as shown in FIG. 5.
  • the resolution of the fingerprint image is
  • Xe*Ye
  • Ns Xe*Ye.
  • the image pixel point of the to-be-matched fingerprint image in the preset template fingerprint image coordinate range is an image pixel point where the overlapping area is located, that is, first determined to be located within the coordinate range of the preset template fingerprint image 102.
  • the image pixel points in the fingerprint image 100 to be matched are then determined to be image pixel points in the overlapping region 104 that are located in the fingerprint image 100 to be matched within the coordinate range.
  • only the image pixel points in the fingerprint image 100 to be matched within the position range of the preset template fingerprint image 102 are the image pixel points in the overlap region 104.
  • the coordinate range is a range of positions in which the preset template fingerprint image 102 is located, that is, an abscissa range of 0 to Xe, and an ordinate range of 0 to Ye, that is, a resolution range of the preset template fingerprint image 102.
  • the X coordinate of the image pixel of the overlapping region in the fingerprint image 100 to be matched is within 0 to Xe, and the Y coordinate Within 0 ⁇ Ye.
  • the pixel coordinates of the image where the non-overlapping region of the fingerprint image 100 to be matched is located are less than 0 or greater than Xe and Ye. Therefore, when the position of the fingerprint image 100 to be matched is adjusted to the position shown in FIG. 5, the image pixel point in the fingerprint image 100 to be matched that satisfies 0 ⁇ X ⁇ Xe and 0 ⁇ Y ⁇ Xe is in the overlap region 104. Image pixel point.
  • the coordinates of all the image pixel points in the fingerprint image 100 to be matched are determined, and the number N of image pixel points whose abscissa is 0 ⁇ X ⁇ Xe and the ordinate is in the range of 0 ⁇ Y ⁇ Ye is calculated, and the overlap region is calculated.
  • the area S, Sa of the overlap area 104 is the area of the preset template fingerprint image 102, and N/Ns is the ratio.
  • step S15 the feature that the digital image is composed of one image pixel is utilized, and the image pixel coordinates of the overlapping region 104 in the fingerprint image 100 to be matched after the rotation translation are all within the Xe*Ye resolution range, The number of image pixel points that satisfy the coordinate range is counted to calculate the area of the overlapping area such as an irregular geometry.
  • the abscissa of the image pixel in the overlap region 104 in the fingerprint image 100 to be matched satisfies: 0 ⁇ X ⁇ 100
  • the ordinate of the image pixel in the overlap region in the fingerprint image 100 to be matched satisfies: 0 ⁇ Y ⁇ 100, that is, the X coordinate and the Y coordinate of the image pixel in the overlapping region in the fingerprint image 100 to be matched are in the range of 0 to 100.
  • the area of the overlapping area of an arbitrary shape can be calculated, and The area is accurate to the pixel level, and the obtained area is more accurate, which is convenient for later calculation, which makes the fingerprint matching more accurate and improves the user experience.
  • the electronic device 200 of the preferred embodiment of the present invention includes an acquisition module 202 and a processing module 204.
  • the collecting module 202 is configured to collect a fingerprint to be matched and obtain a fingerprint image to be matched.
  • the acquisition module 202 can be coupled to the fingerprint sensor 206 to obtain a fingerprint image.
  • the electronic device 200 is described by taking a mobile phone as an example. It can be understood that in other embodiments, the electronic device 200 can also be an electronic device that requires fingerprint recognition, such as a tablet computer, a notebook computer, a smart wearable device, an audio player, or a video player.
  • the acquisition module and the processing module may be disposed inside the electronic device 200.
  • the collection window 208 of the fingerprint sensor 206 is disposed on the front panel 210 of the electronic device 200 to facilitate collection of user fingerprints. Of course, the collection window 208 can also be disposed at other positions on the side and the back of the electronic device 200 according to other requirements.
  • the processing module 204 is configured to extract a plurality of pairs of matching feature points in the fingerprint image to be matched and the preset template fingerprint image, and obtain an image offset according to the plurality of matched feature points, and adjust the image offset by using the image offset
  • the position of the fingerprint image to be matched is obtained, and the overlapping area of the fingerprint image to be matched and the preset template fingerprint image is obtained, and the number of image pixel points in the overlapping area is counted, and the area of the overlapping area is calculated according to the quantity.
  • the calculation method of the area of the overlapping area of the fingerprint may be referred to, and details are not described herein again.
  • the electronic device 200 can calculate the area of the overlapping area of an arbitrary shape by decomposing the overlapping area into a plurality of pixel points and counting the number of pixel points in the overlapping area to calculate the area of the overlapping area.
  • the area is accurate to the pixel level, and the obtained area is more accurate, which is convenient for later calculation, which makes the fingerprint matching more accurate and improves the user experience.
  • 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, solution The program is processed electronically in other suitable ways, if necessary, 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.
  • 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)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Human Computer Interaction (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Geometry (AREA)
  • Collating Specific Patterns (AREA)
  • Image Input (AREA)
  • Image Analysis (AREA)

Abstract

一种指纹重叠区域面积的计算方法及电子装置，该计算方法包括以下步骤：采集待匹配指纹（S11）并得到待匹配指纹图像；在该待匹配指纹图像与预设模板指纹图像中寻找多对匹配的特征点（S12）；根据该多对匹配的特征点获得待匹配指纹图像的图像偏移量；利用该图像偏移量，调整该待匹配指纹图像的位置并得到该待匹配指纹图像与该预设模板指纹图像的重叠区域；统计该重叠区域内的图像像素点的数量以获得该重叠区域的面积。上述计算方法，通过把重叠区域分解为一个个像素点并统计在重叠区域所在像素点的数量来计算重叠区域的面积，求出的面积更准确，方便后面计算，使指纹匹配更准确，提高用户体验。

Description

指纹重叠区域面积的计算方法及电子装置 技术领域
本发明涉及于指纹识别领域，更具体而言，涉及一种指纹重叠区域面积的计算方法及一种电子装置。
背景技术
在指纹识别领域中，由于指纹传感器的面积越来越小，在指纹录入阶段可能没有录完整个手指的指纹。在之后的使用过程中采集的指纹与录入的指纹只有一部分重合。不同人的指纹手指完整指纹相似的概率是70亿分之一，但是如果只是整个指纹的一小部分，不同指纹有很高的概率具有局部相似性。当采集的指纹与录入的指纹的重叠区域面积较小时，匹配的特征点不仅数量较少，而且距离太近，匹配可靠性很低，极容易出现误识，所以需要计算重叠区域面积来判断特征点匹配是否可靠。
目前，要计算两幅匹配指纹的重叠区域的面积，一般的做法是在每个指纹各取一个包含所有匹配特征点的最小矩形，求得这两个矩形的面积S1、S2，取S＝(S1+S2)/2为重叠区域的面积。但是，上述方法求得的面积受特征点分布影响。当特征点分布均匀时，上述方法求得的面积接近真实重叠面积。当特征点分布比较集中时，上述方法求得的面积远小于重叠面积。当特征点分布比较分散时，上述方法求得的面积可能大于真实重叠面积。
而且，由于手指按压指纹传感器的角度不同，指纹图像具有一定的旋转角度，采集的指纹和录入的指纹取的矩形面积可能相差过大，求得的面积不准。
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重叠区域面积的计算方法及一种电子装置。
一种指纹重叠区域面积的计算方法，包括以下步骤：
采集待匹配指纹并得到待匹配指纹图像；
在该待匹配指纹图像与预设模板指纹图像中寻找多对匹配的特征点；
根据该多对匹配的特征点获得待匹配指纹图像的图像偏移量；
利用该图像偏移量，调整该待匹配指纹图像的位置并得到该待匹配指纹图像与该预设模板指纹图像的重叠区域；及
统计该重叠区域内的图像像素点的数量，并根据该重叠区域内的图像像素点的数量计 算该重叠区域的面积。
上述计算方法，通过把重叠区域分解为一个个像素点并统计在重叠区域所在像素点的数量来计算重叠区域的面积，可以计算出任意形状的重叠区域的面积，而且求出的面积精确到像素级，求出的面积更准确，方便后面计算，使指纹匹配更准确，提高用户体验。
在一个实施方式中，在待匹配指纹图像与预设模板指纹图像中寻找多对匹配的特征点步骤,包括以下步骤：
对该待匹配指纹图像进行滤波增强、二值化及细化操作后提取多个第一特征点；
在该预设模板指纹图像的特征点中寻找分别与多个第一特征点相匹配的多个第二特征点。
在一个实施方式中，该图像偏移量包括旋转角度及平移量中的至少一种。
在一个实施方式中，统计所述重叠区域内的图像像素点的数量，并根据所述重叠区域内的图像像素点的数量计算所述重叠区域的面积的步骤具体包括：根据该预设模板指纹图像建立坐标系；判断位于该预设模板指纹图像坐标范围内的该待匹配指纹图像中的图像像素点属于该重叠区域内的图像像素点；及统计该重叠区域内的图像像素点的数量，计算该重叠区域内的图像像素点的数量与该预设模板指纹图像中的图像像素点的数量的比值，并根据该比值计算该重叠区域的面积。
在一个实施方式中，确定位于所述预设模板指纹图像坐标范围内的所述待匹配指纹图像中的图像像素点属于所述重叠区域内的图像像素点的步骤,具体为:确定满足X1<X<X2且Y1<Y<Y2的该待匹配指纹图像中的图像像素点属于该重叠区域内的图像像素点，其中，X为该待匹配指纹图像中的图像像素点在该坐标系的横坐标，Y为该待匹配指纹图像中的图像像素点在该坐标系的纵坐标，X1～X2为该预设模板指纹图像在该坐标系的横坐标范围，Y1～Y2为该预设模板指纹图像在该坐标系的纵坐标范围，|X2-X1|*|Y2-Y1|为该预设模板指纹图像的图像分辨率。
在一个实施方式中，该重叠区域的面积由以下公式确定：S＝Sa*N/Ns，其中，S为该重叠区域的面积，Sa为该预设模板指纹图像的面积，N为该重叠区域内的图像像素点的数量，Ns为该预设模板指纹图像中的图像像素点的数量。
一种电子装置，包括采集模块及处理模块。该采集模块用于采集待匹配指纹并得到待匹配指纹图像。该处理模块用于在该待匹配指纹图像与预设模板指纹图像中寻找多对匹配的特征点，及根据该多对匹配的特征点获得待匹配指纹图像的图像偏移量，及利用该图像偏移量，调整该待匹配指纹图像的位置并得到该待匹配指纹图像与该预设模板指纹图像的重叠区域，及统计该重叠区域内的图像像素点的数量，并根据该重叠区域内的图像像素点的数量计算该重叠区域的面积。
在一个实施方式中，所述处理模块具体用于：对所述待匹配指纹图像进行滤波增强、二值化及细化操作后提取多个第一特征点；在所述预设模板指纹图像的特征点中寻找分别与所述多个第一特征点相匹配的多个第二特征点。
在一个实施方式中，所述图像偏移量包括旋转角度及平移量中的至少一种。
在一个实施方式中，该处理模块用于根据该预设模板指纹图像建立坐标系，确定位于该预设模板指纹图像坐标范围内的该待匹配指纹图像中的图像像素点属于该重叠区域内的图像像素点，及统计该重叠区域内的图像像素点的数量，计算该重叠区域内的图像像素点的数量与该预设模板指纹图像的图像像素点的数量的比值，并根据该比值计算该重叠区域的面积。
在一个实施方式中，所述处理模块还用于确定满足X1<X<X2且Y1<Y<Y2的该待匹配指纹图像中的图像像素点属于该重叠区域内的图像像素点，其中，X为该待匹配指纹图像中的图像像素点在该坐标系的横坐标，Y为该待匹配指纹图像中的图像像素点在该坐标系的纵坐标，X1～X2为该预设模板指纹图像在该坐标系的横坐标范围，Y1～Y2为该预设模板指纹图像在该坐标系的纵坐标范围，|X2-X1|*|Y2-Y1|为该预设模板指纹图像的图像分辨率。
在一个实施方式中，该重叠区域的面积由以下公式确定：S＝Sa*N/Ns，其中，S为该重叠区域的面积，Sa为该预设模板指纹图像的面积，N为该重叠区域内的图像像素点的数量，Ns为该预设模板指纹图像中的图像像素点的数量。
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是本发明较佳实施方式的指纹重叠区域面积的计算方法的流程示意图；
图2是本发明较佳实施方式的指纹重叠区域面积的计算方法的另一流程示意图；
图3是本发明较佳实施方式的指纹重叠区域面积的计算方法的原理示意图；
图4是本发明较佳实施方式的指纹重叠区域面积的计算方法所用到的指纹图像的示意图；
图5是本发明较佳实施方式的指纹重叠区域面积的计算方法建立坐标系的示意图；
图6是本发明较佳实施方式的电子装置的模块示意图；及
图7是本发明较佳实施方式的电子装置的平面示意图。
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～图5，本发明较佳实施方式的指纹重叠区域面积的计算方法包括以下步骤：
S11：采集待匹配指纹并得到待匹配指纹图像；
S12：在该待匹配指纹图像与预设模板指纹图像中寻找多对匹配的特征点；
S13：根据该多对匹配的特征点获得待匹配指纹图像的图像偏移量；
S14：利用该图像偏移量，调整该待匹配指纹图像的位置并得到该待匹配指纹图像与该预设模板指纹图像的重叠区域；
S15：统计该重叠区域内的图像像素点的数量，并根据该重叠区域内的图像像素点的数量计算该重叠区域的面积。
在步骤S11，当用户需要进行指纹匹配时，可根据提示将手指按在指纹传感器上，该指纹传感器例如可以安装在手机，平板电脑，音频播放器或视频播放器等电子装置上，该指纹传感器的采集窗口可设置在电子装置的前面，侧面或背面等位置。
在步骤S12中，其中，多对匹配的特征点指的是至少两对匹配的特征点。预设模板指纹图像102例如可以是要采集前预先储存在电子装置中。在用户使用指纹识别功能时，可 通过在电子装置的指纹传感器预先录入模板指纹。电子装置处理该模板指纹后形成多个预设模板指纹图像102。在后续进行指纹匹配时，只有与该预设模板指纹图像102相匹配的指纹才能启用相应的功能。特别地，如果存在多个预设模板指纹图像，则可分别对每个预设模板指纹图像进行相应的匹配。
进一步地，请参图2，步骤S12包括以下步骤：
S21：对该待匹配指纹图像滤波增强、二值化及细化后提取多个第一特征点；其中，多个第一特征点指的是至少两个第一特征点。
S22：根据该第一特征点在该预设模板指纹图像的特征点中寻找分别与该多个第一特征点相匹配的多个第二特征点。其中，多个第二特征点指的是至少两个第二特征点。
在步骤S21中，二值化处理一般是指通过一系列图像处理把指纹图像的脊线灰度置为0，把谷线置为255，形成只有2种灰度值的图像。采集指纹图像为指纹识别领域相关的现有技术，在此不再详细展开。
在指纹图像中，一些指纹的特征部分会被提取作为特征点。这些特征点例如可以为指纹的脊线端点及分叉点。而特征点的选取可考虑以下因素：1)特征点具有不同于一般特征的特殊性；2)特征点具有相对的稳定性；3)尽量选择组合特征点。
在步骤S22中，根据多个第一特征点在预设模板指纹图像的特征点中寻找分别与多个第一特征点相匹配的多个第二特征点。
具体地，请结合图3，对预设模板指纹图像和待匹配指纹图像均选取任意一特征点作为局部中心点。例如，图3中白点Z为局部中心点，它与其周围特征点A、B、C分别得到3个向量[d,α,β]，d为两个特征点之间的距离，α表示的是两个特征点方向的角度差，β表示的是特征点A和局部中心点Z连线方向与特征点A方向的夹角，其中，特征点方向指该特征点所在位置脊线的切线方向，特征点相互关系指特征点之间的距离及角度差等信息。
比如,以预设模板指纹图像中特征点Mi为作为局部中心点，计算与周围特征点的相互关系向量。再以待匹配指纹图像中特征点Nj为作为局部中心点，计算与周围特征点的相互关系向量。i、j为特征点序号。举例而言，在以预设模板指纹图像中的特征点Mi为局部中心点时，得到Mi与周围特征点A1、B1、C1的关系向量，分别记为VMiA1、VMiB1、VMiC1；在以待匹配指纹图像中的特征点Nj为局部中心点时，得到Nj与周围特征点A2、B2、C2的关系向量，分别记为VNjA2、VNjB2、VNjC2。分别对比向量VMiA1与VNjA2、向量VMiB1与VNjB2、向量VMiC1与VNjC2。如果对向量对比之后，每组相对比的向量中的d、α、β的差值均小于设定阈值则认为特征点Mi和特征点Nj是一对匹配的特征点。Nj为待匹配指纹图像100的匹配的特征点。匹配的特征点的对数可根据实际所求来确定，例如10对。图像偏移量是根据匹配的特 征点方向的角度差及特征点之间的距离求出。图像偏移量包括旋转角度及平移量中的至少一种。
具体的,在得到图像偏移量后，较佳地，可将预设模板指纹图像102的位置固定，而调整待匹配指纹图像100的位置。本实施方式中，待匹配指纹图像100相对于预设模板指纹图像102存在旋转偏移及平移偏移，那么图像偏移量包括旋转角度及平移量。
当然，在其它实施方式中，如果待匹配指纹图像100相对于预设模板指纹图像102只存在旋转偏移，那么图像偏移量包括旋转角度；如果待匹配指纹图像100相对于预设模板指纹图像102只存在平移偏移，那么图像偏移量包括平移量；在少数的情况下，如果待匹配指纹图像100相对于预设模板指纹图像102不存在偏移，那么图像偏移量为零。
在步骤S14中，根据步骤S13中计算得到的旋转角度及平移量，对待匹配指纹图像100作同样的旋转平移，使待匹配指纹图像100与预设模板指纹图像102中的匹配的特征点相重合。请结合图4，为了方便说明，颜色较浅的指纹图像是预设模板指纹图像102，颜色较深的指纹图像是待匹配指纹图像100。对待匹配指纹图像100调整位置使两个指纹图像中的匹配的特征点重合后，这两个图像的重叠区域104为不规则形状(图4实线所围成的区域)。
在步骤S15中，由图4可知，重叠区域104为不规则形状，无法用几何方法求出准确面积。步骤S15可通过指纹图像的图像像素点所在的坐标判断它是否在重叠区域104，进而统计重叠区域104内的图像像素点数量。对于同一个指纹传感器，预设模板指纹图像102的分辨率与待匹配指纹图像100的分辨率相等。
首先，根据预设模板指纹图像102建立坐标系，例如，以预设模板指纹图像102的左下角为原点，相邻两连接的边界为轴建立坐标系，如图5所示。那么，指纹图像的分辨率为|Xe-0|*|Ye-0|＝Xe*Ye，指纹图像的总图像像素点数量Ns＝Xe*Ye。
之后，判断在该预设模板指纹图像坐标范围内的该待匹配指纹图像的图像像素点是该重叠区域所在的图像像素点,也就是说先确定位于该预设模板指纹图像102坐标范围内的该待匹配指纹图像100中的图像像素点,接着确定位于所述坐标范围内的该待匹配指纹图像100中的图像像素点属于该重叠区域104内的图像像素点。在本实施方式中，如图5所示，只有在预设模板指纹图像102的位置范围内的待匹配指纹图像100中的图像像素点才是重叠区域104内的图像像素点。所以坐标范围是预设模板指纹图像102在该坐标系所处的位置范围，即0～Xe的横坐标范围，0～Ye的纵坐标范围，也就是预设模板指纹图像102的分辨率范围。
由图5可知，在调整待匹配指纹图像100的位置使两个指纹图像的匹配的特征点重合后，待匹配指纹图像100中重叠区域的图像像素点的X坐标在0～Xe内，Y坐标在0～Ye内。 而待匹配指纹图像100中非重叠区域所在的图像像素点坐标都小于0或大于Xe、Ye。所以把待匹配指纹图像100的位置调整到如图5所示的位置时，满足0<X<Xe且0<Y<Xe的待匹配指纹图像100中的图像像素点是该重叠区域104内的图像像素点。因此，判断待匹配指纹图像100中的所有图像像素点的坐标，统计横坐标在0<X<Xe且纵坐标在0<Y<Ye范围内的图像像素点的数量N，计算该重叠区域内的图像像素点的数量N与该预设模板指纹图像中的图像像素点的数量Ns的比值，并根据该比值计算该重叠区域的面积S，具体地，根据公式S＝Sa*N/Ns计算重叠区域104的面积S，Sa为该预设模板指纹图像102的面积，N/Ns为该比值。
在步骤S15中,利用了数字图像由一个个图像像素组成这一特性，及旋转平移后待匹配指纹图像100中的重叠区域104的图像像素坐标都在Xe*Ye分辨率范围内的特征，来统计满足坐标范围的图像像素点的数量来计算例如不规则几何形状的重叠区域的面积。
假设Xe＝100，Ye＝100，那么指纹图像的分辨率为100×100，一幅指纹图像的总像素个数Ns＝100×100。待匹配指纹图像100中的重叠区域104内的图像像素点的横坐标满足：0<X<100，且待匹配指纹图像100中的重叠区域内的图像像素点的纵坐标满足：0<Y<100，即待匹配指纹图像100中的重叠区域内的图像像素点的X坐标和Y坐标都在0～100范围内。
综上所述，上述计算方法，通过把重叠区域104分解为一个个像素点并统计在重叠区域所在像素点的数量来计算重叠区域的面积，可以计算出任意形状的重叠区域的面积，而且求出的面积精确到像素级，求出的面积更准确，方便后面计算，使指纹匹配更准确，提高用户体验。
请参图6，本发明较佳实施方式的电子装置200包括采集模块202及处理模块204。
该采集模块202用于采集待匹配指纹并得到待匹配指纹图像。采集模块202可连接至指纹传感器206以得到指纹图像。
请结合图7，本实施方式中，该电子装置200以手机为例进行说明。可以理解，在其它实施方式中，电子装置200可还为平板电脑、笔记本电脑、智能穿戴设备、音频播放器或视频播放器等对指纹识别有需求的电子装置。该采集模块与处理模块可设置在电子装置200的内部。指纹传感器206的采集窗口208设置在电子装置200的前面板210，方便采集用户指纹。当然，采集窗口208还可根据其它需求设置在电子装置200的侧面及背面等的其它位置。
该处理模块204用于提取该待匹配指纹图像与预设模板指纹图像中的多对匹配的特征点，及根据多对匹配的特征点获得图像偏移量，及利用该图像偏移量，调整该待匹配指纹图像的位置并得到该待匹配指纹图像与该预设模板指纹图像的重叠区域，及统计该重叠区域内的图像像素点的数量，并根据该数量计算该重叠区域的面积。
处理模块204具体的处理过程，可参以上指纹重叠区域面积的计算方法，在此不再赘述。
综上所述，上述电子装置200，通过把重叠区域分解为一个个像素点并统计在重叠区域所在像素点的数量来计算重叠区域的面积，可以计算出任意形状的重叠区域的面积，而且求出的面积精确到像素级，求出的面积更准确，方便后面计算，使指纹匹配更准确，提高用户体验。
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 (13)

  1. 一种指纹重叠区域面积的计算方法，其特征在于，包括以下步骤：
    采集待匹配指纹并得到待匹配指纹图像；
    在所述待匹配指纹图像与预设模板指纹图像中寻找多对匹配的特征点；
    根据所述多对匹配的特征点获得所述待匹配指纹图像的图像偏移量；
    利用所述图像偏移量，调整所述待匹配指纹图像的位置并得到所述待匹配指纹图像与所述预设模板指纹图像的重叠区域；及
    统计所述重叠区域内的图像像素点的数量，并根据所述重叠区域内的图像像素点的数量计算所述重叠区域的面积。
  2. 如权利要求1所述的计算方法，其特征在于，在所述待匹配指纹图像与预设模板指纹图像中寻找多对匹配的特征点步骤,包括以下步骤：
    对所述待匹配指纹图像进行滤波增强、二值化及细化操作后提取多个第一特征点；
    在所述预设模板指纹图像的特征点中寻找分别与所述多个第一特征点相匹配的多个第二特征点。
  3. 如权利要求1或2所述的计算方法，其特征在于，所述图像偏移量包括旋转角度及平移量中的至少一种。
  4. 如权利要求1-3中任一项所述的计算方法，其特征在于，所述统计所述重叠区域内的图像像素点的数量，并根据所述重叠区域内的图像像素点的数量计算所述重叠区域的面积的步骤,具体包括：
    根据所述预设模板指纹图像建立坐标系；
    确定位于所述预设模板指纹图像坐标范围内的所述待匹配指纹图像中的图像像素点属于所述重叠区域内的图像像素点；及
    统计所述重叠区域内的图像像素点的数量，计算所述重叠区域内的图像像素点的数量与所述预设模板指纹图像中的图像像素点的数量的比值，并根据所述比值计算所述重叠区域的面积。
  5. 如权利要求4所述的计算方法，其特征在于，所述确定位于所述预设模板指纹图像坐标范围内的所述待匹配指纹图像中的图像像素点属于所述重叠区域内的图像像素点的步骤,具体为:
    确定满足X1<X<X2且Y1<Y<Y2的所述待匹配指纹图像中的图像像素点属于所述重叠区域内的图像像素点，其中，X为所述待匹配指纹图像中的图像像素点在所述坐标系的横坐标，Y为所述待匹配指纹图像中的图像像素点在所述坐标系的纵坐标，X1～X2为所述预设模 板指纹图像在所述坐标系的横坐标范围，Y1～Y2为所述预设模板指纹图像在所述坐标系的纵坐标范围，|X2-X1|*|Y2-Y1|为所述预设模板指纹图像的图像分辨率。
  6. 如权利要求4或5所述的计算方法，其特征在于，所述重叠区域的面积由以下公式确定：S＝Sa*N/Ns，其中，S为所述重叠区域的面积，Sa为所述预设模板指纹图像的面积，N为所述重叠区域内的图像像素点的数量，Ns为所述预设模板指纹图像中的图像像素点的数量。
  7. 一种电子装置，其特征在于，包括采集模块及处理模块；
    所述采集模块用于采集待匹配指纹并得到待匹配指纹图像；
    所述处理模块用于在所述待匹配指纹图像与预设模板指纹图像中寻找多对匹配的特征点，及根据所述多对匹配的特征点获得所述待匹配指纹图像的图像偏移量，及利用所述图像偏移量，调整所述待匹配指纹图像的位置并得到所述待匹配指纹图像与所述预设模板指纹图像的重叠区域，及统计所述重叠区域内的图像像素点的数量，并根据所述重叠区域内的图像像素点的数量计算所述重叠区域的面积。
  8. 如权利要求7所述的电子装置，其特征在于，所述处理模块具体用于：
    对所述待匹配指纹图像进行滤波增强、二值化及细化操作后提取多个第一特征点；
    在所述预设模板指纹图像的特征点中寻找分别与所述多个第一特征点相匹配的多个第二特征点。
  9. 如权利要求7或8所述的电子装置，其特征在于，所述图像偏移量包括旋转角度及平移量中的至少一种。
  10. 如权利要求7-9中任一项所述的电子装置，其特征在于，所述处理模块还用于根据所述预设模板指纹图像建立坐标系，确定位于所述预设模板指纹图像坐标范围内的所述待匹配指纹图像中的图像像素点属于所述重叠区域内的图像像素点，及统计所述重叠区域内的图像像素点的数量，计算所述重叠区域内的图像像素点的数量与所述预设模板指纹图像的图像像素点的数量的比值，并根据所述比值计算所述重叠区域的面积。
  11. 如权利要求10所述的电子装置，其特征在于，所述处理模块还用于确定满足X1<X<X2且Y1<Y<Y2的所述待匹配指纹图像中的图像像素点属于所述重叠区域内的图像像素点，其中，X为所述待匹配指纹图像中的图像像素点在所述坐标系的横坐标，Y为所述待匹配指纹图像中的图像像素点在所述坐标系的纵坐标，X1～X2为所述预设模板指纹图像在所述坐标系的横坐标范围，Y1～Y2为所述预设模板指纹图像在所述坐标系的纵坐标范围，|X2-X1|*|Y2-Y1|为所述预设模板指纹图像的图像分辨率。
  12. 如权利要求10或11所述的电子装置，其特征在于，所述重叠区域的面积由以下公式确定：S＝Sa*N/Ns，其中，S为所述重叠区域的面积，Sa为所述预设模板指纹图像的面 积，N为所述重叠区域内的图像像素点的数量，Ns为所述预设模板指纹图像中的图像像素点的数量。
  13. 一种计算机可读存储介质，包括计算机指令，当所述计算机指令被执行时，使得执行根据权利要求1-6中任一项所述的指纹重叠区域面积的计算方法。
PCT/CN2016/070193 2015-02-13 2016-01-05 指纹重叠区域面积的计算方法及电子装置 WO2016127736A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
KR1020177022459A KR101912420B1 (ko) 2015-02-13 2016-01-05 지문 중첩 영역의 면적을 계산하는 방법 및 전자 기기
EP16748537.4A EP3258416A4 (en) 2015-02-13 2016-01-05 Computing method for area of fingerprint overlapping area and electronic apparatus
JP2017542174A JP6511149B2 (ja) 2015-02-13 2016-01-05 指紋重複領域の面積算出方法、それを行う電子機器、コンピュータプログラム、及び、記録媒体
US15/549,121 US20180018499A1 (en) 2015-02-13 2016-01-05 Method for calculating area of fingerprint overlapping region and electronic device thereof

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510079577.0 2015-02-13
CN201510079577.0A CN105205439B (zh) 2015-02-13 2015-02-13 指纹重叠区域面积的计算方法及电子装置

Publications (1)

Publication Number Publication Date
WO2016127736A1 true WO2016127736A1 (zh) 2016-08-18

Family

ID=54953112

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/070193 WO2016127736A1 (zh) 2015-02-13 2016-01-05 指纹重叠区域面积的计算方法及电子装置

Country Status (7)

Country Link
US (1) US20180018499A1 (zh)
EP (1) EP3258416A4 (zh)
JP (1) JP6511149B2 (zh)
KR (1) KR101912420B1 (zh)
CN (1) CN105205439B (zh)
TW (1) TWI619080B (zh)
WO (1) WO2016127736A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
SE1751569A1 (en) * 2017-12-18 2019-06-19 Fingerprint Cards Ab Method and device for classifying fingerprint
CN111160244A (zh) * 2019-12-27 2020-05-15 敦泰电子（深圳）有限公司 一种指纹识别方法及装置
CN111652091A (zh) * 2020-05-19 2020-09-11 上海恒浥智能科技股份有限公司 一种检测冷却片叠装合规性的方法
CN112070084A (zh) * 2020-09-04 2020-12-11 北京百度网讯科技有限公司 重复图像单元的位置确定方法和装置

Families Citing this family (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105205439B (zh) * 2015-02-13 2017-05-03 比亚迪股份有限公司 指纹重叠区域面积的计算方法及电子装置
FR3049090B1 (fr) * 2016-03-21 2021-06-25 Sebastien Jean Serge Dupont Dispositif d'authentification biometrique adaptatif par echographie, photographies en lumiere visible de contraste et infrarouge, sans divulgation, a travers un reseau informatique decentralise
CN107545217B (zh) * 2016-06-28 2021-07-30 比亚迪半导体股份有限公司 指纹匹配方法、指纹匹配装置和指纹识别芯片
CN106934361B (zh) * 2017-03-06 2021-01-05 苏州佳世达光电有限公司 一种辨识方法以及电子设备
US10909347B2 (en) 2017-03-14 2021-02-02 Samsung Electronics Co., Ltd. Method and apparatus with fingerprint verification
JP6926838B2 (ja) * 2017-08-31 2021-08-25 富士通株式会社 情報処理装置、情報処理方法、及びプログラム
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
CN109960911A (zh) * 2017-12-14 2019-07-02 宏碁股份有限公司 指纹验证方法与电子装置
CN110390230B (zh) * 2018-04-20 2022-03-18 比亚迪半导体股份有限公司 指纹识别模块异常判定方法、装置、存储介质及电子设备
CN108805034B (zh) * 2018-05-22 2021-09-28 公安部物证鉴定中心 一种基于概率几何特征的指纹特征相似度评价方法
CN110378951A (zh) * 2018-09-10 2019-10-25 天津京东深拓机器人科技有限公司 确定堆垛物品支撑面积的方法和装置
CN111611831A (zh) * 2019-02-26 2020-09-01 浙江中正智能科技有限公司 一种指纹模板自学习方法
TWI741362B (zh) * 2019-09-06 2021-10-01 大陸商北京集創北方科技股份有限公司 指紋採集方法、指紋採集裝置及資訊處理裝置
CN111461016A (zh) * 2020-04-01 2020-07-28 联想(北京)有限公司 残迹确定方法、装置和电子设备
CN113496183B (zh) * 2020-04-08 2023-02-03 上海耕岩智能科技有限公司 指纹匹配方法、装置、电子设备及可读存储介质
CN112229349B (zh) * 2020-09-23 2022-05-06 中科云谷科技有限公司 用于确定农业机械作业面积的方法、装置及农业机械
KR102570081B1 (ko) * 2020-12-18 2023-08-23 서울대학교산학협력단 딥러닝 알고리즘을 이용하여 지문중첩영상에서 지문을 분리하는 방법 및 그 장치
CN112837223B (zh) * 2021-01-28 2023-08-29 杭州国芯科技股份有限公司 一种基于重叠子区域的超大图像配准拼接方法
CN112884756A (zh) * 2021-03-12 2021-06-01 敦泰电子（深圳）有限公司 一种指纹图像处理方法、指纹芯片及电子设备
CN113392913B (zh) * 2021-06-21 2023-09-29 常州大学 基于边界特征点集的平面图形匹配度评价方法、装置及系统
CN113313088B (zh) * 2021-07-28 2022-02-15 深圳阜时科技有限公司 侧边弧面指纹数据的优化方法及指纹识别模组
CN115147469A (zh) * 2022-05-10 2022-10-04 腾讯科技（深圳）有限公司 配准方法、装置、设备及存储介质
CN116311395B (zh) * 2022-08-18 2023-11-14 荣耀终端有限公司 指纹识别的方法和装置
CN116434352B (zh) * 2023-06-12 2023-09-22 深圳市航顺芯片技术研发有限公司 指纹库生成方法、指纹识别装置及存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060045350A1 (en) * 2004-08-30 2006-03-02 Sharp Kabushiki Kaisha Apparatus, method and program performing image collation with similarity score as well as machine readable recording medium recording the program
CN101329727A (zh) * 2008-06-27 2008-12-24 哈尔滨工业大学 点线结合的指纹识别方法
CN103839283A (zh) * 2014-03-11 2014-06-04 浙江省特种设备检验研究院 一种小型不规则物体的面积周长无损测量方法
CN104156707A (zh) * 2014-08-14 2014-11-19 深圳市汇顶科技股份有限公司 指纹识别方法及其指纹识别装置
CN105205439A (zh) * 2015-02-13 2015-12-30 比亚迪股份有限公司 指纹重叠区域面积的计算方法及电子装置

Family Cites Families (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4736569A (en) * 1987-02-20 1988-04-12 Manville Corporation Dust flap tucking mechanism for use in forming sleeve-type carriers
US5909501A (en) * 1996-09-09 1999-06-01 Arete Associates Systems and methods with identity verification by comparison and interpretation of skin patterns such as fingerprints
US6785408B1 (en) * 1999-05-11 2004-08-31 Authentic, Inc. Fingerprint segment area processing method and associated apparatus
US6546122B1 (en) * 1999-07-29 2003-04-08 Veridicom, Inc. Method for combining fingerprint templates representing various sensed areas of a fingerprint to derive one fingerprint template representing the fingerprint
AU2000244476A1 (en) * 2000-04-13 2001-10-30 Nanyang Technological University Method and device for determining a total minutiae template from a plurality of partial minutiae templates
FR2829264A1 (fr) * 2001-09-04 2003-03-07 St Microelectronics Sa Procede de comparaison d'empreintes digitales
US7274807B2 (en) * 2002-05-30 2007-09-25 Activcard Ireland Limited Method and apparatus for supporting a biometric registration performed on a card
DE60330276D1 (de) * 2003-04-25 2010-01-07 Fujitsu Ltd Fingerabdruckvergleichseinrichtung, fingerabdruckvergleichsverfahren und fingerabdruckvergleichsprogramm
JP4553644B2 (ja) * 2004-06-30 2010-09-29 セコム株式会社 生体情報認証装置
CN100455266C (zh) * 2005-03-29 2009-01-28 深圳迈瑞生物医疗电子股份有限公司 宽景成像处理方法
CN100412883C (zh) * 2006-03-23 2008-08-20 北京中控科技发展有限公司 指纹识别方法与系统
CN101114335A (zh) * 2007-07-19 2008-01-30 南京大学 全角度快速指纹识别方法
CN101414350A (zh) * 2007-12-14 2009-04-22 浙江师范大学 一种融合多参考节点整体对齐和方向场的指纹图像匹配方法
CN101221661B (zh) * 2008-01-29 2010-09-22 深圳市迅雷网络技术有限公司 一种图像配准方法及装置
JP5277804B2 (ja) * 2008-09-05 2013-08-28 富士通株式会社 指紋認証装置、指紋認証プログラムおよび指紋認証方法
CN101373516B (zh) * 2008-09-10 2011-05-25 成都方程式电子有限公司 指纹采集图像库的可处理性分析评估方法和系统
CN101533470B (zh) * 2009-04-16 2012-01-25 成都方程式电子有限公司 用于刮擦传感器图像拼接的方法及装置
EP2600307B1 (en) * 2010-07-29 2020-12-02 Fujitsu Limited Biometric authentication device, biometric authentication method and computer program for biometric authentication
TWI501166B (zh) * 2010-09-29 2015-09-21 Gingy Technology Inc A segmented image recognition method and a region identification device thereof
TWI437501B (zh) * 2010-11-26 2014-05-11 Egis Technology Inc 基於生物特徵之身分驗證裝置及其方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060045350A1 (en) * 2004-08-30 2006-03-02 Sharp Kabushiki Kaisha Apparatus, method and program performing image collation with similarity score as well as machine readable recording medium recording the program
CN101329727A (zh) * 2008-06-27 2008-12-24 哈尔滨工业大学 点线结合的指纹识别方法
CN103839283A (zh) * 2014-03-11 2014-06-04 浙江省特种设备检验研究院 一种小型不规则物体的面积周长无损测量方法
CN104156707A (zh) * 2014-08-14 2014-11-19 深圳市汇顶科技股份有限公司 指纹识别方法及其指纹识别装置
CN105205439A (zh) * 2015-02-13 2015-12-30 比亚迪股份有限公司 指纹重叠区域面积的计算方法及电子装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3258416A4 *

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
SE1751569A1 (en) * 2017-12-18 2019-06-19 Fingerprint Cards Ab Method and device for classifying fingerprint
WO2019125270A1 (en) * 2017-12-18 2019-06-27 Fingerprint Cards Ab Method and device for classifying fingerprint
CN111160244A (zh) * 2019-12-27 2020-05-15 敦泰电子（深圳）有限公司 一种指纹识别方法及装置
CN111160244B (zh) * 2019-12-27 2023-10-03 敦泰电子（深圳）有限公司 一种指纹识别方法及装置
CN111652091A (zh) * 2020-05-19 2020-09-11 上海恒浥智能科技股份有限公司 一种检测冷却片叠装合规性的方法
CN111652091B (zh) * 2020-05-19 2023-03-24 上海恒浥智能科技股份有限公司 一种检测冷却片叠装合规性的方法
CN112070084A (zh) * 2020-09-04 2020-12-11 北京百度网讯科技有限公司 重复图像单元的位置确定方法和装置
CN112070084B (zh) * 2020-09-04 2024-01-12 北京百度网讯科技有限公司 重复图像单元的位置确定方法和装置

Also Published As

Publication number Publication date
TW201629848A (zh) 2016-08-16
JP2018505495A (ja) 2018-02-22
CN105205439A (zh) 2015-12-30
CN105205439B (zh) 2017-05-03
KR101912420B1 (ko) 2018-10-26
TWI619080B (zh) 2018-03-21
EP3258416A4 (en) 2018-10-31
KR20170106385A (ko) 2017-09-20
US20180018499A1 (en) 2018-01-18
JP6511149B2 (ja) 2019-05-15
EP3258416A1 (en) 2017-12-20

Similar Documents

Publication Publication Date Title
WO2016127736A1 (zh) 指纹重叠区域面积的计算方法及电子装置
Prasad et al. Edge curvature and convexity based ellipse detection method
US10354117B2 (en) Fingerprint identification method and apparatus
Song et al. A finger-vein verification system using mean curvature
US8879847B2 (en) Image processing device, method of controlling image processing device, and program for enabling computer to execute same method
US10558841B2 (en) Method and apparatus for recognizing fingerprint ridge point
US10740912B2 (en) Detection of humans in images using depth information
CN109272016B (zh) 目标检测方法、装置、终端设备和计算机可读存储介质
Liu et al. 3D fingerprint reconstruction system using feature correspondences and prior estimated finger model
WO2020108225A1 (zh) 指纹采集方法及相关装置
WO2018077104A1 (zh) 指纹采集方法、指纹采集设备及存储介质
CN107633237B (zh) 图像背景分割方法、装置、设备及介质
JP2018508891A (ja) 線間距離計算方法、線間距離計算装置、コンピュータプログラム、及びコンピュータ読み取り可能な記憶媒体
WO2018176514A1 (zh) 指纹配准方法及装置
US9245194B2 (en) Efficient line detection method
CN112396050B (zh) 图像的处理方法、设备以及存储介质
CN108960247B (zh) 图像显著性检测方法、装置以及电子设备
CN110740315B (zh) 摄像头矫正方法、装置、电子设备及存储介质
CN116109572A (zh) 工件边缘微弱缺陷的检测方法、装置及电子设备
WO2018058573A1 (zh) 对象检测方法、对象检测装置以及电子设备
WO2018107574A1 (zh) 一种对印防伪特征的检测方法及装置
CN108764343B (zh) 一种跟踪算法中的跟踪目标框的定位方法
US20230186677A1 (en) Electronic apparatus and method of processing fingerprint image
CN108629786B (zh) 图像边缘检测方法及装置
CN112416128B (zh) 一种手势识别方法及终端设备

Legal Events

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

Ref document number: 16748537

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 15549121

Country of ref document: US

ENP Entry into the national phase

Ref document number: 20177022459

Country of ref document: KR

Kind code of ref document: A

Ref document number: 2017542174

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

REEP Request for entry into the european phase

Ref document number: 2016748537

Country of ref document: EP