WO2017067270A1 - 指纹图像的识别的方法、装置及终端 - Google Patents

指纹图像的识别的方法、装置及终端 Download PDF

Info

Publication number
WO2017067270A1
WO2017067270A1 PCT/CN2016/092697 CN2016092697W WO2017067270A1 WO 2017067270 A1 WO2017067270 A1 WO 2017067270A1 CN 2016092697 W CN2016092697 W CN 2016092697W WO 2017067270 A1 WO2017067270 A1 WO 2017067270A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
target
target image
shape feature
fingerprint
Prior art date
Application number
PCT/CN2016/092697
Other languages
English (en)
French (fr)
Inventor
张强
王立中
周海涛
蒋奎
贺威
Original Assignee
广东欧珀移动通信有限公司
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 广东欧珀移动通信有限公司 filed Critical 广东欧珀移动通信有限公司
Priority to US15/759,359 priority Critical patent/US10755076B2/en
Priority to EP16856705.5A priority patent/EP3336749A4/en
Publication of WO2017067270A1 publication Critical patent/WO2017067270A1/zh
Priority to US16/201,470 priority patent/US10572714B2/en

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
    • G06V40/1347—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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • 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
    • G06V40/1376—Matching features related to ridge properties or fingerprint texture

Definitions

  • Embodiments of the present invention relate to a fingerprint identification technology, and in particular, to a method, an apparatus, and a terminal for identifying a fingerprint image.
  • fingerprint recognition technology is widely applied to smart terminals.
  • the user unlocks the smart terminal through fingerprint recognition.
  • a capacitive fingerprint sensor is used for fingerprint recognition. Since the human body is a conductor, when the finger presses the capacitive fingerprint sensor, the fingerprint sensor can obtain the texture of the finger, and then perform subsequent fingerprint recognition operations according to the texture.
  • the invention provides a method, a device and a terminal for identifying a fingerprint image, so as to effectively identify the captured image and improve resource utilization of the terminal.
  • an embodiment of the present invention provides a method for identifying a fingerprint image, including:
  • the target shape feature matches the preset finger shape feature, it is determined that the texture image is fingerprinted.
  • the embodiment of the present invention further provides an apparatus for identifying a fingerprint image, including:
  • a target image acquiring unit configured to acquire a target image from the captured texture image
  • a shape feature acquiring unit configured to acquire a target shape feature corresponding to the target image acquired by the target image acquiring unit, where the target shape feature is used to represent a shape feature of the target image;
  • a fingerprint image determining unit configured to perform fingerprint recognition on the texture image if the target shape feature acquired by the shape feature acquiring unit matches the preset finger shape feature.
  • an embodiment of the present invention further provides a terminal, where the terminal includes a fingerprint sensor and a device for identifying a fingerprint image, where the fingerprint sensor is connected to the device for identifying the fingerprint image, and the fingerprint image is identified.
  • the devices include:
  • a target image acquiring unit configured to acquire a target image from the captured texture image
  • a shape feature acquiring unit configured to acquire a target shape feature corresponding to the target image acquired by the target image acquiring unit, where the target shape feature is used to represent a shape feature of the target image;
  • a fingerprint image determining unit configured to perform fingerprint recognition on the texture image if the target shape feature acquired by the shape feature acquiring unit matches the preset finger shape feature.
  • the present invention acquires a target shape feature corresponding to the target image in the texture image before performing fingerprint recognition, and determines that the texture image is fingerprinted when the target shape feature matches the preset finger shape feature.
  • the present invention can determine whether the target image in the texture image matches the preset finger shape feature before starting the fingerprint recognition, and initiates fingerprint recognition on the texture image when the signature is matched. In turn, unnecessary fingerprint recognition is performed on non-finger objects, thereby improving system resource utilization and recognition efficiency.
  • Embodiment 1 is a flowchart of a method for identifying a fingerprint image in Embodiment 1 of the present invention
  • FIG. 2 is a schematic diagram of coordinates of a texture image in the first embodiment of the present invention.
  • Embodiment 3 is a schematic diagram of a fingerprint texture image in Embodiment 1 of the present invention.
  • FIG. 4 is a flowchart of a method for identifying a first fingerprint image in Embodiment 2 of the present invention.
  • FIG. 5 is a flowchart of a method for identifying a second fingerprint image in Embodiment 2 of the present invention.
  • FIG. 6 is a flowchart of a method for identifying a third fingerprint image in Embodiment 2 of the present invention.
  • FIG. 7 is a flowchart of a method for identifying a fourth fingerprint image in Embodiment 2 of the present invention.
  • Embodiment 8 is a schematic diagram showing the position of a preset position area in Embodiment 2 of the present invention.
  • FIG. 9 is a flowchart of a method for identifying a fifth fingerprint image in Embodiment 2 of the present invention.
  • FIG. 10 is a schematic structural diagram of an apparatus for fingerprint identification in a third embodiment of the present invention.
  • FIG. 11 is a schematic structural diagram of a second fingerprint recognition apparatus in Embodiment 3 of the present invention.
  • FIG. 1 is a flowchart of a method for identifying a fingerprint image according to Embodiment 1 of the present invention.
  • the present embodiment is applicable to a case where a fingerprint is recognized by an intelligent terminal, and the method may be performed by an intelligent terminal having a fingerprint recognition function.
  • the terminal includes a smart phone, a tablet, etc., and the method specifically includes the following steps:
  • Step 110 Acquire a target image from the captured texture image.
  • the smart terminal acquires a texture image through a fingerprint sensor.
  • the texture image can be a grayscale image.
  • the target image may be a texture image or a sub-image in the texture image.
  • Step 120 Acquire a target shape feature corresponding to the target image, where the target shape feature is used to represent a shape feature of the target image.
  • the target shape feature is composed of a plurality of feature values, each of which is used to represent the width of one line in the target image, thereby depicting the shape of the target image.
  • each feature value may also be used to represent the length of a column in the target image, and the shape of the target image is depicted by the length of each column.
  • the feature value is the number of texels contained in a row.
  • the texture image acquired by the fingerprint sensor is a grayscale image, and the pixel point in the grayscale image in which the grayscale value (pixel value) is greater than the preset grayscale value is determined as the texture pixel point.
  • the preset gray value may be 150-255, preferably 200.
  • the color of each pixel in the grayscale image is represented by a red, green, and blue RGB triplet.
  • the (R, G, B) triplet of each pixel is obtained by any one of the following conversion methods to obtain a gray value (ie, a pixel value) corresponding to the (R, G, B) triplet. :
  • the gradation value corresponding to the pixel point can be obtained by any of the above methods.
  • Each coordinate point in the texture image corresponds to one pixel, and each pixel has a unique pixel value, such as a gray value Gray.
  • the texture image coordinates shown in FIG. 2 are used in the embodiment and the subsequent embodiments.
  • the texture image is composed of m-row n-column pixel dot matrix, and includes m ⁇ n.
  • the pixel value, the pixel value (x n , y m ) of the m rows and n columns corresponds to a pixel value of G nm .
  • Step 130 If the target shape feature matches the preset finger shape feature, determine to perform fingerprint recognition on the texture image.
  • the preset finger shape feature is used to represent the shape feature of the finger print.
  • the preset finger shape feature may be a trend of a change in the width of the fingerprint or a change in the length of the fingerprint.
  • the width of the fingerprint changes from top to bottom, first from narrow to wide and then from wide to narrow.
  • the width of the fingerprint sensor is smaller than the partial fingerprint width, the fingerprint width of the portion acquired by the fingerprint sensor does not change.
  • the length of the fingerprint sensor is smaller than the partial fingerprint length of the finger, the fingerprint length of the portion acquired by the fingerprint sensor does not change.
  • the fingerprint sensor identifies the non-finger object, resulting in waste of system resources, resources. Low utilization.
  • the technical solution provided by the embodiment obtains a target shape feature corresponding to the target image in the texture image before performing fingerprint recognition, and determines that the texture image is fingerprinted when the target shape feature matches the preset finger shape feature.
  • the embodiment can determine whether the target image in the texture image matches the preset finger shape feature before starting the fingerprint recognition, and initiates fingerprint recognition on the texture image when the signature is matched. In order to avoid unnecessary fingerprint recognition of non-finger objects, improve system resource utilization and fingerprint recognition efficiency.
  • the embodiment of the present invention further provides a method for recognizing a fingerprint image.
  • the method further includes:
  • Step 140 Perform binarization processing on the target image.
  • the threshold T is set, and the pixel in the target image is divided into two parts by the threshold T: a pixel group whose pixel value is larger than the threshold T and a pixel group whose pixel value is smaller than the threshold T.
  • the pixel value of the pixel group whose pixel value is larger than the threshold T is set to white (or black), and the pixel value of the pixel group whose pixel value is smaller than the threshold T is set to black (or white).
  • the pixel value of the pixel in the target image is 0 or 1. If the target image is a fingerprint image, the pixel value of the pixel corresponding to the texture of the fingerprint is 1 (or 0), and the pixel value corresponding to the gap between the fingerprint textures is 0 (or 1).
  • the grayscale value corresponding to the threshold T ie, the pixel value
  • the exemplary threshold T has a value of 120.
  • step 120 acquiring a target shape feature corresponding to the target image may be implemented by:
  • Step 120a Acquire a target shape feature corresponding to the binarized target image.
  • the pixel points set in each row in the target image are texels.
  • the width occupied by the texture image in the target image is determined according to the width occupied by the texture pixel.
  • the pixel values of each column of pixels are sequentially acquired from the first column, and the first and last pixel values of 1 are obtained, and the texture in the target image is determined according to the two pixels. The width of the image.
  • the target image can be binarized to obtain a binary image. Since the pixel value of the pixel in the binary image is 0 or 1, the complexity of acquiring the target shape feature of the target image can be reduced, the speed of the variance calculation can be improved, and the recognition efficiency of the image can be improved.
  • step 120 acquiring a target shape feature corresponding to the target image may also be performed in the following manner.
  • Step 120b Acquire a sum of pixel values of each row or column of the target image.
  • the width of a row increases, the number of pixels contained in the row increases, and the sum of the pixel values corresponding to the row increases. Therefore, the width of the line can be represented by the sum of the row pixel values. As the sum of the pixel values increases, the width of the line increases; as the sum of the pixel values decreases, the width of the line decreases.
  • the length of a column increases, the number of pixels included in the column increases, and the sum of the pixel values corresponding to the column increases. Therefore, the length of the column can be represented by the sum of the column pixel values. As the sum of the pixel values increases, the length of the column increases; as the sum of the pixel values decreases, the length of the column decreases.
  • the sum of the pixel values of the pixels located in the same row is calculated in units of rows, respectively.
  • the sum of the pixel values of the pixels located in the same column is calculated in units of columns.
  • step 130 if the target shape feature matches the preset finger shape feature, determining to perform fingerprint identification on the texture image includes:
  • Step 130a If the sum of the pixel values of the preset number of adjacent rows or adjacent columns of the target image is gradually increased or decreased, it is determined that the texture image is fingerprinted.
  • the finger's fingerprint distribution is characterized by a widener top and bottom and a narrower middle. It is judged whether the change trend of the numerical value from [A 1 , A 2 ... A m ] is from small to large, and then small in stool. If so, it is determined that the texture image is fingerprinted. Or, it is judged whether the change tendency of the numerical value from [B 1 , B 2 ... B n ] is from small to large, and then the stool is small. If so, it is determined that the texture image is fingerprinted.
  • N is a positive integer greater than 2, preferably 80.
  • the jump value in the sum of the pixel values of the respective rows of the first N rows in the target image or the sum of the pixel values of the rows of the subsequent N rows.
  • the preset threshold is 5-10, preferably 8.
  • the technical solution provided by the embodiment can determine whether the target image is a fingerprint image according to a change trend of the sum of pixel values of each row or column in the target image, thereby improving the fingerprint recognition efficiency.
  • step 120 acquiring a target shape feature corresponding to the target image may also be performed in the following manner.
  • Step 120c Acquire edge pixel point coordinates of each row or column of the target image.
  • Obtaining the edge pixel coordinates of each line of the target image can be implemented by:
  • the pixel value of each pixel in the column is obtained.
  • the pixel value whose pixel value is greater than or equal to the preset pixel value is sequentially searched from the first column to the last column. If a pixel point whose pixel value is greater than or equal to the preset pixel value is found, and the column number of the pixel point is smaller than the maximum column number, the pixel point is determined as one edge pixel point P of the row, and the row number of the edge pixel point P The column number and its column number form its coordinates.
  • the pixel value whose pixel value is greater than or equal to the preset pixel value is sequentially searched from the last column to the first column. If a pixel point whose pixel value is greater than or equal to the preset pixel value is found, and the column number of the pixel point is greater than the minimum column number, the pixel point is determined as another edge pixel point Q of the row, and the row of the edge pixel point Q The number and column number form its coordinates.
  • step 130 if the target shape feature matches the preset finger shape feature, determining to perform fingerprint identification on the texture image includes:
  • Step 130b If the preset number of adjacent rows of the target image or the edge pixel coordinates of the adjacent columns gradually increase or decrease, it is determined that the texture image is fingerprinted.
  • the preset number of lines may be all the lines contained in the target image, or may be the first N lines or the last N lines in the target image.
  • the abscissa of the edge pixel point P of the preset number of adjacent rows decreases as the ordinate of the P point increases, and the abscissa of the edge pixel point Q increases as the ordinate of the Q point increases, determining the texture The image is fingerprinted.
  • the technical solution provided by the embodiment can determine whether the target image is a fingerprint image according to a preset trend of the target number of adjacent rows or adjacent columns, and improve the accuracy of the fingerprint image recognition.
  • step 110 obtaining a target image from the captured texture image, may also be implemented by the following manner. :
  • Step 110' determining an image in a preset area of the captured texture image as the target image.
  • the size of the preset position area can be determined according to the rated recognition range of the fingerprint sensor.
  • the width of the preset position area is the same as the width of the fingerprint sensor, and the length of the preset position area is one quarter of the length of the fingerprint sensor, and the preset position area is located at the top or bottom of the fingerprint identification area.
  • the top and bottom regions of the fingerprint image can more clearly represent the shape feature of the finger, whether the texture image is a fingerprint image by using the texture image at the top and bottom of the texture image can reduce the pixel value. Calculate the amount, which in turn improves the efficiency of fingerprint image recognition.
  • FIG. 9 The foregoing embodiment is further illustrated by a usage scenario, as shown in FIG. 9, including:
  • Step 210 Acquire a sensing range of the fingerprint sensor.
  • the range of perception ranges from the starting coordinate (0,0) to the ending coordinate (x,y).
  • Step 220 Calculate the sum of the pixel values of each row [A 0 , A 1 ... A y ] line by line from the starting coordinates (0, 0).
  • Step 230 Count the trend of the sum of the pixel values of each row.
  • Step 240 If the change trend is that the value gradually increases from low to high, and the value gradually decreases from high to low after reaching a certain peak value, it is determined as a finger.
  • the gradual increase from low to high indicates that the pressing area from top to bottom is gradually increasing.
  • the value gradually decreases from high to low, indicating that the pressing area is gradually reduced from top to bottom.
  • the embodiment of the present invention further provides a device 1 for identifying a fingerprint image.
  • the device 1 is used to implement the method shown in the foregoing embodiment and is located in the smart terminal. As shown in FIG. 10, the device 1 includes:
  • a target image obtaining unit 11 configured to acquire a target image from the captured texture image
  • a shape feature acquiring unit 12 configured to acquire a target shape feature corresponding to the target image acquired by the target image acquiring unit 11, and the target shape feature is used to represent a shape feature of the target image;
  • the fingerprint image determining unit 13 is configured to perform fingerprint recognition on the texture image if the target shape feature acquired by the shape feature acquiring unit 12 matches the preset finger shape feature.
  • the device further includes:
  • the binarization unit 14 is configured to perform binarization processing on the target image acquired by the target image acquiring unit 11;
  • the target image acquiring unit 11 is further configured to acquire a target shape feature corresponding to the binarized target image.
  • the shape feature acquiring unit 12 is further configured to:
  • the fingerprint image determining unit 13 is further configured to: if the sum of pixel values of a preset number of adjacent rows or adjacent columns of the target image is gradually increased or decreased, determining to perform fingerprint identification on the texture image .
  • the shape feature acquiring unit 12 is further configured to acquire the number of the jump values in the sum of the pixel values after acquiring the sum of the pixel values of each row or column of the target image;
  • the shape feature acquiring unit 12 is further configured to:
  • the fingerprint image determining unit 13 is further configured to: if the edge number coordinate value of the preset number of adjacent rows or adjacent columns of the target image is gradually increased or decreased, determining to fingerprint the texture image Identification.
  • the target image acquiring unit 11 is further configured to:
  • the image in the preset area of the captured texture image is determined as the target image.
  • the foregoing apparatus can perform the methods provided in Embodiment 1 and Embodiment 2 of the present invention, and has the corresponding functional modules and beneficial effects of performing the foregoing methods.
  • the foregoing apparatus can perform the methods provided in Embodiment 1 and Embodiment 2 of the present invention, and has the corresponding functional modules and beneficial effects of performing the foregoing methods.
  • the target shape feature includes a plurality of feature values for indicating a width of a row or a length of a column in the target image.
  • the embodiment of the present invention further provides a terminal, which includes a device for identifying a fingerprint sensor and a fingerprint image, and the fingerprint sensor is connected to the device for identifying the fingerprint image, and the device for identifying the fingerprint image includes:
  • a target image acquiring unit configured to acquire a target image from the captured texture image
  • a shape feature acquiring unit configured to acquire the target image acquired by the target image acquiring unit a corresponding target shape feature, the target shape feature being used to represent a shape feature of the target image;
  • a fingerprint image determining unit configured to perform fingerprint recognition on the texture image if the target shape feature acquired by the shape feature acquiring unit matches the preset finger shape feature.
  • the device for identifying the fingerprint image further includes:
  • a binarization unit configured to perform binarization processing on the target image acquired by the target image acquiring unit
  • the target image acquiring unit is further configured to acquire a target shape feature corresponding to the binarized target image.
  • the shape feature acquiring unit is further configured to:
  • the fingerprint image determining unit is further configured to perform fingerprint recognition on the texture image if a sum of pixel values of a predetermined number of adjacent rows or adjacent columns of the target image is gradually increased or decreased.
  • the shape feature acquiring unit is further configured to:
  • the fingerprint image determining unit is further configured to: if the preset number of adjacent rows or adjacent columns of the target image, the edge pixel point coordinate values gradually increase or decrease, determining to perform fingerprint identification on the texture image .
  • the target image acquiring unit is further configured to:
  • the image in the preset area of the captured texture image is determined as the target image.
  • the terminal provided by the embodiment of the present invention can perform the methods provided in Embodiment 1 and Embodiment 2 of the present invention, and has the corresponding functional modules and beneficial effects of performing the foregoing methods.
  • the terminal provided by the embodiment of the present invention can perform the methods provided in Embodiment 1 and Embodiment 2 of the present invention, and has the corresponding functional modules and beneficial effects of performing the foregoing methods.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Computational Mathematics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computing Systems (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Input (AREA)
  • Collating Specific Patterns (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

一种指纹图像的识别的方法，该方法包括：从捕获的纹理图像中获取目标图像；获取所述目标图像对应的目标形状特征，所述目标形状特征用于表示所述目标图像的形状特征；如果所述目标形状特征与预设手指形状特征相符，则确定对所述纹理图像进行指纹识别。本发明还提供了一种指纹图像的识别的装置及终端。

Description

指纹图像的识别的方法、装置及终端
本申请要求于2015年10月19日提交中国专利局、申请号为201510681069.X、发明名称为“指纹图像的识别方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明实施例涉及指纹识别技术，尤其涉及一种指纹图像的识别的方法、装置及终端。
背景技术
随着电子设备的发展，指纹识别技术被广泛应用到智能终端中。用户通过指纹识别对智能终端进行解锁等操作。
现有技术中，使用电容式指纹传感器进行指纹识别。由于人体为导体，因此当手指按压电容式指纹传感器时，指纹传感器可获得手指的纹理，进而根据该纹理进行后续的指纹识别操作。
发明内容
本发明提供一种指纹图像的识别的方法、装置及终端，以实现对捕获的图像进行有效识别，提高终端的资源利用率。
第一方面，本发明实施例提供了一种指纹图像的识别的方法，包括：
从捕获的纹理图像中获取目标图像；
获取所述目标图像对应的目标形状特征，所述目标形状特征用于表示所述目标图像的形状特征；
如果所述目标形状特征与预设手指形状特征相符，则确定对所述纹理图像进行指纹识别。
第二方面，本发明实施例还提供了一种指纹图像的识别的装置，包括：
目标图像获取单元，用于从捕获的纹理图像中获取目标图像；
形状特征获取单元，用于获取所述目标图像获取单元获取的所述目标图像对应的目标形状特征，所述目标形状特征用于表示所述目标图像的形状特征；
指纹图像确定单元，用于如果所述形状特征获取单元获取的所述目标形状特征与预设手指形状特征相符，则确定对所述纹理图像进行指纹识别。
第三方面，本发明实施例还提供了一种终端，所述终端包括指纹传感器和指纹图像的识别的装置，所述指纹传感器与所述指纹图像的识别的装置连接，所述指纹图像的识别的装置包括：
目标图像获取单元，用于从捕获的纹理图像中获取目标图像；
形状特征获取单元，用于获取所述目标图像获取单元获取的所述目标图像对应的目标形状特征，所述目标形状特征用于表示所述目标图像的形状特征；
指纹图像确定单元，用于如果所述形状特征获取单元获取的所述目标形状特征与预设手指形状特征相符，则确定对所述纹理图像进行指纹识别。
与现有技术相比，本发明在进行指纹识别之前，获取纹理图像中目标图像对应的目标形状特征，当目标形状特征与预设手指形状特征相符时，确定对纹理图像进行指纹识别。与现有技术中直接对纹理图像进行指纹识别相比，本发明能够在启动指纹识别之前，判定纹理图像中目标图像是否与预设手指形状特征相符，当相符时启动对纹理图像的指纹识别，进而避免对当非手指物体进行不必要的指纹识别，提高系统资源的利用率和识别效率。
附图说明
图1是本发明实施例一中的一个指纹图像的识别方法的流程图；
图2是本发明实施例一中的一个纹理图像的坐标示意图；
图3是本发明实施例一中的一个指纹纹理图像示意图；
图4是本发明实施例二中的第一个指纹图像的识别方法的流程图；
图5是本发明实施例二中的第二个指纹图像的识别方法的流程图；
图6是本发明实施例二中的第三个指纹图像的识别方法的流程图；
图7是本发明实施例二中的第四个指纹图像的识别方法的流程图；
图8是本发明实施例二中的预设位置区域的位置示意图；
图9是本发明实施例二中的第五个指纹图像的识别方法的流程图；
图10是本发明实施例三中的第一个指纹识别的装置的结构示意图；
图11是本发明实施例三中的第二个指纹识别的装置的结构示意图。
具体实施方式
下面结合附图和实施例对本发明作进一步的详细说明。可以理解的是，此处所描述的具体实施例仅仅用于解释本发明，而非对本发明的限定。另外还需 要说明的是，为了便于描述，附图中仅示出了与本发明相关的部分而非全部结构。
实施例一
图1为本发明实施例一提供的指纹图像的识别的方法的流程图，本实施例可适用于通过智能终端进行指纹识别的情况，该方法可以由具有指纹识别功能的智能终端来执行，智能终端如智能手机、平板电脑等，该方法具体包括如下步骤：
步骤110、从捕获的纹理图像中获取目标图像。
智能终端通过指纹传感器获取纹理图像。纹理图像可以为灰度图。目标图像可以为纹理图像，也可以为纹理图像中的子图像。
步骤120、获取目标图像对应的目标形状特征，目标形状特征用于表示目标图像的形状特征。
目标形状特征由多个特征值组成，每个特征值用于表示目标图像中的一行的宽度，进而描绘出目标图像的形状。可选的，每个特征值还可用于表示目标图像中的一列的长度，通过各个列的长度描绘出目标图像的形状。示例性的，特征值为某一行包含的纹理像素点的数量。通过指纹传感器获取到的纹理图像为灰度图，将灰度图中灰度值(像素值)大于预设灰度值的像素点确定为纹理像素点。其中，预设灰度值可以为150-255，优选为200。
灰度图中每个像素点的色彩由红绿蓝RGB三元组表示。为了方便计算，将每个像素的(R，G，B)三元组通过下述任意一种转换方式得到与(R，G，B)三元组对应的灰度值(即像素值)Gray：
方式一：浮点算法：Gray＝R×0.3+G×0.59+B×0.11
方式二：整数方法：Gray＝(R×30+G×59+B×11)÷100
方式三：平均值法：Gray＝(R+G+B)÷3
方式四：仅取绿色：Gray＝G
通过上述任意一种方式可得到像素点对应的灰度值，即像素点的像素值。纹理图像中的每个坐标点对应一个像素点，每个像素点具有唯一的像素值，如灰度值Gray。为了方便说明，本实施例及后续实施例中采用如图2所示的纹理图像坐标进行说明，如图4所示，纹理图像由m行n列的像素点矩阵组成， 共包含m×n个像素点，位于m行n列的像素点(xn，ym)对应的像素值为Gnm。可选的，m＝n＝480。
步骤130、如果目标形状特征与预设手指形状特征相符，则确定对纹理图像进行指纹识别。
预设手指形状特征用于表示手指指纹的形状特征。预设手指形状特征可以是一个指纹宽度的变化趋势或者指纹长度的变化趋势。
示例性的，当预设手指形状特征为一变化趋势时，如图3所示，指纹的宽度变化趋势为从上至下，先由窄变宽再由宽变窄。当指纹传感器的宽度小于部分指纹宽度时，指纹传感器获取的该部分的指纹宽度不变。当指纹传感器的长度小于手指的部分指纹长度时，指纹传感器获取的该部分的指纹长度不变。
现有技术中，在智能终端的使用过程中，当非手指物体，如衣服面料、手掌皮肤等物质触碰到指纹传感器时，指纹传感器会对非手指物体进行识别，造成系统资源的浪费，资源利用率低。
本实施例提供的技术方案在进行指纹识别之前，获取纹理图像中目标图像对应的目标形状特征，当目标形状特征与预设手指形状特征相符时，确定对纹理图像进行指纹识别。与现有技术中直接对纹理图像进行指纹识别相比，本实施例能够在启动指纹识别之前，判定纹理图像中目标图像是否与预设手指形状特征相符，当相符时启动对纹理图像的指纹识别，进而避免对非手指物体进行不必要的指纹识别，提高系统资源的利用率和指纹识别效率。
实施例二
本发明实施例还提供了一种指纹图像的识别的方法，作为对实施例一的进一步说明，如图4所示，在步骤110、获取目标图像之后，所述方法还包括：
步骤140、对所述目标图像进行二值化处理。
设定阈值T，用阈值T将目标图像中的像素点分成两部分：像素值大于阈值T的像素群和像素值小于阈值T的像素群。将像素值大于阈值T的像素群的像素值设定为白色(或者黑色)，像素值小于阈值T的像素群的像素值设定为黑色(或者白色)。经二值化处理后，目标图像中的像素点的像素值为0或1。如果目标图像为指纹图像，则指纹的纹理对应的像素点的像素值为1(或者为0)，指纹纹理之间的缝隙对应的像素点的像素值为0(或者为1)。当目 标图像为灰度图时，阈值T对应的灰度值(即像素值)的取值范围为0-255，示例性的阈值T的取值为120。
相应的，步骤120、获取目标图像对应的目标形状特征，可通过下述方式进行实施：
步骤120a、获取二值化的目标图像对应的目标形状特征。
进行二值化后，目标图像中每行中置1的像素点为纹理像素点。根据纹理像素点占用的宽度确定目标图像中纹理图像占用的宽度。对于目标图像中任意一行像素点，从第一列开始依次获取每列像素点的像素值，获取第一个和最后一个像素值为1的像素点，并根据两个像素点确定目标图像中纹理图像所占的宽度。
本实施例提供的技术方案，能够将目标图像进行二值化处理，得到二值图像。由于二值图像中像素点的像素值为0或为1，因此能够降低获取目标图像的目标形状特征的复杂度，提高方差计算的速度，进而提高图片的识别效率。
本发明实施例还提供了一种指纹图像的识别的方法，作为对上述实施例的进一步说明，如图5所示，步骤120、获取目标图像对应的目标形状特征，还可通过下述方式进行实施：
步骤120b、获取目标图像每行或每列的像素值之和。
当某行的宽度增加时，该行所包含的像素点增多，进而该行对应的像素值之和随之增加。因此，可通过行像素值之和表示行的宽度。当像素值之和增加时，行的宽度随之增加；当像素值之和减小时，行的宽度随之降低。
同理，当某列的长度增加时，该列所包含的像素点增多，进而该列对应的像素值之和随之增加。因此，可通过列像素值之和表示列的长度。当像素值之和增加时，列的长度随之增加；当像素值之和减小时，列的长度随之降低。
在一种实现方式中，以行为单位，分别计算位于同一行的像素点的像素值的和。首先获取第一行中的全部像素点[(x1，y1)、(x2，y1)...(xn，y1)]及其像素值[G11、G12...G1n]，并计算第一行各像素点像素值[G11、G12...G1n]的和A1。然后，获取第二行中的全部像素点[(x1，y2)、(x2，y2)...(xn，y2)]及其像素值[G21、G22...G2n]，并计算第二行各像素点像素值[G21、G22...G2n]的和A2。以此类推，得到第三行至第m行各行像素点的像素值之和[A3、A4...Am]。
在另一种实现方式中，以列为单位，分别计算位于同一列的像素点的像素值的和。首先获取第一列中的全部像素点[(x1，y1)、(x1，y2)...(x1，ym)]及其像素值[G11、G21...Gm1]，并计算第一列各像素点像素值[G11、G21...Gm1]的和B1。然后，获取第二列中的全部像素点[(x2，y1)、(x2，y2)...(x2，ym)]及其像素值[G12、G22...Gm2]，并计算第二列各像素点像素值[G12、G22...Gm2]的和B2。以此类推，得到第三列至第n列各列像素点的像素值之和[B3、B4...Bn]。
相应的，步骤130、如果目标形状特征与预设手指形状特征相符，则确定对纹理图像进行指纹识别，包括：
步骤130a、如果目标图像的预设数量的相邻行或相邻列的像素值之和逐渐增加或逐渐减小，则确定对纹理图像进行指纹识别。
手指的指纹分布特征为顶部和底部较窄中间较宽。判断从[A1、A2...Am]的数值大小的变化趋势是否为由小变大，再由大便小。如果是，则确定对纹理图像进行指纹识别。或者，判断从[B1、B2...Bn]的数值大小的变化趋势是否为由小变大，再由大便小。如果是，则确定对纹理图像进行指纹识别。
可选的，由于指纹的顶部和底部的宽度变化较明显，可仅对目标图像的顶部和底部为对象，判断是否为手指图像。具体的，判断目标图像中的前N行(顶部)的各行像素值之和是否呈逐渐增加趋势；和/或，判断目标图像中的后N行(底部)的各行像素值之和是否呈逐渐减小趋势。其中，N为大于2的正整数，优选为80。
进一步的，有时目标图像中的前N行的各行像素值之和或者后N行的各行像素值之和可能存在跳跃值。为了避免跳跃值影响目标图像的判断结果，当跳跃值的数量小于预设阈值时，删除跳跃值，进而减小噪点对判断是否为指纹图像的干扰。其中，预设阈值为5-10，优选为8。
本实施例提供的技术方案，能够根据目标图像中每行或每列的像素值之和的变化趋势确定目标图像是否为指纹图像，提高指纹识别效率。
本发明实施例还提供了一种指纹图像的识别的方法，作为对上述实施例的进一步说明，如图6所示，步骤120、获取目标图像对应的目标形状特征，还可通过下述方式进行实施：
步骤120c、获取目标图像每行或每列的边缘像素点坐标。
获取目标图像每行的边缘像素点坐标可通过下述方式进行实施：
首先，对于目标图像的任意一列，获取该列中每个像素点的像素值。
然后，从第一列向最后一列依次查找像素点的像素值大于等于预设像素值的像素点。如果查找到像素值大于等于预设像素值的像素点，且该像素点的列号小于最大列号，则将该像素点确定为该行的一个边缘像素点P，边缘像素点P的行号和列号构成其坐标。
最后，从最后一列向第一列依次查找像素点的像素值大于等于预设像素值的像素点。如果查找到像素值大于等于预设像素值的像素点，且该像素点的列号大于最小列号，则将该像素点确定为该行的另一个边缘像素点Q，边缘像素点Q的行号和列号构成其坐标。
获取目标图像每列的边缘像素点坐标的方式可参照上述获取行的边缘像素点坐标等方式，此处不做赘述。
相应的，步骤130、如果目标形状特征与预设手指形状特征相符，则确定对纹理图像进行指纹识别，包括：
步骤130b、如果目标图像的预设数量的相邻行或相邻列的边缘像素点坐标逐渐增加或逐渐减小，则确定对纹理图像进行指纹识别。
预设数量的行可以为目标图像包含的全部行，也可以是目标图像中的前N行或者后N行。
如果预设数量的相邻行的边缘像素点P的横坐标随着P点纵坐标的增加而减少，且边缘像素点Q的横坐标随着Q点纵坐标的增加而增加，则确定对纹理图像进行指纹识别。
本实施例提供的技术方案，能够根据目标图像的预设数量的相邻行或相邻列的边缘像素点坐标的变化趋势，确定目标图像是否为指纹图像，提高指纹图像识别的准确度。
本发明实施例还提供了一种指纹识别的方法，作为对上述实施例的进一步说明，如图7所示，步骤110、从捕获的纹理图像中获取目标图像，还可通过下述方式进行实施：
步骤110′、将捕获的纹理图像的预设区域中的图像确定为目标图像。
预设位置区域的大小可以根据指纹传感器的额定识别范围确定。可选的， 如图8所示，预设位置区域的宽度与指纹传感器宽度相同，预设位置区域的长度为指纹传感器长度的四分之一，预设位置区域位于指纹识别区域的顶部或底部。
本实施例提供的技术方案，由于指纹图像的顶部和底部区域能够较为明显的表现手指的形状特征，因此通过纹理图像的顶部和底部的纹理图像确定纹理图像是否为指纹图像，能够减少像素值的计算量，进而提高指纹图像识别的效率。
下面通过一个使用场景对上述实施例进行进一步说明，如图9所示，包括：
步骤210、获取指纹传感器的感知范围。
感知范围从起始坐标(0，0)至终止坐标(x，y)。
步骤220、从起始坐标(0，0)开始逐行计算每行的像素数值总和[A0、A1...Ay]。
步骤230、统计每行像素值总和的变化趋势。
步骤240、如果变化趋势为数值从低到高逐步增加，且到达一定峰值后数值从高到低逐步减小，则判定为手指。
从低到高逐步增加表示，从上到下按压区域逐步增多。当到达一定峰值后，数值又从高到低逐步减小，表示从上到下，按压区域又逐步减小。
实施例三
本发明实施例还提供了一种指纹图像的识别的装置1，该装置1用于实施上述实施例所示的方法且位于智能终端中，如图10所示，该装置1包括：
目标图像获取单元11，用于从捕获的纹理图像中获取目标图像；
形状特征获取单元12，用于获取所述目标图像获取单元11获取的所述目标图像对应的目标形状特征，所述目标形状特征用于表示所述目标图像的形状特征；
指纹图像确定单元13，用于如果所述形状特征获取单元12获取的所述目标形状特征与预设手指形状特征相符，则确定对所述纹理图像进行指纹识别。
进一步的，如图11所示，所述装置还包括：
二值化单元14，用于对所述目标图像获取单元11获取的所述目标图像进行二值化处理；
所述目标图像获取单元11还用于，获取二值化的目标图像对应的目标形状特征。
进一步的，所述形状特征获取单元12还用于：
获取所述目标图像每行或每列的像素值之和；
所述指纹图像确定单元13还用于，如果所述目标图像的预设数量的相邻行或相邻列的像素值之和逐渐增加或逐渐减小，则确定对所述纹理图像进行指纹识别。
进一步的，所述形状特征获取单元12还用于，在获取所述目标图像每行或每列的像素值之和之后，获取所述像素值之和中的跳跃值的数量；
判断所述数量是否小于预设阈值；
若是，则删除所述跳跃值。
进一步的，所述形状特征获取单元12还用于：
获取所述目标图像每行或每列的边缘像素点坐标值；
所述指纹图像确定单元13还用于，如果所述目标图像的预设数量的相邻行或相邻列的边缘像素点坐标值逐渐增加或逐渐减小，则确定对所述纹理图像进行指纹识别。
进一步的，所述目标图像获取单元11还用于：
将捕获的纹理图像的预设区域中的图像确定为目标图像。
上述装置可执行本发明实施例一和实施例二所提供的方法，具备执行上述方法相应的功能模块和有益效果。未在本实施例中详尽描述的技术细节，可参见本发明实施例一和实施例二所提供的方法。
进一步的，所述目标形状特征包括多个特征值，所述特征值用于表示所述目标图像中的一行的宽度或一列的长度。
实施例四
本发明实施例还提供了一种终端，该终端包括指纹传感器和指纹图像的识别的装置，该指纹传感器与该指纹图像的识别的装置连接，该指纹图像的识别的装置包括：
目标图像获取单元，用于从捕获的纹理图像中获取目标图像；
形状特征获取单元，用于获取所述目标图像获取单元获取的所述目标图像 对应的目标形状特征，所述目标形状特征用于表示所述目标图像的形状特征；
指纹图像确定单元，用于如果所述形状特征获取单元获取的所述目标形状特征与预设手指形状特征相符，则确定对所述纹理图像进行指纹识别。
进一步的，该指纹图像的识别的装置还包括：
二值化单元，用于对所述目标图像获取单元获取的所述目标图像进行二值化处理；
所述目标图像获取单元还用于，获取二值化的目标图像对应的目标形状特征。
进一步的，所述形状特征获取单元还用于：
获取所述目标图像每行或每列的像素值之和；
所述指纹图像确定单元还用于，如果所述目标图像的预设数量的相邻行或相邻列的像素值之和逐渐增加或逐渐减小，则确定对所述纹理图像进行指纹识别。
进一步的，所述形状特征获取单元还用于：
获取所述目标图像每行或每列的边缘像素点坐标值；
所述指纹图像确定单元还用于，如果所述目标图像的预设数量的相邻行或相邻列的边缘像素点坐标值逐渐增加或逐渐减小，则确定对所述纹理图像进行指纹识别。
进一步的，所述目标图像获取单元还用于：
将捕获的纹理图像的预设区域中的图像确定为目标图像。
本发明实施例提供的终端可执行本发明实施例一和实施例二所提供的方法，具备执行上述方法相应的功能模块和有益效果。未在本实施例中详尽描述的技术细节，可参见本发明实施例一和实施例二所提供的方法。
注意，上述仅为本发明的较佳实施例及所运用技术原理。本领域技术人员会理解，本发明不限于这里所述的特定实施例，对本领域技术人员来说能够进行各种明显的变化、重新调整和替代而不会脱离本发明的保护范围。因此，虽然通过以上实施例对本发明进行了较为详细的说明，但是本发明不仅仅限于以上实施例，在不脱离本发明构思的情况下，还可以包括更多其他等效实施例，而本发明的范围由所附的权利要求范围决定。

Claims (20)

  1. 一种指纹图像的识别的方法，其中，包括：
    从捕获的纹理图像中获取目标图像；
    获取所述目标图像对应的目标形状特征，所述目标形状特征用于表示所述目标图像的形状特征；
    如果所述目标形状特征与预设手指形状特征相符，则确定对所述纹理图像进行指纹识别。
  2. 根据权利要求1所述的指纹图像的识别的方法，其中，在从捕获的纹理图像中获取目标图像之后，所述方法还包括：
    对所述目标图像进行二值化处理；
    相应的，所述获取所述目标图像对应的目标形状特征，包括：
    获取二值化的目标图像对应的目标形状特征。
  3. 根据权利要求1所述的指纹图像的识别的方法，其中，所述获取所述目标图像对应的目标形状特征，包括：
    获取所述目标图像每行或每列的像素值之和；
    相应的，所述如果所述目标形状特征与预设手指形状特征相符，则确定对所述纹理图像进行指纹识别，包括：
    如果所述目标图像的预设数量的相邻行或相邻列的像素值之和逐渐增加或逐渐减小，则确定对所述纹理图像进行指纹识别。
  4. 根据权利要求3所述的指纹图像的识别的方法，其中，所述获取所述目标图像每行或每列的像素值之和的步骤之后，还包括：
    获取所述像素值之和中的跳跃值的数量；
    判断所述数量是否小于预设阈值；
    若是，则删除所述跳跃值。
  5. 根据权利要求1所述的指纹图像的识别的方法，其中，所述获取所述目标图像对应的目标形状特征，包括：
    获取所述目标图像每行或每列的边缘像素点坐标；
    相应的，所述如果所述目标形状特征与预设手指形状特征相符，则确定对所述纹理图像进行指纹识别，包括：
    如果所述目标图像的预设数量的相邻行或相邻列的边缘像素点坐标逐渐增加或逐渐减小，则确定对所述纹理图像进行指纹识别。
  6. 根据权利要求1至5中任一项所述的指纹图像的识别的方法，其中，所述从捕获的纹理图像中获取目标图像，包括：
    将捕获的纹理图像的预设区域中的图像确定为目标图像。
  7. 根据权利要求1至5中任一项所述的指纹图像的识别的方法，其中：
    所述目标形状特征包括多个特征值，所述特征值用于表示所述目标图像中的一行的宽度或一列的长度。
  8. 一种指纹图像的识别的装置，其中，包括：
    目标图像获取单元，用于从捕获的纹理图像中获取目标图像；
    形状特征获取单元，用于获取所述目标图像获取单元获取的所述目标图像对应的目标形状特征，所述目标形状特征用于表示所述目标图像的形状特征；
    指纹图像确定单元，用于如果所述形状特征获取单元获取的所述目标形状特征与预设手指形状特征相符，则确定对所述纹理图像进行指纹识别。
  9. 根据权利要求8所述的指纹图像的识别的装置，其中，所述装置还包括：
    二值化单元，用于对所述目标图像获取单元获取的所述目标图像进行二值化处理；
    所述目标图像获取单元还用于，获取二值化的目标图像对应的目标形状特征。
  10. 根据权利要求8所述的指纹图像的识别的装置，其中，所述形状特征获取单元还用于：
    获取所述目标图像每行或每列的像素值之和；
    所述指纹图像确定单元还用于，如果所述目标图像的预设数量的相邻行或相邻列的像素值之和逐渐增加或逐渐减小，则确定对所述纹理图像进行指纹识别。
  11. 根据权利要求10所述的指纹图像的识别的装置，其中，所述形状特征获取单元还用于：
    在获取所述目标图像每行或每列的像素值之和之后，获取所述像素值之和 中的跳跃值的数量；
    判断所述数量是否小于预设阈值；
    若是，则删除所述跳跃值。
  12. 根据权利要求8所述的指纹图像的识别的装置，其中，所述形状特征获取单元还用于：
    获取所述目标图像每行或每列的边缘像素点坐标值；
    所述指纹图像确定单元还用于，如果所述目标图像的预设数量的相邻行或相邻列的边缘像素点坐标值逐渐增加或逐渐减小，则确定对所述纹理图像进行指纹识别。
  13. 根据权利要求8至12中任一项所述的指纹图像的识别的装置，其中，所述目标图像获取单元还用于：
    将捕获的纹理图像的预设区域中的图像确定为目标图像。
  14. 根据权利要求8至12中任一项所述的指纹图像的识别的装置，其中：
    所述目标形状特征包括多个特征值，所述特征值用于表示所述目标图像中的一行的宽度或一列的长度。
  15. 一种终端，其中，所述终端包括指纹传感器和指纹图像的识别的装置，所述指纹传感器与所述指纹图像的识别的装置连接，所述指纹图像的识别的装置包括：
    目标图像获取单元，用于从捕获的纹理图像中获取目标图像；
    形状特征获取单元，用于获取所述目标图像获取单元获取的所述目标图像对应的目标形状特征，所述目标形状特征用于表示所述目标图像的形状特征；
    指纹图像确定单元，用于如果所述形状特征获取单元获取的所述目标形状特征与预设手指形状特征相符，则确定对所述纹理图像进行指纹识别。
  16. 根据权利要求15所述的终端，其中，所述指纹图像的识别的装置还包括：
    二值化单元，用于对所述目标图像获取单元获取的所述目标图像进行二值化处理；
    所述目标图像获取单元还用于，获取二值化的目标图像对应的目标形状特征。
  17. 根据权利要求15所述的终端，其中，所述形状特征获取单元还用于：
    获取所述目标图像每行或每列的像素值之和；
    所述指纹图像确定单元还用于，如果所述目标图像的预设数量的相邻行或相邻列的像素值之和逐渐增加或逐渐减小，则确定对所述纹理图像进行指纹识别。
  18. 根据权利要求17所述的终端，其中，所述形状特征获取单元还用于：
    在获取所述目标图像每行或每列的像素值之和之后，获取所述像素值之和中的跳跃值的数量；
    判断所述数量是否小于预设阈值；
    若是，则删除所述跳跃值。
  19. 根据权利要求15所述的终端，其中，所述形状特征获取单元还用于：
    获取所述目标图像每行或每列的边缘像素点坐标值；
    所述指纹图像确定单元还用于，如果所述目标图像的预设数量的相邻行或相邻列的边缘像素点坐标值逐渐增加或逐渐减小，则确定对所述纹理图像进行指纹识别。
  20. 根据权利要求15至19中任一项所述的终端，其中，所述目标图像获取单元还用于：
    将捕获的纹理图像的预设区域中的图像确定为目标图像。
PCT/CN2016/092697 2015-10-19 2016-08-01 指纹图像的识别的方法、装置及终端 WO2017067270A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US15/759,359 US10755076B2 (en) 2015-10-19 2016-08-01 Fingerprint image recognition method, apparatus and terminal
EP16856705.5A EP3336749A4 (en) 2015-10-19 2016-08-01 Fingerprint image recognition method, apparatus, and terminal
US16/201,470 US10572714B2 (en) 2015-10-19 2018-11-27 Fingerprint image recognition method, apparatus and terminal

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510681069.XA CN105389541B (zh) 2015-10-19 2015-10-19 指纹图像的识别方法及装置
CN201510681069.X 2015-10-19

Related Child Applications (2)

Application Number Title Priority Date Filing Date
US15/759,359 A-371-Of-International US10755076B2 (en) 2015-10-19 2016-08-01 Fingerprint image recognition method, apparatus and terminal
US16/201,470 Continuation US10572714B2 (en) 2015-10-19 2018-11-27 Fingerprint image recognition method, apparatus and terminal

Publications (1)

Publication Number Publication Date
WO2017067270A1 true WO2017067270A1 (zh) 2017-04-27

Family

ID=55421813

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/092697 WO2017067270A1 (zh) 2015-10-19 2016-08-01 指纹图像的识别的方法、装置及终端

Country Status (4)

Country Link
US (2) US10755076B2 (zh)
EP (1) EP3336749A4 (zh)
CN (2) CN108427932B (zh)
WO (1) WO2017067270A1 (zh)

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108427932B (zh) 2015-10-19 2021-07-02 Oppo广东移动通信有限公司 指纹图像的识别方法及装置
CN105760021B (zh) * 2016-03-17 2018-09-28 周奇 一种通过指纹采集获取压力的方法和装置
EP3663900B1 (en) * 2017-08-30 2023-01-18 Huawei Technologies Co., Ltd. Method for controlling screen and terminal
US20200302151A1 (en) * 2019-03-19 2020-09-24 Pixart Imaging Inc. Event detection device
CN110765857A (zh) * 2019-09-12 2020-02-07 敦泰电子（深圳）有限公司 指纹识别方法、芯片及电子装置
CN110782454B (zh) * 2019-11-12 2022-04-26 上海电气集团股份有限公司 一种发电机定子铁心叠片的识别方法以及识别装置
CN111753723B (zh) * 2020-06-24 2024-03-26 上海依图网络科技有限公司 一种基于密度校准的指纹识别方法及装置

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH02270075A (ja) * 1989-04-12 1990-11-05 Oki Electric Ind Co Ltd 指紋照合装置の給電方式
CN1221161A (zh) * 1997-12-24 1999-06-30 夏普公司 信息处理装置
CN101470804A (zh) * 2005-04-22 2009-07-01 日立欧姆龙金融系统有限公司 生物体认证装置
CN103870071A (zh) * 2012-12-13 2014-06-18 中国移动通信集团公司 一种触摸源识别方法及系统
CN104615991A (zh) * 2015-02-10 2015-05-13 深圳市亚耕电子科技有限公司 指纹感测装置、电子产品及其指纹感测方法
CN104751103A (zh) * 2013-12-26 2015-07-01 齐发光电股份有限公司 手指指纹读取系统及指纹读取方法
WO2015105360A1 (ko) * 2014-01-10 2015-07-16 주식회사 고영테크놀러지 3차원 형상측정장치 및 방법
CN105389541A (zh) * 2015-10-19 2016-03-09 广东欧珀移动通信有限公司 指纹图像的识别方法及装置

Family Cites Families (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE60039002D1 (de) * 1999-05-17 2008-07-10 Nippon Telegraph & Telephone Gerät und Verfahren zur Oberflächenmustererkennung
DE602004024995D1 (de) * 2003-05-23 2010-02-25 Nippon Telegraph & Telephone Parallelverarbeitungseinrichtung und parallelverarbeitungsverfahren
FR2863080B1 (fr) * 2003-11-27 2006-02-24 Advestigo Procede d'indexation et d'identification de documents multimedias
KR100825773B1 (ko) * 2005-08-23 2008-04-28 삼성전자주식회사 방향 추정 방법 및 장치
US20070292005A1 (en) * 2006-06-14 2007-12-20 Motorola, Inc. Method and apparatus for adaptive hierarchical processing of print images
TWI423145B (zh) * 2009-10-26 2014-01-11 Wistron Corp 指紋圖像檢測方法
EP2500863B1 (en) * 2009-11-10 2023-09-13 Nec Corporation Fake-finger determination device, fake-finger determination method and fake-finger determination program
WO2011077879A1 (ja) * 2009-12-22 2011-06-30 日本電気株式会社 偽指判定装置
TWI599964B (zh) * 2010-09-03 2017-09-21 國立台灣科技大學 手指靜脈辨識系統與方法
CN101976334B (zh) * 2010-10-26 2014-02-19 广东威创视讯科技股份有限公司 一种抗干扰的触摸点识别方法及装置
CN102184056B (zh) * 2011-04-26 2013-02-13 广东威创视讯科技股份有限公司 多触摸点识别方法及装置
CN102789574B (zh) 2012-07-02 2015-07-29 湖北微驾技术有限公司 基于三棱镜光学传感器的指纹图像几何矫正算法
CN104036160B (zh) * 2013-03-07 2019-03-15 腾讯科技（深圳）有限公司 一种网页浏览方法、装置及浏览器
KR102214503B1 (ko) * 2013-03-26 2021-02-09 삼성전자주식회사 지문 인식 방법 및 그 전자 장치
WO2015009111A1 (ko) * 2013-07-18 2015-01-22 삼성전자 주식회사 생체인식 기반 인증 방법 및 장치
TWI525555B (zh) * 2014-04-24 2016-03-11 友達光電股份有限公司 影像處理裝置及處理方法
KR102264808B1 (ko) * 2014-06-23 2021-06-14 삼성전자주식회사 지문 처리 방법 및 그 전자 장치
CN104598870A (zh) * 2014-07-25 2015-05-06 北京智膜科技有限公司 基于智能移动信息设备的指纹活体检测方法
CN104951748B (zh) * 2015-04-28 2018-12-07 广东光阵光电科技有限公司 一种假指纹识别方法及装置
KR101639986B1 (ko) * 2015-10-07 2016-07-15 크루셜텍 (주) 지문 등록 및 인증 속도 향상을 위한 지문 정보 프로세싱 방법 및 그 장치

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH02270075A (ja) * 1989-04-12 1990-11-05 Oki Electric Ind Co Ltd 指紋照合装置の給電方式
CN1221161A (zh) * 1997-12-24 1999-06-30 夏普公司 信息处理装置
CN101470804A (zh) * 2005-04-22 2009-07-01 日立欧姆龙金融系统有限公司 生物体认证装置
CN103870071A (zh) * 2012-12-13 2014-06-18 中国移动通信集团公司 一种触摸源识别方法及系统
CN104751103A (zh) * 2013-12-26 2015-07-01 齐发光电股份有限公司 手指指纹读取系统及指纹读取方法
WO2015105360A1 (ko) * 2014-01-10 2015-07-16 주식회사 고영테크놀러지 3차원 형상측정장치 및 방법
CN104615991A (zh) * 2015-02-10 2015-05-13 深圳市亚耕电子科技有限公司 指纹感测装置、电子产品及其指纹感测方法
CN105389541A (zh) * 2015-10-19 2016-03-09 广东欧珀移动通信有限公司 指纹图像的识别方法及装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3336749A4 *

Also Published As

Publication number Publication date
US10755076B2 (en) 2020-08-25
CN108427932B (zh) 2021-07-02
EP3336749A4 (en) 2018-08-08
EP3336749A1 (en) 2018-06-20
US20180253581A1 (en) 2018-09-06
US20190147210A1 (en) 2019-05-16
US10572714B2 (en) 2020-02-25
CN105389541B (zh) 2018-05-01
CN105389541A (zh) 2016-03-09
CN108427932A (zh) 2018-08-21

Similar Documents

Publication Publication Date Title
WO2017067270A1 (zh) 指纹图像的识别的方法、装置及终端
WO2017067287A1 (zh) 一种指纹识别的方法、装置及终端
TWI737040B (zh) 指紋識別方法、晶片及電子裝置
JP6487576B2 (ja) 指紋隆線点認識方法および装置
CN107491755B (zh) 用于手势识别的方法及装置
JP2021517330A (ja) 画像中の物体を識別するための方法、及び当該方法を実施するためのモバイル装置
CN103870071B (zh) 一种触摸源识别方法及系统
US11402918B2 (en) Method for controlling terminal apparatus, apparatus for controlling terminal apparatus, and computer-program product
CN106203326B (zh) 一种图像处理方法、装置及移动终端
CN110263667B (zh) 图像数据处理方法、装置以及电子设备
CN108509909A (zh) 一种指纹采集方法及装置
JP2018536948A (ja) 指紋画像を形成する方法及び指紋感知システム
US10037454B2 (en) Method and device for forming a fingerprint representation
CN110728201B (zh) 用于指纹识别的图像处理方法及装置
WO2021228194A1 (zh) 线缆检测方法、机器人和存储装置
JP5669572B2 (ja) 指紋認証装置
US10262185B2 (en) Image processing method and image processing system
TWI727514B (zh) 指紋識別方法、裝置、儲存介質，及終端
CN106599889A (zh) 一种识别字符的方法和装置
EP2541469A2 (en) Image recognition device, image recognition method and image recognition program
JP2007156841A5 (zh)
TW201909021A (zh) 電子裝置與其指紋辨識方法
CN114022856A (zh) 一种非结构化道路可行驶区域识别方法、电子设备及介质
CN109977734B (zh) 图像处理方法和装置
Sandnes A two-stage binarizing algorithm for automatic 2D: 4D finger ratio measurement of hands with non-separated fingers

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: 16856705

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 15759359

Country of ref document: US

WWE Wipo information: entry into national phase

Ref document number: 2016856705

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE