Nothing Special   »   [go: up one dir, main page]

WO2016074248A1 - 基于人脸识别的验证使用方法及装置 - Google Patents

基于人脸识别的验证使用方法及装置 Download PDF

Info

Publication number
WO2016074248A1
WO2016074248A1 PCT/CN2014/091213 CN2014091213W WO2016074248A1 WO 2016074248 A1 WO2016074248 A1 WO 2016074248A1 CN 2014091213 W CN2014091213 W CN 2014091213W WO 2016074248 A1 WO2016074248 A1 WO 2016074248A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
distance
spot
template
eyes
Prior art date
Application number
PCT/CN2014/091213
Other languages
English (en)
French (fr)
Inventor
张黎君
熊胜峰
叶培锋
郑旭升
田辉
Original Assignee
深圳市三木通信技术有限公司
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 深圳市三木通信技术有限公司 filed Critical 深圳市三木通信技术有限公司
Priority to PCT/CN2014/091213 priority Critical patent/WO2016074248A1/zh
Priority to CN201480001802.2A priority patent/CN104584030B/zh
Publication of WO2016074248A1 publication Critical patent/WO2016074248A1/zh

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31User authentication
    • G06F21/32User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR 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
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2221/00Indexing scheme relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F2221/21Indexing scheme relating to G06F21/00 and subgroups addressing additional information or applications relating to security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F2221/2133Verifying human interaction, e.g., Captcha

Definitions

  • the invention belongs to the field of intelligent terminals, and in particular relates to a method and a device for verifying and using based on face recognition.
  • Mobile terminals commonly known as mobile phones, have passed the analog era, the digital age and the intelligent era. Most of the existing mobile phones are smart phones, and their functions are also powerful, including: Internet, video calls, app applications, etc. Function, mobile phone has gradually become an essential tool for people in their daily lives.
  • An object of the embodiments of the present invention is to provide a method for verifying the use of a mobile phone based on face recognition, which solves the problem of low security in the prior art.
  • a method for verifying and using a face recognition method includes the following steps:
  • the person image is compared with the image template, and it is determined whether the smart device is turned on according to the comparison result.
  • the implementation manner of comparing the image of the person with the image template is specifically:
  • Extracting the gray value of each pixel in the image of the person, extracting the pixel point and its coordinates within the range of the gray value of the spot, and the pixel within the range of the gray value of the spot is the spot, such as the distance between the adjacent spots is less than the setting
  • the distance is divided into a spot area, and all the spots are traversed to distinguish all the spot areas; all the spot areas are displayed at corresponding positions of the person image, and all the spot areas in the image template are extracted to the center of the eyes.
  • the point is the origin, 360° uniformly emits a plurality of rays through all the plaque regions, and the distance between the edge of each plaque region and the center point is obtained according to the intersection of the plurality of ray and the edge of all the plaque regions; and the edge of each plaque region in the image of the person is obtained
  • the distance between the center points and the distance between the edge of each spot in the image template and the center point are compared with the distance between the edge of each spot in the image and the center point. For example, there is a set number of spot areas in the image template. In the presence of a character image, it is determined that the alignment is not similar, otherwise the similarity is determined.
  • the method further includes:
  • the comparing the image of the person with the image template, and determining whether to open the smart device according to the comparison result specifically includes:
  • the distance between the origin of the character image and the coordinates of the nth intersection is the set threshold and is a constant.
  • the comparing the image of the person with the image template, and determining whether to open the smart device according to the comparison result specifically includes:
  • the contour of the character image and the midpoint of the eyes of the character image Obtaining the contour of the character image and the midpoint of the eyes of the character image, acquiring the contour of the image template and the midpoint of the eyes, and matching the midpoint of the eyes of the image module with the midpoint of the eyes of the person image, such as the contour of the character image
  • the contour of the image module also coincides with the smart device.
  • an intelligent terminal device comprising:
  • An extracting unit configured to extract an image of the operator's face from the photo
  • the image comparison unit is configured to compare the image of the person with the image template, and determine whether to open the smart device according to the comparison result.
  • the image comparison unit is specifically configured to:
  • Extracting the gray value of each pixel in the image of the person, extracting the pixel point and its coordinates within the range of the gray value of the spot, and the pixel within the range of the gray value of the spot is the spot, such as the distance between the adjacent spots is less than the setting
  • the distance is divided into a spot area, and all the spots are traversed to distinguish all the spot areas; all the spot areas are displayed at corresponding positions of the person image, and all the spot areas in the image template are extracted to the center of the eyes.
  • the point is the origin, 360° uniformly emits a plurality of rays through all the plaque regions, and the distance between the edge of each plaque region and the center point is obtained according to the intersection of the plurality of ray and the edge of all the plaque regions; and the edge of each plaque region in the image of the person is obtained
  • the distance between the center points and the distance between the edge of each spot in the image template and the center point are compared with the distance between the edge of each spot in the image and the center point. For example, there is a set number of spot areas in the image template. In the presence of a character image, it is determined that the alignment is not similar, otherwise the similarity is determined.
  • the device further includes:
  • a replacement unit configured to replace the image template with the character image after the opening unit turns on the smart device.
  • the image comparison unit is specifically configured to:
  • the distance between the origin of the character image and the coordinates of the nth intersection is the set threshold and is a constant.
  • the image comparison unit is specifically configured to:
  • the contour of the character image and the midpoint of the eyes of the character image Obtaining the contour of the character image and the midpoint of the eyes of the character image, acquiring the contour of the image template and the midpoint of the eyes, and matching the midpoint of the eyes of the image module with the midpoint of the eyes of the person image, such as the contour of the character image
  • the contour of the image module also coincides with the smart device.
  • the mobile phone provided by the technical solution of the present invention uses a face recognition method to monitor and verify the mobile phone, so that when the mobile phone user changes, the non-owner's operation can be automatically shielded, so that the mobile phone has high security. A little bit.
  • FIG. 1 is a flow chart of a method for verifying and using face recognition based on the present invention
  • FIG. 2 is a structural diagram of an intelligent terminal device provided by the present invention.
  • a specific embodiment of the present invention provides a method for verifying and using face recognition, which is performed by a mobile phone or other smart device (for example, an iPad, a PDA, etc.).
  • the method is as shown in FIG. 1 and includes the following steps:
  • the above comparison results may be: similar or dissimilar. Because the face image of the operator may not be constant, the possibility of being identical is not great, because the face will change, so only the similarity can be realized here, and the similar method is determined. See the description below.
  • the implementation manner of comparing the image of the person with the image template may be:
  • Extracting the gray value of each pixel in the image of the person, extracting the pixel point and its coordinates within the range of the gray value of the spot, and the pixel within the range of the gray value of the spot is the spot, such as the distance between the adjacent spots is less than the setting
  • the distance is divided into a spot area, and all the spots are traversed to distinguish all the spot areas; all the spot areas are displayed at corresponding positions of the person image, and all the spot areas in the image template are extracted to the center of the eyes.
  • the point is the origin, 360° uniformly emits a plurality of rays through all the plaque regions, and the distance between the edge of each plaque region and the center point is obtained according to the intersection of the plurality of ray and the edge of all the plaque regions; and the edge of each plaque region in the image of the person is obtained
  • the distance between the center points and the distance between the edge of each spot in the image template and the center point are compared with the distance between the edge of each spot in the image and the center point. For example, there is a set number of spot areas in the image template. In the presence of a character image, it is determined that the alignment is not similar, otherwise the similarity is determined.
  • This design mainly uses the spot area to identify the image of the person, because for the portrait, there are generally spots, and the gray value of the spot is basically in a range, and it is easier to distinguish the gray value, then all the spots are compared.
  • the problem can be achieved by distinguishing the images of the characters, because for each person, the spots must not be consistent, and all of them can be clearly distinguished.
  • the central point of the eyes is used as a reference point to avoid people's gain. The effect of the contrast caused by long thinness on the result can be avoided by taking the center point of both eyes as the reference point, so the above method has the advantage of high accuracy.
  • the foregoing method may further include:
  • the image template is replaced with the character image.
  • the comparing the image of the person with the image template, and determining whether to open the smart device according to the comparison result specifically includes:
  • the specific implementation manner of the foregoing 103 may be:
  • the distance between the origin of the character image and the coordinates of the nth intersection is the set threshold and is a constant.
  • the specific implementation manner of the foregoing 103 may be:
  • the contour of the character image and the midpoint of the eyes of the character image Obtaining the contour of the character image and the midpoint of the eyes of the character image, acquiring the contour of the image template and the midpoint of the eyes, and matching the midpoint of the eyes of the image module with the midpoint of the eyes of the person image, such as the contour of the character image
  • the contour of the image module also coincides with the smart device.
  • This method is equivalent to the addition of the learning function, that is, each comparison can guarantee that it belongs to the latest image.
  • the embodiment of the present invention further provides an intelligent terminal device. As shown in FIG. 2, the device includes:
  • the obtaining unit 21 is configured to obtain a photo of the operator
  • An extracting unit 22 configured to extract an image of the face of the operator from the photo
  • the image comparison unit 25 is configured to compare the person image with the image template, and determine whether to open the smart device according to the comparison result.
  • the image comparison unit 25 is specifically configured to:
  • Extracting the gray value of each pixel in the image of the person, extracting the pixel point and its coordinates within the range of the gray value of the spot, and the pixel within the range of the gray value of the spot is the spot, such as the distance between the adjacent spots is less than the setting
  • the distance is divided into a spot area, and all the spots are traversed to distinguish all the spot areas; all the spot areas are displayed at corresponding positions of the person image, and all the spot areas in the image template are extracted to the center of the eyes.
  • the point is the origin, 360° uniformly emits a plurality of rays through all the plaque regions, and the distance between the edge of each plaque region and the center point is obtained according to the intersection of the plurality of ray and the edge of all the plaque regions; and the edge of each plaque region in the image of the person is obtained
  • the distance between the center points and the distance between the edge of each spot in the image template and the center point are compared with the distance between the edge of each spot in the image and the center point. For example, there is a set number of spot areas in the image template. In the presence of a character image, it is determined that the alignment is not similar, otherwise the similarity is determined.
  • the foregoing apparatus further includes:
  • the replacing unit 26 is configured to replace the image template with the character image after the opening unit turns on the smart device.
  • the image comparison unit 25 is specifically used to:
  • the distance between the origin of the character image and the coordinates of the nth intersection is the set threshold and is a constant.
  • the image comparison unit 25 is specifically configured to:
  • the contour of the character image and the midpoint of the eyes of the character image Obtaining the contour of the character image and the midpoint of the eyes of the character image, acquiring the contour of the image template and the midpoint of the eyes, and matching the midpoint of the eyes of the image module with the midpoint of the eyes of the person image, such as the contour of the character image
  • the contour of the image module also coincides with the smart device.
  • each unit included is only divided according to functional logic, but is not limited to the above division, as long as the corresponding function can be implemented; in addition, the specific name of each functional unit is also They are only used to facilitate mutual differentiation and are not intended to limit the scope of the present invention.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Security & Cryptography (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Human Computer Interaction (AREA)
  • Multimedia (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

本发明适用智能终端领域,提供了一种基于人脸识别的验证使用方法,所述方法包括如下步骤:获取操作者的照片;从照片中提取出操作者的面部图像;将人物图像与图像模板进行比对,根据比对结果确定是否打开智能设备。本发明提供的技术方案具有人物识别准确率高,安全性高的优点。

Description

基于人脸识别的验证使用方法及装置 技术领域
本发明属于智能终端领域,尤其涉及一种基于人脸识别的验证使用方法及装置。
背景技术
移动终端,俗称手机,现有的手机经过了模拟时代,数字时代和智能时代,现有的手机大部分均为智能手机,其功能也比较强大,包括:上网、视频通话、app应用等众多的功能,手机也逐渐成为人们在日常生活中的一种必备的工具。
手机由于比较小巧,在现实生活中经常会丢失,对于手机这样的私人物品来说,被别人误操作是很多用户无法接受的,所以现在的市场上需要一种安全的手机验证使用方法。
技术问题
本发明实施例的目的在于提供一种基于人脸识别的手机验证使用方法,其解决现有技术的安全性低的问题。
技术解决方案
本发明实施例是这样实现的,一方面,一种基于人脸识别的验证使用方法,所述方法包括如下步骤:
获取操作者的照片;
从照片中提取出操作者的面部图像;
将人物图像与图像模板进行比对,根据比对结果确定是否打开智能设备。
可选的,所述将人物图像与图像模板进行比对的实现方式具体为:
提取人物图像中每个像素点的灰度值,提取斑点灰度值范围内的像素点及其坐标,斑点灰度值范围内的像素点即斑点,如相邻斑点之间的距离小于设定距离,则将该相邻斑点划分为一个斑区域,遍历所有的斑点区分出所有的斑区域;将所有的斑区域显示在人物图像的对应位置,提取图像模板中的所有斑区域,以双眼中心点为原点,360°均匀放出多条射线穿过所有斑区域,依据多条射线与所有斑区域边缘的交点获取每个斑区域边缘与中心点的距离;获取人物图像中每个斑区域边缘与中心点的距离,将图像模板中每个斑区域边缘与中心点的距离逐个与人物图像中每个斑区域边缘与中心点的距离进行比对,如图像模板中有设定数量个斑区域不存在人物图像中,则确定比对不相似,否则确定相似。
可选的,所述方法在打开智能设备之后,还包括:
则用该人物图像替换图像模板。
可选的,所述将人物图像与图像模板进行比对,根据比对结果确定是否打开智能设备具体包括:
获取人物图像的轮廓线,将人物图像的双眼之间的中点作为原点,呈360°均匀发射出360个射线,记录每条射线与轮廓线的交点坐标,计算原点与每个交点坐标的距离L;获取图像模板的轮廓线,将图像模板的双眼之间的中点作为原点,呈360°均匀发射出360个射线,记录每条射线与图像模板轮廓线的交点坐标,计算原点与每个交点坐标的距离E;
∑(Ln- En)<c公式1;
当满足公式1时,确定人物图像与图像模板近似,打开智能设备;
其中, 人物图像中原点与第n个交点坐标之间的距离; 图像模板中原点与第n个交点坐标之间的距离,C为设定阈值,为常数。
可选的,所述将人物图像与图像模板进行比对,根据比对结果确定是否打开智能设备具体包括:
获取人物图像的轮廓线以及人物图像的双眼的中点,获取图像模板的轮廓线以及双眼的中点,将图像模块的双眼中点与人物图像的双眼的中点重合,如人物图像的轮廓线与图像模块的轮廓线也重合,打开智能设备。
另一方面,提供一种智能终端装置,所述装置包括:
获取单元,用于获取操作者的照片;
提取单元,用于从照片中提取出操作者的面部图像;
图像比对单元,用于将人物图像与图像模板进行比对,根据比对结果确定是否打开智能设备。
可选的,所述图像比对单元具体用于:
提取人物图像中每个像素点的灰度值,提取斑点灰度值范围内的像素点及其坐标,斑点灰度值范围内的像素点即斑点,如相邻斑点之间的距离小于设定距离,则将该相邻斑点划分为一个斑区域,遍历所有的斑点区分出所有的斑区域;将所有的斑区域显示在人物图像的对应位置,提取图像模板中的所有斑区域,以双眼中心点为原点,360°均匀放出多条射线穿过所有斑区域,依据多条射线与所有斑区域边缘的交点获取每个斑区域边缘与中心点的距离;获取人物图像中每个斑区域边缘与中心点的距离,将图像模板中每个斑区域边缘与中心点的距离逐个与人物图像中每个斑区域边缘与中心点的距离进行比对,如图像模板中有设定数量个斑区域不存在人物图像中,则确定比对不相似,否则确定相似。
可选的,所述装置还包括:
替换单元,用于在所述打开单元打开智能设备之后,用该人物图像替换图像模板。
可选的,所述图像比对单元具体用于:
获取人物图像的轮廓线,将人物图像的双眼之间的中点作为原点,呈360°均匀发射出360个射线,记录每条射线与轮廓线的交点坐标,计算原点与每个交点坐标的距离L;获取图像模板的轮廓线,将图像模板的双眼之间的中点作为原点,呈360°均匀发射出360个射线,记录每条射线与图像模板轮廓线的交点坐标,计算原点与每个交点坐标的距离E;
∑(Ln- En)<c公式1;
当满足公式1时,确定人物图像与图像模板近似,打开智能设备;
其中, 人物图像中原点与第n个交点坐标之间的距离; 图像模板中原点与第n个交点坐标之间的距离,C为设定阈值,为常数。
可选的,所述图像比对单元具体用于:
获取人物图像的轮廓线以及人物图像的双眼的中点,获取图像模板的轮廓线以及双眼的中点,将图像模块的双眼中点与人物图像的双眼的中点重合,如人物图像的轮廓线与图像模块的轮廓线也重合,打开智能设备。
有益效果
在本发明实施例中,本发明提供的技术方案的手机采用人脸识别的方式来监控验证手机,所以其在手机用户发生变化时,能够自动屏蔽非主人的操作,所以其具有安全性高的有点。
附图说明
图1是本发明提供的一种基于人脸识别的验证使用方法的流程图;
图2是本发明提供的一种智能终端装置的结构图。
本发明的实施方式
为了使本发明的目的、技术方案及优点更加清楚明白,以下结合附图及实施例,对本发明进行进一步详细说明。应当理解,此处所描述的具体实施例仅仅用以解释本发明,并不用于限定本发明。
本发明具体实施方式提供一种基于人脸识别的验证使用方法,上述方法由手机或其他的智能设备(例如ipad、PDA等)执行,该方法如图1所示,包括如下步骤:
101、获取操作者的照片;
102、从照片中提取出操作者的面部图像;
103、将人物图像与图像模板进行比对,根据比对结果确定是否打开智能设备。
上述比对结果可以为:相似或不相似。因为对于操作者来说,其面部图像不可能是不变的,所以完全相同的可能性不大,因为人脸是会有所变化的,所以这里只需要相似就可以实现,具体判断相似的方法可以参见下面描述。
可选的,上述将人物图像与图像模板进行比对的实现方式具体可以为:
提取人物图像中每个像素点的灰度值,提取斑点灰度值范围内的像素点及其坐标,斑点灰度值范围内的像素点即斑点,如相邻斑点之间的距离小于设定距离,则将该相邻斑点划分为一个斑区域,遍历所有的斑点区分出所有的斑区域;将所有的斑区域显示在人物图像的对应位置,提取图像模板中的所有斑区域,以双眼中心点为原点,360°均匀放出多条射线穿过所有斑区域,依据多条射线与所有斑区域边缘的交点获取每个斑区域边缘与中心点的距离;获取人物图像中每个斑区域边缘与中心点的距离,将图像模板中每个斑区域边缘与中心点的距离逐个与人物图像中每个斑区域边缘与中心点的距离进行比对,如图像模板中有设定数量个斑区域不存在人物图像中,则确定比对不相似,否则确定相似。
此设计主要是通过斑点区域来进行人物图像的识别,因为对于人像来说,一般都有斑点,并且斑点的灰度值基本处于一个范围内,比较容易区分出灰度值,则通过对比所有斑点的问题就可以实现人物图像的区分,因为对于每个人来说,其斑点肯定不可能一致,所有其也可以明显的进行区分,另外,这里以双眼中心点作为基准点也是为了避免人的长胖长瘦所引起的对比对结果的影响,以双眼中心点为基准点能避免其产生的影响,所以上述方法具有比对准确度高的优点。
可选的,上述方法在103之后还可以包括:
如打开智能设备,则用该人物图像替换图像模板。
所述将人物图像与图像模板进行比对,根据比对结果确定是否打开智能设备具体包括:
可选的,上述103的具体实现方法可以为:
获取人物图像的轮廓线,将人物图像的双眼之间的中点作为原点,呈360°均匀发射出360个射线,记录每条射线与轮廓线的交点坐标,计算原点与每个交点坐标的距离L;获取图像模板的轮廓线,将图像模板的双眼之间的中点作为原点,呈360°均匀发射出360个射线,记录每条射线与图像模板轮廓线的交点坐标,计算原点与每个交点坐标的距离E;
∑(Ln- En)<c公式1;
当满足公式1时,确定人物图像与图像模板近似,打开智能设备;
其中, 人物图像中原点与第n个交点坐标之间的距离; 图像模板中原点与第n个交点坐标之间的距离,C为设定阈值,为常数。
可选的,上述103的具体实现方法可以为:
获取人物图像的轮廓线以及人物图像的双眼的中点,获取图像模板的轮廓线以及双眼的中点,将图像模块的双眼中点与人物图像的双眼的中点重合,如人物图像的轮廓线与图像模块的轮廓线也重合,打开智能设备。
此种方式相当于增加了学习功能,即每次比对都可以保证其属于最新的图像。
本发明具体实施方式还提供一种智能终端装置,该装置如图2所示,包括:
获取单元21,用于获取操作者的照片;
提取单元22,用于从照片中提取出操作者的面部图像;
图像比对单元25,用于将人物图像与图像模板进行比对,根据比对结果确定是否打开智能设备。
可选的,图像比对单元25具体用于:
提取人物图像中每个像素点的灰度值,提取斑点灰度值范围内的像素点及其坐标,斑点灰度值范围内的像素点即斑点,如相邻斑点之间的距离小于设定距离,则将该相邻斑点划分为一个斑区域,遍历所有的斑点区分出所有的斑区域;将所有的斑区域显示在人物图像的对应位置,提取图像模板中的所有斑区域,以双眼中心点为原点,360°均匀放出多条射线穿过所有斑区域,依据多条射线与所有斑区域边缘的交点获取每个斑区域边缘与中心点的距离;获取人物图像中每个斑区域边缘与中心点的距离,将图像模板中每个斑区域边缘与中心点的距离逐个与人物图像中每个斑区域边缘与中心点的距离进行比对,如图像模板中有设定数量个斑区域不存在人物图像中,则确定比对不相似,否则确定相似。
可选的,上述装置还包括:
替换单元26,用于在所述打开单元打开智能设备之后,用该人物图像替换图像模板。
图像比对单元25具体用于:
获取人物图像的轮廓线,将人物图像的双眼之间的中点作为原点,呈360°均匀发射出360个射线,记录每条射线与轮廓线的交点坐标,计算原点与每个交点坐标的距离L;获取图像模板的轮廓线,将图像模板的双眼之间的中点作为原点,呈360°均匀发射出360个射线,记录每条射线与图像模板轮廓线的交点坐标,计算原点与每个交点坐标的距离E;
∑(Ln- En)<c公式1;
当满足公式1时,确定人物图像与图像模板近似,打开智能设备;
其中, 人物图像中原点与第n个交点坐标之间的距离; 图像模板中原点与第n个交点坐标之间的距离,C为设定阈值,为常数。
可选的,所述图像比对单元25具体用于:
获取人物图像的轮廓线以及人物图像的双眼的中点,获取图像模板的轮廓线以及双眼的中点,将图像模块的双眼中点与人物图像的双眼的中点重合,如人物图像的轮廓线与图像模块的轮廓线也重合,打开智能设备。
值得注意的是,上述实施例中,所包括的各个单元只是按照功能逻辑进行划分的,但并不局限于上述的划分,只要能够实现相应的功能即可;另外,各功能单元的具体名称也只是为了便于相互区分,并不用于限制本发明的保护范围。
另外,本领域普通技术人员可以理解实现上述各实施例方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成,相应的程序可以存储于一计算机可读取存储介质中,所述的存储介质,如ROM/RAM、磁盘或光盘等。
以上所述仅为本发明的较佳实施例而已,并不用以限制本发明,凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等,均应包含在本发明的保护范围之内。

Claims (10)

  1. 一种基于人脸识别的验证使用方法,其特征在于,所述方法包括如下步骤:
    获取操作者的照片;
    从照片中提取出操作者的面部图像;
    将人物图像与图像模板进行比对,根据比对结果确定是否打开智能设备。
  2. 根据权利要求1所述的方法,其特征在于,所述将人物图像与图像模板进行比对的实现方式具体为:
    提取人物图像中每个像素点的灰度值,提取斑点灰度值范围内的像素点及其坐标,斑点灰度值范围内的像素点即斑点,如相邻斑点之间的距离小于设定距离,则将该相邻斑点划分为一个斑区域,遍历所有的斑点区分出所有的斑区域;将所有的斑区域显示在人物图像的对应位置,提取图像模板中的所有斑区域,以双眼中心点为原点,360°均匀放出多条射线穿过所有斑区域,依据多条射线与所有斑区域边缘的交点获取每个斑区域边缘与中心点的距离;获取人物图像中每个斑区域边缘与中心点的距离,将图像模板中每个斑区域边缘与中心点的距离逐个与人物图像中每个斑区域边缘与中心点的距离进行比对,如图像模板中有设定数量个斑区域不存在人物图像中,则确定比对不相似,否则确定相似。
  3. 根据权利要求1所述的方法,其特征在于,所述方法在打开智能设备之后,还包括:
    则用该人物图像替换图像模板。
  4. 根据权利要求1所述的方法,其特征在于,所述将人物图像与图像模板进行比对,根据比对结果确定是否打开智能设备具体包括:
    获取人物图像的轮廓线,将人物图像的双眼之间的中点作为原点,呈360°均匀发射出360个射线,记录每条射线与轮廓线的交点坐标,计算原点与每个交点坐标的距离L;获取图像模板的轮廓线,将图像模板的双眼之间的中点作为原点,呈360°均匀发射出360个射线,记录每条射线与图像模板轮廓线的交点坐标,计算原点与每个交点坐标的距离E;
    ∑(Ln- En)<c公式1;
    当满足公式1时,确定人物图像与图像模板近似,打开智能设备;
    其中, 人物图像中原点与第n个交点坐标之间的距离; 图像模板中原点与第n个交点坐标之间的距离,C为设定阈值,为常数。
  5. 根据权利要求1所述的方法,其特征在于,所述将人物图像与图像模板进行比对,根据比对结果确定是否打开智能设备具体包括:
    获取人物图像的轮廓线以及人物图像的双眼的中点,获取图像模板的轮廓线以及双眼的中点,将图像模块的双眼中点与人物图像的双眼的中点重合,如人物图像的轮廓线与图像模块的轮廓线也重合,打开智能设备。
  6. 一种智能终端装置,其特征在于,所述装置包括:
    获取单元,用于获取操作者的照片;
    提取单元,用于从照片中提取出操作者的面部图像;
    图像比对单元,用于将人物图像与图像模板进行比对,根据比对结果确定是否打开智能设备。
  7. 根据权利要求6所述的装置,其特征在于,所述图像比对单元具体用于:
    提取人物图像中每个像素点的灰度值,提取斑点灰度值范围内的像素点及其坐标,斑点灰度值范围内的像素点即斑点,如相邻斑点之间的距离小于设定距离,则将该相邻斑点划分为一个斑区域,遍历所有的斑点区分出所有的斑区域;将所有的斑区域显示在人物图像的对应位置,提取图像模板中的所有斑区域,以双眼中心点为原点,360°均匀放出多条射线穿过所有斑区域,依据多条射线与所有斑区域边缘的交点获取每个斑区域边缘与中心点的距离;获取人物图像中每个斑区域边缘与中心点的距离,将图像模板中每个斑区域边缘与中心点的距离逐个与人物图像中每个斑区域边缘与中心点的距离进行比对,如图像模板中有设定数量个斑区域不存在人物图像中,则确定比对不相似,否则确定相似。
  8. 根据权利要求6所述的装置,其特征在于,所述装置还包括:
    替换单元,用于在所述打开单元打开智能设备之后,用该人物图像替换图像模板。
  9. 根据权利要求6所述的装置,其特征在于,所述图像比对单元具体用于:
    获取人物图像的轮廓线,将人物图像的双眼之间的中点作为原点,呈360°均匀发射出360个射线,记录每条射线与轮廓线的交点坐标,计算原点与每个交点坐标的距离L;获取图像模板的轮廓线,将图像模板的双眼之间的中点作为原点,呈360°均匀发射出360个射线,记录每条射线与图像模板轮廓线的交点坐标,计算原点与每个交点坐标的距离E;
    ∑(Ln- En)<c公式1;
    当满足公式1时,确定人物图像与图像模板近似,打开智能设备;
    其中, 人物图像中原点与第n个交点坐标之间的距离; 图像模板中原点与第n个交点坐标之间的距离,C为设定阈值,为常数。
  10. 根据权利要求6所述的装置,其特征在于,所述图像比对单元具体用于:
    获取人物图像的轮廓线以及人物图像的双眼的中点,获取图像模板的轮廓线以及双眼的中点,将图像模块的双眼中点与人物图像的双眼的中点重合,如人物图像的轮廓线与图像模块的轮廓线也重合,打开智能设备。
PCT/CN2014/091213 2014-11-15 2014-11-15 基于人脸识别的验证使用方法及装置 WO2016074248A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2014/091213 WO2016074248A1 (zh) 2014-11-15 2014-11-15 基于人脸识别的验证使用方法及装置
CN201480001802.2A CN104584030B (zh) 2014-11-15 2014-11-15 基于人脸识别的验证使用方法及装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2014/091213 WO2016074248A1 (zh) 2014-11-15 2014-11-15 基于人脸识别的验证使用方法及装置

Publications (1)

Publication Number Publication Date
WO2016074248A1 true WO2016074248A1 (zh) 2016-05-19

Family

ID=53097341

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/091213 WO2016074248A1 (zh) 2014-11-15 2014-11-15 基于人脸识别的验证使用方法及装置

Country Status (2)

Country Link
CN (1) CN104584030B (zh)
WO (1) WO2016074248A1 (zh)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105938552B (zh) * 2016-06-29 2020-04-24 北京旷视科技有限公司 底图自动更新的人脸识别方法及装置
CN107742071A (zh) * 2017-09-11 2018-02-27 广东欧珀移动通信有限公司 网络游戏的装备解锁方法和电子装置
CN111932283B (zh) * 2020-09-22 2024-07-02 北京大鱼梦想科技有限公司 一种防伪检测方法及装置

Citations (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5933527A (en) * 1995-06-22 1999-08-03 Seiko Epson Corporation Facial image processing method and apparatus
CN1585957A (zh) * 2001-09-13 2005-02-23 霍尼韦尔国际公司 用于面部检测的近红外方法和系统
TW200809700A (en) * 2006-08-15 2008-02-16 Compal Electronics Inc Method for recognizing face area
US20080069410A1 (en) * 2006-09-18 2008-03-20 Jong Gook Ko Iris recognition method and apparatus thereof
CN101226591A (zh) * 2008-01-31 2008-07-23 上海交通大学 基于手机摄像头结合人脸识别技术的身份识别方法
CN101349961A (zh) * 2008-08-11 2009-01-21 深圳华为通信技术有限公司 一种自动切换便携式终端显示模式的方法及装置
CN101393598A (zh) * 2007-09-21 2009-03-25 希姆通信息技术(上海)有限公司 利用手机摄像头对人脸识别来决定允许开机/解锁的方法
CN102035929A (zh) * 2009-09-29 2011-04-27 比亚迪股份有限公司 识别终端用户身份的方法、系统及终端
CN102479320A (zh) * 2010-11-25 2012-05-30 康佳集团股份有限公司 一种人脸识别方法、装置及移动终端
CN102509053A (zh) * 2011-11-23 2012-06-20 唐辉 用于验证授权的方法、处理器、设备和移动终端
CN102546938A (zh) * 2011-12-27 2012-07-04 广东步步高电子工业有限公司 利用前置摄像头智能捕捉人脸图像实现安全防护的手机
CN102629955A (zh) * 2012-03-30 2012-08-08 上海华勤通讯技术有限公司 人脸识别手机及其实现方法
CN102970411A (zh) * 2012-10-24 2013-03-13 康佳集团股份有限公司 基于人脸检测的智能手机锁屏解锁控制方法及智能手机
CN102968636A (zh) * 2012-12-11 2013-03-13 山东神思电子技术股份有限公司 一种人脸轮廓的提取方法
CN103179265A (zh) * 2012-09-20 2013-06-26 深圳市金立通信设备有限公司 基于人脸识别的来电静音系统及方法
CN103188412A (zh) * 2011-12-29 2013-07-03 大连文森特软件科技有限公司 一种基于手机识别的远程家电控制方法
CN103581378A (zh) * 2013-10-31 2014-02-12 中晟国计科技有限公司 一种高安全性能的智能手机

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN201667042U (zh) * 2009-07-22 2010-12-08 东莞慧盈塑胶有限公司 一种带有脸部识别功能的笔记本电脑
CN103324879B (zh) * 2013-07-05 2016-08-10 公安部第三研究所 移动设备基于人脸识别和智能卡的身份验证系统及方法
CN103824051B (zh) * 2014-02-17 2017-05-03 北京旷视科技有限公司 一种基于局部区域匹配的人脸搜索方法

Patent Citations (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5933527A (en) * 1995-06-22 1999-08-03 Seiko Epson Corporation Facial image processing method and apparatus
CN1585957A (zh) * 2001-09-13 2005-02-23 霍尼韦尔国际公司 用于面部检测的近红外方法和系统
TW200809700A (en) * 2006-08-15 2008-02-16 Compal Electronics Inc Method for recognizing face area
US20080069410A1 (en) * 2006-09-18 2008-03-20 Jong Gook Ko Iris recognition method and apparatus thereof
CN101393598A (zh) * 2007-09-21 2009-03-25 希姆通信息技术(上海)有限公司 利用手机摄像头对人脸识别来决定允许开机/解锁的方法
CN101226591A (zh) * 2008-01-31 2008-07-23 上海交通大学 基于手机摄像头结合人脸识别技术的身份识别方法
CN101349961A (zh) * 2008-08-11 2009-01-21 深圳华为通信技术有限公司 一种自动切换便携式终端显示模式的方法及装置
CN102035929A (zh) * 2009-09-29 2011-04-27 比亚迪股份有限公司 识别终端用户身份的方法、系统及终端
CN102479320A (zh) * 2010-11-25 2012-05-30 康佳集团股份有限公司 一种人脸识别方法、装置及移动终端
CN102509053A (zh) * 2011-11-23 2012-06-20 唐辉 用于验证授权的方法、处理器、设备和移动终端
CN102546938A (zh) * 2011-12-27 2012-07-04 广东步步高电子工业有限公司 利用前置摄像头智能捕捉人脸图像实现安全防护的手机
CN103188412A (zh) * 2011-12-29 2013-07-03 大连文森特软件科技有限公司 一种基于手机识别的远程家电控制方法
CN102629955A (zh) * 2012-03-30 2012-08-08 上海华勤通讯技术有限公司 人脸识别手机及其实现方法
CN103179265A (zh) * 2012-09-20 2013-06-26 深圳市金立通信设备有限公司 基于人脸识别的来电静音系统及方法
CN102970411A (zh) * 2012-10-24 2013-03-13 康佳集团股份有限公司 基于人脸检测的智能手机锁屏解锁控制方法及智能手机
CN102968636A (zh) * 2012-12-11 2013-03-13 山东神思电子技术股份有限公司 一种人脸轮廓的提取方法
CN103581378A (zh) * 2013-10-31 2014-02-12 中晟国计科技有限公司 一种高安全性能的智能手机

Also Published As

Publication number Publication date
CN104584030B (zh) 2017-02-22
CN104584030A (zh) 2015-04-29

Similar Documents

Publication Publication Date Title
WO2011081379A2 (en) Display device and control method thereof
WO2017113974A1 (zh) 一种语音处理的方法、装置以及终端
WO2014019317A1 (zh) 基于云的智能人脸识别检索方法
WO2014157806A1 (en) Display device and control method thereof
WO2014026443A1 (zh) 身份认证管理装置及其方法
WO2014194620A1 (zh) 图像特征提取、训练、检测方法及模块、装置、系统
WO2017067291A1 (zh) 一种指纹识别的方法、装置及终端
TW201421376A (zh) 臉部表情控制系統、表情控制之方法及其電腦系統
WO2016074248A1 (zh) 基于人脸识别的验证使用方法及装置
WO2020108111A1 (zh) 医保欺诈行为的识别方法、装置、设备及可读存储介质
WO2017128853A1 (zh) 摄制视频的处理方法、装置和设备
WO2014190870A1 (zh) 一种识别用户活动类型的方法及系统
WO2016123898A1 (zh) 一种短信管理方法及其移动终端
WO2017067290A1 (zh) 指纹录入方法、装置及终端设备
WO2017005023A1 (zh) 智能手表手势输入方法及智能手表
WO2015119326A1 (en) Display device and method for controlling the same
WO2018058955A1 (zh) 一种穿戴式终端的防丢失方法、系统及穿戴式终端
WO2012034469A1 (zh) 基于手势的人机交互方法及系统、计算机存储介质
WO2015196878A1 (zh) 一种电视虚拟触控方法及系统
WO2015109507A1 (zh) 一种输入字符的方法和电子设备
WO2018223354A1 (zh) 基于定位的考勤记录方法及系统
WO2018053763A1 (zh) 一种图像识别方法和装置
WO2014026425A1 (zh) 一种触摸屏终端的解锁方法、装置及终端
WO2016112515A1 (zh) 智能移动终端的扫描方法及系统
WO2019054534A1 (en) METHOD AND APPARATUS FOR SCREEN CAPTURE FOR AN ELECTRONIC TERMINAL

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: 14905860

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205 DATED 05/10/2017)

122 Ep: pct application non-entry in european phase

Ref document number: 14905860

Country of ref document: EP

Kind code of ref document: A1