+

CN105303173A - Method and device for reducing misrecognition rate - Google Patents

Method and device for reducing misrecognition rate Download PDF

Info

Publication number
CN105303173A
CN105303173A CN201510681066.6A CN201510681066A CN105303173A CN 105303173 A CN105303173 A CN 105303173A CN 201510681066 A CN201510681066 A CN 201510681066A CN 105303173 A CN105303173 A CN 105303173A
Authority
CN
China
Prior art keywords
image data
fingerprint
reference image
fingerprint image
acquired
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201510681066.6A
Other languages
Chinese (zh)
Inventor
张强
王立中
周海涛
蒋奎
贺威
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Guangdong Oppo Mobile Telecommunications Corp Ltd
Original Assignee
Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Guangdong Oppo Mobile Telecommunications Corp Ltd filed Critical Guangdong Oppo Mobile Telecommunications Corp Ltd
Priority to CN201510681066.6A priority Critical patent/CN105303173A/en
Publication of CN105303173A publication Critical patent/CN105303173A/en
Priority to PCT/CN2016/091867 priority patent/WO2017067264A1/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING OR CALCULATING; COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/12Fingerprints or palmprints
    • G06V40/13Sensors therefor

Landscapes

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

Abstract

本发明实施例公开了一种降低误识别率的方法和装置,所述方法包括:当检测到无手指按压指纹传感器时,将获取的指纹传感器的空载图像数据作为基准图像数据;在有手指按压指纹传感器时,获取指纹图像数据;将所述指纹图像数据减去所述基准图像数据,得到新的指纹图像数据;使用所述新的指纹图像数据进行指纹识别。本发明实施例提供的技术方案,可以消除指纹传感器基准值偏移带来的误差,降低指纹识别系统的误识别率,延长指纹传感器的使用寿命。

The embodiment of the present invention discloses a method and device for reducing the false recognition rate, the method comprising: when it is detected that no finger is pressing the fingerprint sensor, using the acquired idle image data of the fingerprint sensor as the reference image data; when a finger is pressing the fingerprint sensor, acquiring the fingerprint image data; subtracting the reference image data from the fingerprint image data to obtain new fingerprint image data; and using the new fingerprint image data to perform fingerprint recognition. The technical solution provided by the embodiment of the present invention can eliminate the error caused by the offset of the fingerprint sensor reference value, reduce the false recognition rate of the fingerprint recognition system, and extend the service life of the fingerprint sensor.

Description

一种降低误识别率的方法和装置A method and device for reducing misrecognition rate

技术领域technical field

本发明实施例涉及指纹识别技术领域,尤其涉及一种降低误识别率的方法和装置。Embodiments of the present invention relate to the technical field of fingerprint identification, and in particular to a method and device for reducing a false identification rate.

背景技术Background technique

指纹识别技术,是指利用指纹的某些特点来对其主体进行识别和确认的技术。指纹识别系统采用指纹识别技术,其工作原理是:事先注册指纹,经过算法处理形成的指纹模板保存在某种介质上;验证时,比对现场指纹和保存的指纹模板,比对结果决定是否通过身份验证。指纹识别系统的核心硬件设备就是指纹传感器。Fingerprint identification technology refers to the technology of using certain characteristics of fingerprints to identify and confirm its subject. The fingerprint identification system adopts fingerprint identification technology, and its working principle is: register the fingerprint in advance, and save the fingerprint template formed by algorithm processing on a certain medium; when verifying, compare the on-site fingerprint and the saved fingerprint template, and the comparison result determines whether to pass Authentication. The core hardware device of the fingerprint identification system is the fingerprint sensor.

对于电容式的指纹传感器,由于器件表面随着时间推移,基准值会发生变化。由于基准值的变化,指纹识别系统提取的指纹图像特征可能会比较相近,指纹识别系统的误识别率会升高。For capacitive fingerprint sensors, the reference value will change over time due to the surface of the device. Due to the change of the benchmark value, the fingerprint image features extracted by the fingerprint recognition system may be relatively similar, and the false recognition rate of the fingerprint recognition system will increase.

发明内容Contents of the invention

本发明实施例提供一种降低误识别率的方法和装置,以降低指纹识别系统的误识别率。Embodiments of the present invention provide a method and device for reducing the false recognition rate, so as to reduce the false recognition rate of the fingerprint identification system.

一方面,本发明实施例提供了一种降低误识别率的方法,包括:On the one hand, the embodiment of the present invention provides a method for reducing the misrecognition rate, including:

当检测到无手指按压指纹传感器时,将获取的指纹传感器的空载图像数据作为基准图像数据;When no finger is detected to press the fingerprint sensor, the acquired no-load image data of the fingerprint sensor is used as the reference image data;

在有手指按压指纹传感器时,获取指纹图像数据;Acquire fingerprint image data when a finger presses the fingerprint sensor;

将所述指纹图像数据减去所述基准图像数据,得到新的指纹图像数据;Subtracting the reference image data from the fingerprint image data to obtain new fingerprint image data;

使用所述新的指纹图像数据进行指纹识别。Fingerprint identification is performed using the new fingerprint image data.

另一方面,本发明实施例还提供了一种降低误识别率的装置,包括:On the other hand, the embodiment of the present invention also provides a device for reducing the misrecognition rate, including:

基准图像数据获取单元,用于当检测到无手指按压指纹传感器时,将获取的指纹传感器的空载图像数据作为基准图像数据;A reference image data acquisition unit, configured to use the acquired no-load image data of the fingerprint sensor as the reference image data when no finger is detected to press the fingerprint sensor;

指纹图像数据获取单元,用于在有手指按压指纹传感器时,获取指纹图像数据;The fingerprint image data acquisition unit is used to acquire fingerprint image data when a finger presses the fingerprint sensor;

指纹图像数据更新单元,用于将所述指纹图像数据减去所述基准图像数据,得到新的指纹图像数据;A fingerprint image data updating unit, configured to subtract the reference image data from the fingerprint image data to obtain new fingerprint image data;

指纹识别单元,用于使用所述新的指纹图像数据进行指纹识别。A fingerprint identification unit, configured to perform fingerprint identification using the new fingerprint image data.

本发明实施例提供的技术方案,在手指没有按压指纹传感器时,获取指纹空载图像数据作为基准图像数据,并使用获取的指纹图像数据减去基准图像数据,得到新的指纹图像数据,新的指纹图像数据有效地消除了基准值的偏移造成的误差,最后使用新的指纹图像数据进行指纹识别,可以降低指纹识别系统的误识别率。In the technical solution provided by the embodiment of the present invention, when the finger does not press the fingerprint sensor, the fingerprint no-load image data is obtained as the reference image data, and the obtained fingerprint image data is used to subtract the reference image data to obtain new fingerprint image data, the new The fingerprint image data effectively eliminates the error caused by the offset of the reference value, and finally uses the new fingerprint image data for fingerprint identification, which can reduce the false identification rate of the fingerprint identification system.

附图说明Description of drawings

为了更清楚地说明本发明实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图做一简单地介绍,显而易见地,下面描述中的附图是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动的前提下,还可以根据这些附图获得其他的附图。In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description These are some embodiments of the present invention. Those skilled in the art can also obtain other drawings based on these drawings without creative work.

图1是本发明实施例一提供的一种降低误识别率的方法的流程示意图;FIG. 1 is a schematic flowchart of a method for reducing the false recognition rate provided by Embodiment 1 of the present invention;

图2是本发明实施例二提供的一种降低误识别率的方法的流程示意图;FIG. 2 is a schematic flowchart of a method for reducing the false recognition rate provided by Embodiment 2 of the present invention;

图3是本发明实施例三提供的一种降低误识别率的装置的结构示意图。FIG. 3 is a schematic structural diagram of a device for reducing a false recognition rate provided by Embodiment 3 of the present invention.

具体实施方式detailed description

为使本发明的目的、技术方案和优点更加清楚,以下将参照本发明实施例中的附图,通过实施方式清楚、完整地描述本发明的技术方案,显然,所描述的实施例是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例,都属于本发明保护的范围。In order to make the purpose, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described through implementation with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are the embodiment of the present invention. Some, but not all, embodiments. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

实施例一Embodiment one

图1是本发明实施例一提供的一种降低误识别率的方法的流程示意图。该方法可以由配置在终端中的降低误识别率的装置来执行,所述装置可由软件和/或硬件实现。如图1所示,本实施例提供的降低误识别率的方法具体包括如下步骤:FIG. 1 is a schematic flowchart of a method for reducing a false recognition rate provided by Embodiment 1 of the present invention. The method can be executed by a device for reducing the false recognition rate configured in the terminal, and the device can be implemented by software and/or hardware. As shown in Figure 1, the method for reducing the misrecognition rate provided by this embodiment specifically includes the following steps:

S110、当检测到无手指按压指纹传感器时,将获取的指纹传感器的空载图像数据作为基准图像数据;S110. When it is detected that no finger is pressing the fingerprint sensor, use the acquired no-load image data of the fingerprint sensor as the reference image data;

其中,所述指纹传感器可以为电容式指纹传感器。其工作过程是:指纹传感器上包含多个感应单元,将每个像素点上的电容感应单元充电到某一参考电压,当手指接触到指纹传感器时,感应单元进行放电,由于指纹上嵴是凸起的峪是凹下,电容值与距离有关,会在嵴和峪的处形成不同的电容值,因此嵴和峪处的放电速度也不同,嵴处的感应单元(电容量高)放电较慢,而处于峪处的感应单元(电容量低)放电较快,按照放电率的不同,可以探测到嵴和峪的位置,从而形成指纹图像数据。Wherein, the fingerprint sensor may be a capacitive fingerprint sensor. Its working process is: the fingerprint sensor contains multiple sensing units, and the capacitive sensing unit on each pixel is charged to a certain reference voltage. When the finger touches the fingerprint sensor, the sensing unit discharges. Since the ridge on the fingerprint is convex The rising valley is concave, and the capacitance value is related to the distance. Different capacitance values will be formed at the ridge and the valley, so the discharge speed at the ridge and the valley is also different, and the sensing unit (high capacitance) at the ridge discharges slower , while the sensing unit (low capacitance) at the ridge discharges faster, and according to the different discharge rates, the positions of the ridges and ridges can be detected, thereby forming fingerprint image data.

在正常情况下,当无手指按压指纹传感器时,指纹传感器获取的空载图像数据一般都为零(全黑或者全白),指纹传感器经过长时间的使用,性能会有所下降,指纹传感器的感应单元的感应面上会发生变化,即使没有手指按压,也能检测到不为零的指纹图像数据,此时,可以将获取的指纹传感器的空载图像数据作为基准图像数据。Under normal circumstances, when no finger presses the fingerprint sensor, the no-load image data acquired by the fingerprint sensor is generally zero (all black or all white), and the performance of the fingerprint sensor will decline after a long time of use. The sensing surface of the sensing unit will change, even if there is no finger pressing, the non-zero fingerprint image data can be detected. At this time, the acquired no-load image data of the fingerprint sensor can be used as the reference image data.

获取无手指按压时的空载图像数据作为基准图像数据时,为了提高获取的基准图像数据的准确性和稳定性,可以多次获取无手指按压指纹传感器时的空载图像数据;将所述获取的多组空载图像数据进行加权平均,并将加权平均后得到的图像数据作为基准图像数据。When obtaining the no-load image data when no finger is pressed as the reference image data, in order to improve the accuracy and stability of the obtained reference image data, the no-load image data when no finger is pressed on the fingerprint sensor can be obtained multiple times; Multiple sets of unloaded image data are weighted and averaged, and the image data obtained after the weighted average is used as the reference image data.

如指纹图像数据为N×N的矩阵表示的指纹图像的像素值,用O(i,j)表示基准图像第i行第j列的像素值,得到n组空载图像数据O1,O2,……,On后,则可以将k1O1+k2O2+……+knOn作为基准图像数据。其中,k1、k2、……、kn为加权系数,可以根据实际情况对其进行取值,如可以隔设定时间获取一次空载图像数据,时间越靠后加权系数相对较大,因为指纹传感器随着使用,基准值会不断的发生变化,根据使用时间的长短选取加权系数可以确保基准图像数据的稳定性和准确性。当设定时间较短时,可以取O1,O2,……,On的平均值,即将k1、k2、……、kn全都设置为1/n。For example, the fingerprint image data is the pixel value of the fingerprint image represented by an N×N matrix, and O(i, j) is used to represent the pixel value of the i-th row, j-th column of the reference image, and n sets of unloaded image data O 1 , O 2 are obtained. ,..., On, then k 1 O 1 +k 2 O 2 +...+k n O n can be used as the reference image data. Among them, k 1 , k 2 ,..., k n are weighting coefficients, which can be valued according to the actual situation. For example, no-load image data can be obtained once every set time, and the weighting coefficients are relatively larger when the time is later. Because the benchmark value of the fingerprint sensor will change continuously with use, selecting a weighting coefficient according to the length of use can ensure the stability and accuracy of the benchmark image data. When the setting time is short, the average value of O 1 , O 2 , ..., On can be taken, that is, k 1 , k 2 , ..., k n are all set to 1/ n .

S120、在有手指按压指纹传感器时,获取指纹图像数据;S120. Acquire fingerprint image data when a finger presses the fingerprint sensor;

当有手指按压指纹传感器时,获取正常的指纹图像数据,获取的指纹图像数据可以用来进行指纹识别,但基准值的偏差过大时,指纹识别系统的误识别率会上升,影响用户使用。When a finger presses the fingerprint sensor, the normal fingerprint image data is acquired, and the acquired fingerprint image data can be used for fingerprint identification, but when the deviation of the reference value is too large, the false identification rate of the fingerprint identification system will increase, affecting the use of users.

S130、将所述指纹图像数据减去所述基准图像数据,得到新的指纹图像数据;S130. Subtracting the reference image data from the fingerprint image data to obtain new fingerprint image data;

经过长时间的使用,指纹传感器的基准值会有所偏移,当使用获取的指纹图像数据减去基准图像数据,得到的新的指纹图像数据可以消除由于基准值的偏移带来的误差,确保使用新的指纹图像数据进行指纹识别时可以降低指纹识别系统的误识别率。After a long period of use, the reference value of the fingerprint sensor will shift. When the acquired fingerprint image data is subtracted from the reference image data, the new fingerprint image data obtained can eliminate the error caused by the deviation of the reference value. It is ensured that the false identification rate of the fingerprint identification system can be reduced when the new fingerprint image data is used for fingerprint identification.

S140、使用所述新的指纹图像数据进行指纹识别。S140. Perform fingerprint identification using the new fingerprint image data.

本实施例提供的技术方案,在手指没有按压指纹传感器时,获取指纹空载图像数据作为基准图像数据,并对多组基准图像数据进行加权平均处理,提高基准图像数据的准确度,然后使用获取的指纹图像数据减去基准图像数据,得到新的指纹图像数据,新的指纹图像数据有效的消除了基准值的偏移造成的误差,最后使用新的指纹图像数据进行指纹识别,可以降低指纹识别系统的误识别率。In the technical solution provided by this embodiment, when the finger does not press the fingerprint sensor, the fingerprint no-load image data is obtained as the reference image data, and multiple sets of reference image data are weighted and averaged to improve the accuracy of the reference image data, and then use the acquired Subtract the reference image data from the original fingerprint image data to get new fingerprint image data. The new fingerprint image data effectively eliminates the error caused by the offset of the reference value, and finally uses the new fingerprint image data for fingerprint identification, which can reduce the fingerprint identification time. The false recognition rate of the system.

实施例二Embodiment two

图2是本发明实施例二提供的一种降低误识别率的方法的流程示意图。本实施例是在实施例一的基础上增加相关步骤和对相关步骤进行了优化。如图2所示,本实施提供的降低误识别率的方法包括如下步骤:FIG. 2 is a schematic flowchart of a method for reducing the false recognition rate provided by Embodiment 2 of the present invention. In this embodiment, relevant steps are added and optimized on the basis of the first embodiment. As shown in Figure 2, the method for reducing the false recognition rate provided by this implementation includes the following steps:

S210、当检测到无手指按压指纹传感器时,将获取的指纹传感器的空载图像数据作为基准图像数据;S210. When it is detected that no finger is pressing the fingerprint sensor, use the acquired no-load image data of the fingerprint sensor as the reference image data;

S220、在有手指按压指纹传感器时,获取指纹图像数据;S220. Acquire fingerprint image data when a finger presses the fingerprint sensor;

S230、将所述获取的基准图像数据和指纹图像数据进行存储;S230. Store the acquired reference image data and fingerprint image data;

为了方便的对指纹数据进行处理,可以将获取的基准图像数据和指纹图像数据存储在指纹识别系统的存储器中,如在手机中使用指纹传感器时,将手机处理器获取的基准图像数据和指纹图像数据存储在手机内存中。In order to process the fingerprint data conveniently, the obtained reference image data and fingerprint image data can be stored in the memory of the fingerprint recognition system, such as when using a fingerprint sensor in a mobile phone, the reference image data and fingerprint image data obtained by the mobile phone processor The data is stored in the phone memory.

S240、将所述指纹图像数据中各个像素的灰度值与所述基准图像数据中对应像素的灰度值相减,得到新的指纹图像数据;S240. Subtract the gray value of each pixel in the fingerprint image data from the gray value of the corresponding pixel in the reference image data to obtain new fingerprint image data;

获取的指纹图像数据实质是用数值表示的指纹图像各个像素的灰度值,如设指纹图像为N×N的矩阵,用I(i,j)表示指纹图像第i行第j列的像素灰度值,用Z(i,j)表示基准图像第i行第j列的像素灰度值,则新得到的指纹图像数据的第i行第j列为K(i,j)=I(i,j)-Z(i,j),将指纹图像各行各列的像素的灰度值减去基准图像对应行和列的像素的灰度值,即可得到一组新的指纹图像数据。The acquired fingerprint image data is essentially the gray value of each pixel of the fingerprint image represented by a numerical value. For example, if the fingerprint image is an N×N matrix, I(i, j) represents the pixel gray value of the i-th row and j-th column of the fingerprint image. degree value, with Z (i, j) to represent the pixel gray value of the i-th row and j-column of the reference image, then the i-th row and j-column of the newly obtained fingerprint image data is K (i, j)=I(i , j)-Z(i, j), subtract the gray value of the pixels in the corresponding row and column of the reference image from the gray value of the pixels in each row and column of the fingerprint image to obtain a new set of fingerprint image data.

S250、使用所述新的指纹图像数据进行指纹识别。S250. Perform fingerprint recognition using the new fingerprint image data.

指纹识别的过程是一个指纹验证与辨识的过程,需要使用采集的指纹图像与指纹数据库中存储的模板指纹进行匹配。获取指纹图像数据之后,即可根据指纹图像数据生成原始指纹图像,使用原始指纹图像进行指纹识别。The process of fingerprint identification is a process of fingerprint verification and identification, which needs to use the collected fingerprint image to match the template fingerprint stored in the fingerprint database. After the fingerprint image data is acquired, an original fingerprint image can be generated according to the fingerprint image data, and the original fingerprint image can be used for fingerprint identification.

进一步的,提取所述新的指纹图像数据对应的图像的特征点;Further, extracting the feature points of the image corresponding to the new fingerprint image data;

首先采用相应的指纹算法对原始指纹图像进行预处理,预处理是指对含噪声及伪特征的指纹图像采用一定的算法加以处理,使其纹线结构清晰,特征信息突出,改善指纹图像的质量,提高特征提取的准确性。通常,预处理过程包括归一化、图像分割、增强、二值化等处理。然后对指纹的细节特征进行提取,提取的特征点如纹线的起点、终点、结合点和分叉点等。First, the corresponding fingerprint algorithm is used to preprocess the original fingerprint image. Preprocessing refers to the use of certain algorithms to process the fingerprint image containing noise and false features, so that the line structure is clear, the feature information is prominent, and the quality of the fingerprint image is improved. , to improve the accuracy of feature extraction. Usually, the preprocessing process includes normalization, image segmentation, enhancement, binarization and other processing. Then extract the detailed features of the fingerprint, such as the starting point, end point, joint point and bifurcation point of the ridge line.

进一步的,将所述提取的特征点与预先设置的指纹模板进行匹配。Further, the extracted feature points are matched with a preset fingerprint template.

指纹图像的匹配主要是特征点的匹配,预先设置的指纹模板中存储的是根据预先录入的指纹图像提取的指纹特征点,将提取的指纹图像的特征点与预先设置的指纹模板进行匹配的过程主要是计算提取的指纹图像的特征点与已存储的特征模板的相似程度,如通过匹配,二者的相似程度达到设定阈值,则表示匹配成功。The matching of the fingerprint image is mainly the matching of feature points. The pre-set fingerprint template stores the fingerprint feature points extracted from the pre-registered fingerprint image, and the process of matching the feature points of the extracted fingerprint image with the pre-set fingerprint template It mainly calculates the degree of similarity between the feature points of the extracted fingerprint image and the stored feature templates. If the similarity between the two reaches the set threshold through matching, it means that the matching is successful.

本实施例提供的技术方案,将指纹数据进行存储,方便指纹识别系统进行调用,对获取的指纹图像数据中的像素值进行处理,可以精确地获取新的指纹图像数据,提取新的指纹图像的特征点并进行匹配识别,降低了指纹识别系统的误识别率。The technical solution provided by this embodiment stores the fingerprint data, which is convenient for the fingerprint identification system to call, and processes the pixel values in the acquired fingerprint image data, so that new fingerprint image data can be accurately acquired, and the value of the new fingerprint image can be extracted. The feature points are matched and identified, which reduces the false identification rate of the fingerprint identification system.

实施例三Embodiment Three

图3是本发明实施例三提供的一种降低误识别率的装置的结构示意图。如图3所示,该装置包括:FIG. 3 is a schematic structural diagram of a device for reducing a false recognition rate provided by Embodiment 3 of the present invention. As shown in Figure 3, the device includes:

基准图像数据获取单元310,用于当检测到无手指按压指纹传感器时,将获取的指纹传感器的空载图像数据作为基准图像数据;A reference image data acquisition unit 310, configured to use the acquired no-load image data of the fingerprint sensor as the reference image data when no finger is detected to press the fingerprint sensor;

指纹图像数据获取单元320,用于在有手指按压指纹传感器时,获取指纹图像数据;A fingerprint image data acquisition unit 320, configured to acquire fingerprint image data when a finger presses the fingerprint sensor;

指纹图像数据更新单元330,用于将所述指纹图像数据减去所述基准图像数据,得到新的指纹图像数据;A fingerprint image data update unit 330, configured to subtract the reference image data from the fingerprint image data to obtain new fingerprint image data;

指纹识别单元340,用于使用所述新的指纹图像数据进行指纹识别。The fingerprint identification unit 340 is configured to use the new fingerprint image data to perform fingerprint identification.

进一步的,所述基准图像数据获取单元310包括:Further, the reference image data acquisition unit 310 includes:

空载图像数据获取子单元311,用于多次获取无手指按压指纹传感器时的空载图像数据;The no-load image data acquisition subunit 311 is used to acquire no-load image data when no finger presses the fingerprint sensor multiple times;

基准图像数据获取子单元312,用于将所述获取的多组空载图像数据进行加权平均,并将加权平均后得到的图像数据作为基准图像数据。The reference image data acquisition subunit 312 is configured to perform weighted average on the multiple sets of acquired airborne image data, and use the image data obtained after the weighted average as reference image data.

进一步的,所述指纹图像数据更新单元330具体用于:Further, the fingerprint image data updating unit 330 is specifically used for:

将所述指纹图像数据中各个像素的灰度值与所述基准图像数据中对应像素的灰度值相减,得到新的指纹图像数据。Subtracting the gray value of each pixel in the fingerprint image data from the gray value of a corresponding pixel in the reference image data to obtain new fingerprint image data.

进一步的,所述装置还包括:Further, the device also includes:

图像数据存储单元350,用于将所述获取的基准图像数据和指纹图像数据进行存储。The image data storage unit 350 is configured to store the acquired reference image data and fingerprint image data.

进一步的,所述指纹识别单元340包括:Further, the fingerprint identification unit 340 includes:

特征点提取子单元341,用于提取所述新的指纹图像数据对应的图像的特征点;A feature point extraction subunit 341, configured to extract feature points of an image corresponding to the new fingerprint image data;

特征点匹配子单元342,用于将所述提取的特征点与预先设置的指纹模板进行匹配。The feature point matching subunit 342 is configured to match the extracted feature points with a preset fingerprint template.

上述装置可执行本发明任意实施例所提供的降低误识别率的方法,具备执行方法相应的功能模块和有益效果。The above-mentioned device can execute the method for reducing the false recognition rate provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.

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。Note that the above are only preferred embodiments of the present invention and applied technical principles. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and can also include more other equivalent embodiments without departing from the concept of the present invention, and the present invention The scope is determined by the scope of the appended claims.

Claims (10)

1.一种降低误识别率的方法,其特征在于,包括:1. A method for reducing false recognition rate, characterized in that, comprising: 当检测到无手指按压指纹传感器时,将获取的指纹传感器的空载图像数据作为基准图像数据;When no finger is detected to press the fingerprint sensor, the acquired no-load image data of the fingerprint sensor is used as the reference image data; 在有手指按压指纹传感器时,获取指纹图像数据;Acquire fingerprint image data when a finger presses the fingerprint sensor; 将所述指纹图像数据减去所述基准图像数据,得到新的指纹图像数据;Subtracting the reference image data from the fingerprint image data to obtain new fingerprint image data; 使用所述新的指纹图像数据进行指纹识别。Fingerprint identification is performed using the new fingerprint image data. 2.根据权利要求1所述的方法,其特征在于,所述当检测到无手指按压指纹传感器时,将获取的指纹传感器的空载图像数据作为基准图像数据,包括:2. The method according to claim 1, wherein when it is detected that no finger is pressed on the fingerprint sensor, the acquired no-load image data of the fingerprint sensor is used as the reference image data, comprising: 多次获取无手指按压指纹传感器时的空载图像数据;Acquire the no-load image data when no finger presses the fingerprint sensor multiple times; 将所述获取的多组空载图像数据进行加权平均,并将加权平均后得到的图像数据作为基准图像数据。Weighted averaging is performed on the multiple sets of airborne image data acquired, and the image data obtained after the weighted average is used as reference image data. 3.根据权利要求1所述的方法,其特征在于,所述将所述指纹图像数据减去所述基准图像数据,得到新的指纹图像数据,包括:3. The method according to claim 1, wherein said subtracting said reference image data from said fingerprint image data to obtain new fingerprint image data comprises: 将所述指纹图像数据中各个像素的灰度值与所述基准图像数据中对应像素的灰度值相减,得到新的指纹图像数据。Subtracting the gray value of each pixel in the fingerprint image data from the gray value of a corresponding pixel in the reference image data to obtain new fingerprint image data. 4.根据权利要求1所述的方法,其特征在于,所述将所述指纹图像数据减去所述基准图像数据之前,还包括:4. The method according to claim 1, wherein, before subtracting the reference image data from the fingerprint image data, further comprising: 将所述获取的基准图像数据和指纹图像数据进行存储。The acquired reference image data and fingerprint image data are stored. 5.根据权利要求1所述的方法,其特征在于,所述使用所述新的指纹图像数据进行指纹识别,包括:5. The method according to claim 1, wherein said using said new fingerprint image data to carry out fingerprint identification comprises: 提取所述新的指纹图像数据对应的图像的特征点;extracting the feature points of the image corresponding to the new fingerprint image data; 将所述提取的特征点与预先设置的指纹模板进行匹配。Match the extracted feature points with a preset fingerprint template. 6.一种降低误识别率的装置,其特征在于,包括:6. A device for reducing misrecognition rate, characterized in that, comprising: 基准图像数据获取单元,用于当检测到无手指按压指纹传感器时,将获取的指纹传感器的空载图像数据作为基准图像数据;A reference image data acquisition unit, configured to use the acquired no-load image data of the fingerprint sensor as the reference image data when no finger is detected to press the fingerprint sensor; 指纹图像数据获取单元,用于在有手指按压指纹传感器时,获取指纹图像数据;The fingerprint image data acquisition unit is used to acquire fingerprint image data when a finger presses the fingerprint sensor; 指纹图像数据更新单元,用于将所述指纹图像数据减去所述基准图像数据,得到新的指纹图像数据;A fingerprint image data updating unit, configured to subtract the reference image data from the fingerprint image data to obtain new fingerprint image data; 指纹识别单元,用于使用所述新的指纹图像数据进行指纹识别。A fingerprint identification unit, configured to perform fingerprint identification using the new fingerprint image data. 7.根据权利要求6所述的装置,其特征在于,所述基准图像数据获取单元包括:7. The device according to claim 6, wherein the reference image data acquisition unit comprises: 空载图像数据获取子单元,用于多次获取无手指按压指纹传感器时的空载图像数据;The no-load image data acquisition subunit is used to acquire no-load image data when no finger presses the fingerprint sensor multiple times; 基准图像数据获取子单元,用于将所述获取的多组空载图像数据进行加权平均,并将加权平均后得到的图像数据作为基准图像数据。The reference image data acquisition subunit is configured to perform weighted average on the multiple sets of acquired empty image data, and use the image data obtained after the weighted average as the reference image data. 8.根据权利要求6所述的装置,其特征在于,所述指纹图像数据更新单元具体用于:8. The device according to claim 6, wherein the fingerprint image data updating unit is specifically used for: 将所述指纹图像数据中各个像素的灰度值与所述基准图像数据中对应像素的灰度值相减,得到新的指纹图像数据。Subtracting the gray value of each pixel in the fingerprint image data from the gray value of a corresponding pixel in the reference image data to obtain new fingerprint image data. 9.根据权利要求6所述的装置,其特征在于,所述装置还包括:9. The device according to claim 6, further comprising: 图像数据存储单元,用于将所述获取的基准图像数据和指纹图像数据进行存储。An image data storage unit, configured to store the acquired reference image data and fingerprint image data. 10.根据权利要求6所述的装置,其特征在于,所述指纹识别单元包括:10. The device according to claim 6, wherein the fingerprint recognition unit comprises: 特征点提取子单元,用于提取所述新的指纹图像数据对应的图像的特征点;The feature point extraction subunit is used to extract the feature points of the image corresponding to the new fingerprint image data; 特征点匹配子单元,用于将所述提取的特征点与预先设置的指纹模板进行匹配。The feature point matching subunit is used to match the extracted feature points with a preset fingerprint template.
CN201510681066.6A 2015-10-19 2015-10-19 Method and device for reducing misrecognition rate Pending CN105303173A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201510681066.6A CN105303173A (en) 2015-10-19 2015-10-19 Method and device for reducing misrecognition rate
PCT/CN2016/091867 WO2017067264A1 (en) 2015-10-19 2016-07-27 Method and device for reducing misrecognition rate and smart mobile terminal

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510681066.6A CN105303173A (en) 2015-10-19 2015-10-19 Method and device for reducing misrecognition rate

Publications (1)

Publication Number Publication Date
CN105303173A true CN105303173A (en) 2016-02-03

Family

ID=55200417

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510681066.6A Pending CN105303173A (en) 2015-10-19 2015-10-19 Method and device for reducing misrecognition rate

Country Status (2)

Country Link
CN (1) CN105303173A (en)
WO (1) WO2017067264A1 (en)

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105913027A (en) * 2016-04-13 2016-08-31 时建华 Data transmission method with high safety
CN105930777A (en) * 2016-04-13 2016-09-07 时建华 ATM (Automatic Teller Machine) using fingerprint for identification
CN105930776A (en) * 2016-04-13 2016-09-07 时建华 High tension switchgear with identity verification function
CN105956541A (en) * 2016-04-27 2016-09-21 广东欧珀移动通信有限公司 Fingerprint identification method, device and mobile terminal
CN105956564A (en) * 2016-05-06 2016-09-21 广东欧珀移动通信有限公司 Fingerprint image processing method and equipment
CN106203326A (en) * 2016-07-07 2016-12-07 广东欧珀移动通信有限公司 A kind of image processing method, device and mobile terminal
CN106203281A (en) * 2016-06-27 2016-12-07 广东欧珀移动通信有限公司 A fingerprint image processing method and device
WO2017067264A1 (en) * 2015-10-19 2017-04-27 广东欧珀移动通信有限公司 Method and device for reducing misrecognition rate and smart mobile terminal
CN107133577A (en) * 2017-04-18 2017-09-05 北京小米移动软件有限公司 A kind of fingerprint identification method and device
CN107231240A (en) * 2017-07-06 2017-10-03 郑州靓岛建筑设计有限公司 A kind of higher dual identity recognition methods of security
CN107392161A (en) * 2017-07-27 2017-11-24 北京小米移动软件有限公司 The recognition methods of biological information and device, computer-readable recording medium
CN107886083A (en) * 2017-11-27 2018-04-06 北京小米移动软件有限公司 The method, apparatus and readable storage medium storing program for executing of fingerprint module calibration
CN108604294A (en) * 2016-08-04 2018-09-28 华为技术有限公司 Fingerprint processing method and terminal in terminal
CN109074493A (en) * 2017-03-10 2018-12-21 指纹卡有限公司 Inhibit the damage data in fingerprint image
CN109241859A (en) * 2018-08-13 2019-01-18 Oppo广东移动通信有限公司 Fingerprint identification method and Related product
CN109711308A (en) * 2018-12-19 2019-05-03 北京集创北方科技股份有限公司 Fingerprint component, electronic equipment and its fingerprint signal processing method
CN113312944A (en) * 2020-02-27 2021-08-27 北京小米移动软件有限公司 Image acquisition method, calibration method, under-screen fingerprint identification device and mobile terminal

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20210047996A (en) * 2019-10-22 2021-05-03 삼성디스플레이 주식회사 Display device

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1257595A (en) * 1997-04-21 2000-06-21 数字人公司 Fingerprint recognition system
CN1542684A (en) * 2003-04-28 2004-11-03 上海科比生物识别技术有限公司 Acquisition and splicing method of three-face rolling fingerprint
CN101819630A (en) * 2010-04-09 2010-09-01 浙江理工大学 Fingerprint identification system and identification method based on pressure sensitivity fingerprint acquisition and DSP (Digital Signal Processing) algorithm
CN103886297A (en) * 2014-03-26 2014-06-25 浙江大学 Dynamic optical detection method for true and false fingerprints

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
SE0501763L (en) * 2005-08-03 2007-02-04 Precise Biometrics Ab Method and apparatus for aligning a loaded fingerprint
CN105303173A (en) * 2015-10-19 2016-02-03 广东欧珀移动通信有限公司 Method and device for reducing misrecognition rate

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1257595A (en) * 1997-04-21 2000-06-21 数字人公司 Fingerprint recognition system
CN1542684A (en) * 2003-04-28 2004-11-03 上海科比生物识别技术有限公司 Acquisition and splicing method of three-face rolling fingerprint
CN101819630A (en) * 2010-04-09 2010-09-01 浙江理工大学 Fingerprint identification system and identification method based on pressure sensitivity fingerprint acquisition and DSP (Digital Signal Processing) algorithm
CN103886297A (en) * 2014-03-26 2014-06-25 浙江大学 Dynamic optical detection method for true and false fingerprints

Cited By (25)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2017067264A1 (en) * 2015-10-19 2017-04-27 广东欧珀移动通信有限公司 Method and device for reducing misrecognition rate and smart mobile terminal
CN105930777A (en) * 2016-04-13 2016-09-07 时建华 ATM (Automatic Teller Machine) using fingerprint for identification
CN105930776A (en) * 2016-04-13 2016-09-07 时建华 High tension switchgear with identity verification function
CN105913027A (en) * 2016-04-13 2016-08-31 时建华 Data transmission method with high safety
CN105956541A (en) * 2016-04-27 2016-09-21 广东欧珀移动通信有限公司 Fingerprint identification method, device and mobile terminal
CN105956541B (en) * 2016-04-27 2018-09-11 广东欧珀移动通信有限公司 Fingerprint identification method, device and mobile terminal
CN105956564A (en) * 2016-05-06 2016-09-21 广东欧珀移动通信有限公司 Fingerprint image processing method and equipment
CN106203281A (en) * 2016-06-27 2016-12-07 广东欧珀移动通信有限公司 A fingerprint image processing method and device
CN106203281B (en) * 2016-06-27 2017-10-31 广东欧珀移动通信有限公司 A fingerprint image processing method and device
CN106203326A (en) * 2016-07-07 2016-12-07 广东欧珀移动通信有限公司 A kind of image processing method, device and mobile terminal
CN106203326B (en) * 2016-07-07 2018-07-27 广东欧珀移动通信有限公司 A kind of image processing method, device and mobile terminal
CN108604294A (en) * 2016-08-04 2018-09-28 华为技术有限公司 Fingerprint processing method and terminal in terminal
CN109074493A (en) * 2017-03-10 2018-12-21 指纹卡有限公司 Inhibit the damage data in fingerprint image
CN109074493B (en) * 2017-03-10 2020-06-02 指纹卡有限公司 Suppressing damage data in fingerprint images
CN107133577A (en) * 2017-04-18 2017-09-05 北京小米移动软件有限公司 A kind of fingerprint identification method and device
CN107133577B (en) * 2017-04-18 2020-02-07 北京小米移动软件有限公司 Fingerprint identification method and device
CN107231240A (en) * 2017-07-06 2017-10-03 郑州靓岛建筑设计有限公司 A kind of higher dual identity recognition methods of security
CN107392161A (en) * 2017-07-27 2017-11-24 北京小米移动软件有限公司 The recognition methods of biological information and device, computer-readable recording medium
CN107886083A (en) * 2017-11-27 2018-04-06 北京小米移动软件有限公司 The method, apparatus and readable storage medium storing program for executing of fingerprint module calibration
WO2020034710A1 (en) * 2018-08-13 2020-02-20 Oppo广东移动通信有限公司 Fingerprint recognition method and related product
CN109241859A (en) * 2018-08-13 2019-01-18 Oppo广东移动通信有限公司 Fingerprint identification method and Related product
CN109241859B (en) * 2018-08-13 2021-05-04 Oppo广东移动通信有限公司 Fingerprint identification method and related products
CN109711308A (en) * 2018-12-19 2019-05-03 北京集创北方科技股份有限公司 Fingerprint component, electronic equipment and its fingerprint signal processing method
CN109711308B (en) * 2018-12-19 2021-06-01 北京集创北方科技股份有限公司 Fingerprint assembly, electronic equipment and fingerprint signal processing method thereof
CN113312944A (en) * 2020-02-27 2021-08-27 北京小米移动软件有限公司 Image acquisition method, calibration method, under-screen fingerprint identification device and mobile terminal

Also Published As

Publication number Publication date
WO2017067264A1 (en) 2017-04-27

Similar Documents

Publication Publication Date Title
CN105303173A (en) Method and device for reducing misrecognition rate
US11288480B2 (en) Method for authenticating a finger of a user of an electronic device
CN105224931B (en) Method and device for collecting fingerprints
US10169640B2 (en) Method for fingerprint identification and terminal
WO2020156033A1 (en) Fingerprint verification method and related apparatus
CN105243370A (en) A fingerprint identification method, fingerprint identification device and mobile terminal
CN106503609A (en) The recognition methods of fingerprint ridge point and device
CN106203326B (en) A kind of image processing method, device and mobile terminal
CN105303174B (en) fingerprint input method and device
US10037454B2 (en) Method and device for forming a fingerprint representation
WO2017206914A1 (en) Fingerprint recognition method, fingerprint recognition system, and electronic device
WO2017161636A1 (en) Fingerprint-based terminal payment method and device
CN104484652A (en) Method for fingerprint recognition
US9704015B2 (en) Fingerprint image processing method and device
CN105844265B (en) Fingerprint image processing method and device
CN110348386A (en) A kind of facial image recognition method based on fuzzy theory, device and equipment
US20200134341A1 (en) Intelligent terminal
US11120284B2 (en) Startup authentication method for intelligent terminal
CN111079551B (en) Finger vein recognition method, device and storage medium based on singular value decomposition
CN116434352B (en) Fingerprint library generation method, fingerprint identification device and storage medium
Wang et al. Fingerprint image enhancement based on morphological filter
CN114816090A (en) Method and system for manually awakening mouse without need of manual awakening
CN116363005A (en) Method and equipment for acquiring fingerprint characteristics under screen based on optics
Latha et al. Extraction of dynamic region of interest (ROI) for palmprint
CN115690857A (en) Method and device for detecting fingerprint peeling, fingerprint input method and device and chip

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20160203

RJ01 Rejection of invention patent application after publication
点击 这是indexloc提供的php浏览器服务,不要输入任何密码和下载