WO2016074249A1 - 视频验证防止手机误操作的方法及装置 - Google Patents

视频验证防止手机误操作的方法及装置 Download PDF

Info

Publication number
WO2016074249A1
WO2016074249A1 PCT/CN2014/091214 CN2014091214W WO2016074249A1 WO 2016074249 A1 WO2016074249 A1 WO 2016074249A1 CN 2014091214 W CN2014091214 W CN 2014091214W WO 2016074249 A1 WO2016074249 A1 WO 2016074249A1
Authority
WO
WIPO (PCT)
Prior art keywords
face
image
distances
midpoint
eye
Prior art date
Application number
PCT/CN2014/091214
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 CN201480001806.0A priority Critical patent/CN104541230B/zh
Priority to PCT/CN2014/091214 priority patent/WO2016074249A1/zh
Publication of WO2016074249A1 publication Critical patent/WO2016074249A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31—User authentication
    • G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
    • 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
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
    • 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
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/172—Classification, e.g. identification

Definitions

  • the invention belongs to the field of intelligent terminals, and in particular relates to a method and a device for preventing video from being mishandled by video verification.
  • 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.
  • the mobile phone Because the mobile phone is relatively small, it will generally be placed in the pocket. Although the mobile phone will lock the screen, it will still be mishandled.
  • 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 misoperation in the prior art.
  • a method for video verification to prevent a mobile phone from malfunctioning includes the following steps:
  • the distinguishing whether the feature image by the feature of the facial image is:
  • Scale distance between midpoints of the eye / vertical distance from the midpoint of the midpoint of the eye to the contour of the face.
  • the distinguishing whether the feature image by the feature of the facial image is:
  • Extracting the facial contour line and the midpoint of the eye image taking the midpoint of the eye as the origin, uniformly emitting 360 rays at 360°, acquiring 360 intersection coordinates between 360 rays and the facial contour, and calculating the origin and 360 distances between the coordinates of 360 intersection points, and the sum of 360 distances is calculated. If the sum is within the threshold range of the person's face, it is confirmed as a face image.
  • X n is less than the set threshold, it is determined as a face, otherwise it is a non-human face; wherein L n is the distance between the origin and the coordinates of the nth intersection, The mean of 360 distances.
  • ⁇ is the empirical coefficient
  • mov is the offset
  • n is the number of the intersection
  • L n is the distance between the origin and the coordinates of the nth intersection, The mean of 360 distances
  • the cumulative number is increased by 1, and when the cumulative number exceeds 100, it is determined to be a face, otherwise it is a non-human face.
  • an intelligent terminal device comprising:
  • An extracting unit configured to extract an image of the operator's face from the photo
  • a distinguishing unit configured to distinguish whether the image is a person through the feature of the facial image
  • the unit is opened for opening the smart device when the resolution unit distinguishes the image of the person.
  • the resolving unit specifically includes:
  • a midpoint module for extracting a facial contour and a midpoint of the face of the facial image
  • a judging module for determining whether it is a character graphic according to a ratio
  • Scale distance between midpoints of the eye / vertical distance from the midpoint of the midpoint of the eye to the contour of the face.
  • the resolving unit is specifically configured to extract a facial contour line and a midpoint of the eye image, and use the midpoint of the eye as an origin to uniformly emit 360 rays at 360°, and obtain 360 rays and facial contours.
  • the coordinates of 360 intersection points are calculated, 360 distances between the origin and the coordinates of 360 intersection points are calculated, and the sum of 360 distances is calculated. If the sum is within the threshold range of the person's face, it is confirmed as a face image.
  • the distinguishing unit is further configured to determine, according to the 360 distances, whether the face is a face, specifically:
  • X n is less than the set threshold, it is determined as a face, otherwise it is a non-human face; wherein L n is the distance between the origin and the coordinates of the nth intersection, The mean of 360 distances.
  • the distinguishing unit is further configured to determine, according to the 360 distances, whether the face is a face, specifically:
  • ⁇ is the empirical coefficient
  • mov is the offset
  • n is the number of the intersection
  • L n is the distance between the origin and the coordinates of the nth intersection, The mean of 360 distances
  • the cumulative number is increased by 1, and when the cumulative number exceeds 100, it is determined to be a face, otherwise it is a non-human face.
  • 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 video verification preventing a malfunction of a mobile phone according to 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 preventing video from being mishandled by a mobile phone.
  • the foregoing method 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 method provided by the present invention acquires whether it is a character image by a method of comparing images, that is, if a non-person image, such as a dog, a cat, or the like, does not open the device.
  • the implementation method of the foregoing 103 may specifically be:
  • the facial contour line and the midpoint of the eye are extracted, and it is determined according to the scale whether it is a character graphic.
  • the ratio can be specifically:
  • Scale distance between midpoints of the eye / vertical distance from the midpoint of the midpoint of the eye to the contour of the face.
  • the implementation method of the foregoing 103 may specifically be:
  • Extracting the facial contour line and the midpoint of the eye image taking the midpoint of the eye as the origin, uniformly emitting 360 rays at 360°, acquiring 360 intersection coordinates between 360 rays and the facial contour, and calculating the origin and 360 distances between the coordinates of 360 intersection points, and the sum of 360 distances is calculated. If the sum is within the threshold range of the person's face, it is confirmed as a face image.
  • the existing human face is larger than the animal, so the distance of the sampled distance is generally large, so it can avoid misuse, which can not only distinguish between humans and animals, but also avoid misuse of children. Because of the age of the child, the child's face can not meet the above requirements.
  • the implementation method of the foregoing 103 may specifically be:
  • X n is less than the set threshold, it is determined as a face, otherwise it is a non-human face; wherein L n is the distance between the origin and the coordinates of the nth intersection, The mean of 360 distances.
  • the implementation method of the foregoing 103 may specifically be:
  • ⁇ is an empirical coefficient, specifically 0.15.
  • 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
  • a distinguishing unit 23 configured to distinguish, by the feature of the facial image, whether it is a character image
  • the opening unit 24 is configured to open the smart device when the resolution unit distinguishes the image of the person.
  • the resolving unit 23 specifically includes:
  • a midpoint module 231, configured to extract a facial contour line and a midpoint of the eye of the facial image
  • the determining module 232 is configured to determine, according to the ratio, whether it is a character graphic
  • Scale distance between midpoints of the eye / vertical distance from the midpoint of the midpoint of the eye to the contour of the face.
  • the resolving unit 23 is specifically configured to extract a facial contour line and a midpoint of the eye image, and use the midpoint of the eye as an origin to uniformly emit 360 rays at 360°, and obtain 360 rays and facial contour lines.
  • the coordinates of 360 intersection points are calculated, 360 distances between the origin and the coordinates of 360 intersection points are calculated, and the sum of 360 distances is calculated. If the sum is within the threshold range of the person's face, it is confirmed as a face image.
  • the existing human face is larger than the animal, so the distance of the sampled distance is generally large, so it can avoid misuse, which can not only distinguish between humans and animals, but also avoid misuse of children. Because of the age of the child, the child's face can not meet the above requirements.
  • the resolving unit 23 is further configured to determine, according to the 360 distances, whether it is a human face, specifically:
  • X n is less than the set threshold, it is determined as a face, otherwise it is a non-human face; wherein L n is the distance between the origin and the coordinates of the nth intersection, The mean of 360 distances.
  • the resolving unit 23 is further configured to determine, according to the 360 distances, whether it is a human face, specifically:
  • ⁇ is an empirical coefficient, specifically 0.15.

Landscapes

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

Abstract

本发明适用智能终端领域，提供了一种视频验证防止手机误操作的方法，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；通过该面部图像的特征分辨是否为人物图像；如是人物图像，则打开智能设备。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

视频验证防止手机误操作的方法及装置 技术领域
本发明属于智能终端领域，尤其涉及一种视频验证防止手机误操作的方法及装置。
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，一般均会放在口袋里，虽说手机会锁屏，但是还是会出现误操作。
发明内容
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，其解决现有技术的误操作的问题。
本发明实施例是这样实现的，一方面，一种视频验证防止手机误操作的方法，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；
通过该面部图像的特征分辨是否为人物图像；
如是人物图像，则打开智能设备。
可选的，所述通过该面部图像的特征分辨是否为人物图像具体为：
提取面部图像的面部轮廓线和眼部中点，根据比例来确定是否为人物图形，
比例＝眼部中点之间的距离/眼部中点连线中点到面部轮廓的垂直距离。
可选的，所述通过该面部图像的特征分辨是否为人物图像具体为：
提取面部图像的面部轮廓线和眼部中点，以眼部中点为原点，呈360°均匀发射出360条射线，获取360条射线与面部轮廓线之间的360个交点坐标，计算原点与360个交点坐标之间的360个距离，计算360个距离的总和，如总和在人物脸部阈值范围内，则确认为人脸图像。
可选的，根据360个距离判断是否为人脸，具体为：
Figure PCTCN2014091214-appb-000001
Figure PCTCN2014091214-appb-000002
当Xn小于设定阈值时，确定为人脸，否则为非人脸；其中,Ln为原点与第n个交点坐标之间的距离，
Figure PCTCN2014091214-appb-000003
为360个距离的均值。
可选的，根据360个距离判断是否为人脸，具体为：
Figure PCTCN2014091214-appb-000004
其中，γ为经验系数，mov为偏移量，n为交点的编号；Ln为原点与第n个交点坐标之间的距离，
Figure PCTCN2014091214-appb-000005
为360个距离的均值；
当计算出的偏移量大于偏移阈值时，累积数量加1，当累积数量超过100个时，确定为人脸，否则为非人脸。
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；
分辨单元，用于通过该面部图像的特征分辨是否为人物图像；
打开单元，用于在分辨单元分辨出是人物图像时，则打开智能设备。
可选的，所述分辨单元具体包括：
中点模块，用于提取面部图像的面部轮廓线和眼部中点；
判断模块，用于根据比例来确定是否为人物图形，
比例＝眼部中点之间的距离/眼部中点连线中点到面部轮廓的垂直距离。
可选的，所述分辨单元具体用于提取面部图像的面部轮廓线和眼部中点，以眼部中点为原点，呈360°均匀发射出360条射线，获取360条射线与面部轮廓线之间的360个交点坐标，计算原点与360个交点坐标之间的360个距离，计算360个距离的总和，如总和在人物脸部阈值范围内，则确认为人脸图像。
可选的，所述分辨单元还用于根据360个距离判断是否为人脸，具体为：
Figure PCTCN2014091214-appb-000006
Figure PCTCN2014091214-appb-000007
当Xn小于设定阈值时，确定为人脸，否则为非人脸；其中,Ln为原点与第n个交点坐标之间的距离，
Figure PCTCN2014091214-appb-000008
为360个距离的均值。
可选的，所述分辨单元还用于根据360个距离判断是否为人脸，具体为：
Figure PCTCN2014091214-appb-000009
其中，γ为经验系数，mov为偏移量，n为交点的编号；Ln为原点与第n个交点坐标之间的距离，
Figure PCTCN2014091214-appb-000010
为360个距离的均值；
当计算出的偏移量大于偏移阈值时，累积数量加1，当累积数量超过100个时，确定为人脸，否则为非人脸。
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视频验证防止手机误操作的方法的流程图；
图2是本发明提供的一种智能终端装置的结构图。
具体实施方式
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视频验证防止手机误操作的方法，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、通过该面部图像的特征分辨是否为人物图像；
104、如是人物图像，则打开智能设备。
本发明提供的方法通过比对图像的方法来获取是否为人物图像，即如果非人物图像，例如狗、猫等图像即不打开设备。
上述103的实现方法具体可以为：
提取面部图像的面部轮廓线和眼部中点，根据比例来确定是否为人物图形。该比例具体可以为：
比例＝眼部中点之间的距离/眼部中点连线中点到面部轮廓的垂直距离。
通过数据研究发现，不同类型的动物，其上述比例的比值是不同的，其在 一定的范围内，通过此比例的比值就可以非常容易的分辨出是属于人物图像还是动物的图像。
上述103的实现方法具体可以为：
提取面部图像的面部轮廓线和眼部中点，以眼部中点为原点，呈360°均匀发射出360条射线，获取360条射线与面部轮廓线之间的360个交点坐标，计算原点与360个交点坐标之间的360个距离，计算360个距离的总和，如总和在人物脸部阈值范围内，则确认为人脸图像。
通过研究发现，现有的人脸均比动物的大，这样其采样得到的距离的值一般都比较大，所以能够避免误操作，此种不仅能区分出人和动物，还可以避免小孩误操作，因为未成年时，小孩的脸也是无法达到上述要求的。
上述103的实现方法具体可以为：
Figure PCTCN2014091214-appb-000011
Figure PCTCN2014091214-appb-000012
当Xn小于设定阈值时，确定为人脸，否则为非人脸；其中,Ln为原点与第n个交点坐标之间的距离，
Figure PCTCN2014091214-appb-000013
为360个距离的均值。
上述103的实现方法具体可以为：
Figure PCTCN2014091214-appb-000014
其中，γ为经验系数，具体可以为0.15。当计算出的偏移量(mov)大于偏移阈值时，累积数量加1，当累积数量超过100个时，确定为人脸，否则为非人脸。
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；
分辨单元23，用于通过该面部图像的特征分辨是否为人物图像；
打开单元24，用于在分辨单元分辨出是人物图像时，则打开智能设备。
可选的，分辨单元23具体包括：
中点模块231，用于提取面部图像的面部轮廓线和眼部中点；
判断模块232，用于根据比例来确定是否为人物图形，
比例＝眼部中点之间的距离/眼部中点连线中点到面部轮廓的垂直距离。
可选的，分辨单元23具体用于提取面部图像的面部轮廓线和眼部中点，以眼部中点为原点，呈360°均匀发射出360条射线，获取360条射线与面部轮廓线之间的360个交点坐标，计算原点与360个交点坐标之间的360个距离，计算360个距离的总和，如总和在人物脸部阈值范围内，则确认为人脸图像。
通过研究发现，现有的人脸均比动物的大，这样其采样得到的距离的值一般都比较大，所以能够避免误操作，此种不仅能区分出人和动物，还可以避免小孩误操作，因为未成年时，小孩的脸也是无法达到上述要求的。
可选的，分辨单元23还用于根据360个距离判断是否为人脸，具体为：
Figure PCTCN2014091214-appb-000015
Figure PCTCN2014091214-appb-000016
当Xn小于设定阈值时，确定为人脸，否则为非人脸；其中,Ln为原点与第n个交点坐标之间的距离，
Figure PCTCN2014091214-appb-000017
为360个距离的均值。
可选的，分辨单元23还用于根据360个距离判断是否为人脸，具体为：
Figure PCTCN2014091214-appb-000018
其中，γ为经验系数，具体可以为0.15。当计算出的偏移量(mov)大于偏移阈值时，累积数量加1，当累积数量超过100个时，确定为人脸，否则为非人脸。
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. 一种视频验证防止手机误操作的方法，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；
    通过该面部图像的特征分辨是否为人物图像；
    如是人物图像，则打开智能设备。
  2. 根据权利要求1所述的方法，其特征在于，所述通过该面部图像的特征分辨是否为人物图像具体为：
    提取面部图像的面部轮廓线和眼部中点，根据比例来确定是否为人物图形，
    比例＝眼部中点之间的距离/眼部中点连线中点到面部轮廓的垂直距离。
  3. 根据权利要求1所述的方法，其特征在于，所述通过该面部图像的特征分辨是否为人物图像具体为：
    提取面部图像的面部轮廓线和眼部中点，以眼部中点为原点，呈360°均匀发射出360条射线，获取360条射线与面部轮廓线之间的360个交点坐标，计算原点与360个交点坐标之间的360个距离，计算360个距离的总和，如总和在人物脸部阈值范围内，则确认为人脸图像。
  4. 根据权利要求3所述的方法，其特征在于，根据360个距离判断是否为人脸，具体为：
    Figure PCTCN2014091214-appb-100001
    Xn＝|Dn-Dn-1|；
    当Xn小于设定阈值时，确定为人脸，否则为非人脸；其中,Ln为原点与第n个交点坐标之间的距离，
    Figure PCTCN2014091214-appb-100002
    为360个距离的均值。
  5. 根据权利要求3所述的方法，其特征在于，根据360个距离判断是否为 人脸，具体为：
    Figure PCTCN2014091214-appb-100003
    其中，γ为经验系数，mov为偏移量，n为交点的编号；Ln为原点与第n个交点坐标之间的距离，
    Figure PCTCN2014091214-appb-100004
    为360个距离的均值；
    当计算出的偏移量大于偏移阈值时，累积数量加1，当累积数量超过100个时，确定为人脸，否则为非人脸。
  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；
    分辨单元，用于通过该面部图像的特征分辨是否为人物图像；
    打开单元，用于在分辨单元分辨出是人物图像时，则打开智能设备。
  7. 根据权利要求6所述的装置，其特征在于，所述分辨单元具体包括：
    中点模块，用于提取面部图像的面部轮廓线和眼部中点；
    判断模块，用于根据比例来确定是否为人物图形，
    比例＝眼部中点之间的距离/眼部中点连线中点到面部轮廓的垂直距离。
  8. 根据权利要求6所述的装置，其特征在于，所述分辨单元具体用于提取面部图像的面部轮廓线和眼部中点，以眼部中点为原点，呈360°均匀发射出360条射线，获取360条射线与面部轮廓线之间的360个交点坐标，计算原点与360个交点坐标之间的360个距离，计算360个距离的总和，如总和在人物脸部阈值范围内，则确认为人脸图像。
  9. 根据权利要求8所述的装置，其特征在于，所述分辨单元还用于根据360个距离判断是否为人脸，具体为：
    Figure PCTCN2014091214-appb-100005
    Xn＝|Dn-Dn-1|；
    当Xn小于设定阈值时，确定为人脸，否则为非人脸；其中,Ln为原点与第n个交点坐标之间的距离，
    Figure PCTCN2014091214-appb-100006
    为360个距离的均值。
  10. 根据权利要求8所述的装置，其特征在于，所述分辨单元还用于根据360个距离判断是否为人脸，具体为：
    Figure PCTCN2014091214-appb-100007
    其中，γ为经验系数，mov为偏移量，n为交点的编号；Ln为原点与第n个交点坐标之间的距离，
    Figure PCTCN2014091214-appb-100008
    为360个距离的均值；
    当计算出的偏移量大于偏移阈值时，累积数量加1，当累积数量超过100个时，确定为人脸，否则为非人脸。
PCT/CN2014/091214 2014-11-15 2014-11-15 视频验证防止手机误操作的方法及装置 WO2016074249A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN201480001806.0A CN104541230B (zh) 2014-11-15 2014-11-15 视频验证防止手机误操作的方法及装置
PCT/CN2014/091214 WO2016074249A1 (zh) 2014-11-15 2014-11-15 视频验证防止手机误操作的方法及装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2014/091214 WO2016074249A1 (zh) 2014-11-15 2014-11-15 视频验证防止手机误操作的方法及装置

Publications (1)

Publication Number Publication Date
WO2016074249A1 true WO2016074249A1 (zh) 2016-05-19

Family

ID=52855800

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2014/091214 WO2016074249A1 (zh) 2014-11-15 2014-11-15 视频验证防止手机误操作的方法及装置

Country Status (2)

Country Link
CN (1) CN104541230B (zh)
WO (1) WO2016074249A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102542299A (zh) * 2011-12-07 2012-07-04 惠州Tcl移动通信有限公司 人脸识别方法、装置及能识别人脸的移动终端
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
CN103716456A (zh) * 2013-12-10 2014-04-09 柳州译海网络科技有限公司 一种基于人脸特征信息的手机解锁方法
KR20140071802A (ko) * 2012-12-04 2014-06-12 주식회사 엘지유플러스 얼굴 인식을 통한 휴대 단말기 숏컷 정보 실행 시스템 및 방법

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102542299A (zh) * 2011-12-07 2012-07-04 惠州Tcl移动通信有限公司 人脸识别方法、装置及能识别人脸的移动终端
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
KR20140071802A (ko) * 2012-12-04 2014-06-12 주식회사 엘지유플러스 얼굴 인식을 통한 휴대 단말기 숏컷 정보 실행 시스템 및 방법
CN103716456A (zh) * 2013-12-10 2014-04-09 柳州译海网络科技有限公司 一种基于人脸特征信息的手机解锁方法

Also Published As

Publication number Publication date
CN104541230A (zh) 2015-04-22
CN104541230B (zh) 2017-07-04

Similar Documents

Publication Publication Date Title
US10534957B2 (en) Eyeball movement analysis method and device, and storage medium
US10599877B2 (en) Protecting content on a display device from a field-of-view of a person or device
WO2022166243A1 (zh) 捏合手势检测识别方法、装置及***
WO2019095571A1 (zh) 人物情绪分析方法、装置及存储介质
TWI712980B (zh) 理賠資訊提取方法和裝置、電子設備
WO2017045258A1 (zh) 拍照提示方法、装置、设备及非易失性计算机存储介质
CN107077589B (zh) 基于图像的生物计量中的面部假冒检测
WO2017020514A1 (zh) 图片场景判定方法、装置以及服务器
US9582709B2 (en) Privacy for camera with people recognition
WO2019071664A1 (zh) 结合深度信息的人脸识别方法、装置及存储介质
CN110276366A (zh) 使用弱监督模型来检测对象
WO2019033525A1 (zh) Au特征识别方法、装置及存储介质
CN109448007B (zh) 图像处理方法、图像处理装置及存储介质
US10650234B2 (en) Eyeball movement capturing method and device, and storage medium
US10489636B2 (en) Lip movement capturing method and device, and storage medium
EP2784723A3 (en) Method, system and computer program for comparing images
WO2019056503A1 (zh) 门店监控评价方法、装置及存储介质
CN106372603A (zh) 遮挡人脸识别方法及装置
CN109508576B (zh) 一种异常驾驶行为检测方法、装置及电子设备
Ghanem et al. A survey on sign language recognition using smartphones
KR20160025768A (ko) 안면인식을 활용하는 출석관리 시스템
WO2021082045A1 (zh) 微笑表情检测方法、装置、计算机设备及存储介质
WO2021051602A1 (zh) 基于唇语密码的人脸识别方法、***、装置及存储介质
WO2016184092A1 (zh) 终端操作方法及装置
CN103870812A (zh) 一种获取掌纹图像的方法及***

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: 14905980

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 1205A DATED 27/09/2017)

122 Ep: pct application non-entry in european phase

Ref document number: 14905980

Country of ref document: EP

Kind code of ref document: A1