CN104541230B - Video verification prevents the method and device of mobile phone misoperation - Google Patents

Video verification prevents the method and device of mobile phone misoperation Download PDF

Info

Publication number
CN104541230B
CN104541230B CN201480001806.0A CN201480001806A CN104541230B CN 104541230 B CN104541230 B CN 104541230B CN 201480001806 A CN201480001806 A CN 201480001806A CN 104541230 B CN104541230 B CN 104541230B
Authority
CN
China
Prior art keywords
image
distance
midpoint
character
origin
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.)
Active
Application number
CN201480001806.0A
Other languages
Chinese (zh)
Other versions
CN104541230A (en
Inventor
张黎君
熊胜峰
叶培锋
郑旭升
田辉
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.)
Shenzhen Miki Intelligent Technology Co Ltd
Original Assignee
Shenzhen Miki Intelligent Technology Co 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 Shenzhen Miki Intelligent Technology Co Ltd filed Critical Shenzhen Miki Intelligent Technology Co Ltd
Priority to PCT/CN2014/091214 priority Critical patent/WO2016074249A1/en
Publication of CN104541230A publication Critical patent/CN104541230A/en
Application granted granted Critical
Publication of CN104541230B publication Critical patent/CN104541230B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints

Abstract

The applicable intelligent terminal field of the present invention, there is provided a kind of method that video verification prevents mobile phone misoperation, methods described comprises the following steps:Obtain the photo of operator;The face-image of operator is extracted from photo;Whether the feature resolution by the face-image is character image;Character image, then open smart machine in this way.The technical scheme that the present invention is provided has person recognition accuracy rate advantage high, safe.

Description

Video verification prevents the method and device of mobile phone misoperation
Technical field
The method and dress of mobile phone misoperation are prevented the invention belongs to intelligent terminal field, more particularly to a kind of video verification Put.
Background technology
Mobile terminal, is commonly called as mobile phone, and existing mobile phone have passed through the simulation epoch, digital Age and intelligent epoch, existing Mobile phone major part is smart mobile phone, and its function is also more powerful, including:Numerous work(such as online, video calling, app applications Can, mobile phone is increasingly becoming a kind of people's indispensable instrument in daily life.
Mobile phone can be generally placed in pocket due to relatively more compact, though mobile phone meeting screen locking, still occurs behaviour by mistake Make.
The content of the invention
The purpose of the embodiment of the present invention is to provide a kind of mobile phone checking application method based on recognition of face, and it solves existing There is the problem of the maloperation of technology.
The embodiment of the present invention is achieved in that on the one hand, a kind of method that video verification prevents mobile phone misoperation is described Method comprises the following steps:
Obtain the photo of operator;
The face-image of operator is extracted from photo;
Whether the feature resolution by the face-image is character image;
Character image, then open smart machine in this way.
Optionally, whether the feature resolution by the face-image is that character image is specially:
Face contour line and the eye midpoint of face-image are extracted, determine whether to be character graphics according to ratio,
The vertical range at the distance between ratio=eye midpoint/eye midpoint line midpoint to face contour.
Optionally, whether the feature resolution by the face-image is that character image is specially:
Face contour line and the eye midpoint of face-image are extracted, with eye midpoint as origin, is gone out in 360 ° of uniform emissions 360 rays, obtain 360 intersecting point coordinates between 360 rays and face contour line, and datum point and 360 intersection points are sat 360 distances between mark, calculate 360 summations of distance, and such as summation then confirms as face in character facial threshold range Image.
Optionally, whether it is face according to 360 Distance Judgments, specially:
Xn=| Dn-Dn-1|;
Work as XnDuring less than given threshold, it is defined as face, otherwise for non-face;Wherein, LnIt is that origin and n-th intersection point are sat The distance between mark,It is 360 averages of distance.
Optionally, whether it is face according to 360 Distance Judgments, specially:
Wherein, γ is empirical coefficient, and mov is side-play amount, and n is the numbering of intersection point;LnFor origin and n-th intersecting point coordinate it Between distance,It is 360 averages of distance;
When the side-play amount for calculating is more than offset threshold, cumulative amount adds 1, when cumulative amount is more than 100, it is determined that It is face, otherwise for non-face.
On the other hand, there is provided a kind of intelligent end device, described device includes:
Acquiring unit, the photo for obtaining operator;
Extraction unit, the face-image for extracting operator from photo;
Whether resolution cell, be character image for the feature resolution by the face-image;
Opening unit, for when it is character image that resolution cell is told, then opening smart machine.
Optionally, the resolution cell is specifically included:
Middle point module, face contour line and eye midpoint for extracting face-image;
Judge module, for determining whether to be character graphics according to ratio,
The vertical range at the distance between ratio=eye midpoint/eye midpoint line midpoint to face contour.
Optionally, face contour line and eye midpoint of the resolution cell specifically for extraction face-image, with eye Midpoint is origin, and 360 rays are gone out in 360 ° of uniform emissions, obtains 360 intersection points between 360 rays and face contour line Coordinate, 360 distances between datum point and 360 intersecting point coordinates calculate 360 summations of distance, and such as summation is in personage In face's threshold range, then facial image is confirmed as.
Optionally, whether it is face that the resolution cell is additionally operable to according to 360 Distance Judgments, specially:
Xn=| Dn-Dn-1|;
Work as XnDuring less than given threshold, it is defined as face, otherwise for non-face;Wherein, LnIt is that origin and n-th intersection point are sat The distance between mark,It is 360 averages of distance.
Optionally, whether it is face that the resolution cell is additionally operable to according to 360 Distance Judgments, specially:
Wherein, γ is empirical coefficient, and mov is side-play amount, and n is the numbering of intersection point;LnFor origin and n-th intersecting point coordinate it Between distance,It is 360 averages of distance;
When the side-play amount for calculating is more than offset threshold, cumulative amount adds 1, when cumulative amount is more than 100, it is determined that It is face, otherwise for non-face.
In embodiments of the present invention, the mobile phone of the technical scheme that the present invention is provided is monitored by the way of recognition of face and tested Card mobile phone, so it is when cellphone subscriber changes, be capable of the operation of the non-owner of automatic shield, thus its have it is safe A little.
Brief description of the drawings
Fig. 1 is the flow chart of the method that a kind of video verification that the present invention is provided prevents mobile phone misoperation;
Fig. 2 is a kind of structure chart of intelligent end device that the present invention is provided.
Specific embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and It is not used in the restriction present invention.
The specific embodiment of the invention provides a kind of method that video verification prevents mobile phone misoperation, and the above method is by mobile phone Or other smart machines (such as ipad, PDA etc.) perform, the method is as shown in figure 1, comprise the following steps:
101st, the photo of operator is obtained;
102nd, the face-image of operator is extracted from photo;
103rd, whether it is character image by the feature resolution of the face-image;
104th, character image in this way, then open smart machine.
Whether it is character image that the method that the present invention is provided is obtained by the method for comparison chart picture, if that is, non-figure map The image such as picture, such as dog, cat does not open equipment.
Above-mentioned 103 implementation method is specifically as follows:
Face contour line and the eye midpoint of face-image are extracted, determines whether to be character graphics according to ratio.This ratio Example is specifically as follows:
The vertical range at the distance between ratio=eye midpoint/eye midpoint line midpoint to face contour.
Found by data research, different types of animal, the ratio of its aforementioned proportion is different, and it is in certain model In enclosing, the image for being belonging to character image or animal just can very easily be told by the ratio of this ratio.
Above-mentioned 103 implementation method is specifically as follows:
Face contour line and the eye midpoint of face-image are extracted, with eye midpoint as origin, is gone out in 360 ° of uniform emissions 360 rays, obtain 360 intersecting point coordinates between 360 rays and face contour line, and datum point and 360 intersection points are sat 360 distances between mark, calculate 360 summations of distance, and such as summation then confirms as face in character facial threshold range Image.
Found by studying, existing face is bigger than animal, the value of so distance that its sampling is obtained typically all compares It is larger, it is possible to maloperation is avoided, it is this kind of to distinguish humans and animals, child's maloperation can also be avoided, because not During adult, the face of child is also to be unable to reach above-mentioned requirements.
Above-mentioned 103 implementation method is specifically as follows:
Xn=| Dn-Dn-1|;
Work as XnDuring less than given threshold, it is defined as face, otherwise for non-face;Wherein, LnIt is that origin and n-th intersection point are sat The distance between mark,It is 360 averages of distance.
Above-mentioned 103 implementation method is specifically as follows:
Wherein, γ is empirical coefficient, is specifically as follows 0.15.When the side-play amount (mov) for calculating is more than offset threshold, Cumulative amount adds 1, when cumulative amount is more than 100, is defined as face, otherwise for non-face.
The specific embodiment of the invention also provides a kind of intelligent end device, the device as shown in Fig. 2 including:
Acquiring unit 21, the photo for obtaining operator;
Extraction unit 22, the face-image for extracting operator from photo;
Whether resolution cell 23, be character image for the feature resolution by the face-image;
Opening unit 24, for when it is character image that resolution cell is told, then opening smart machine.
Optionally, resolution cell 23 is specifically included:
Middle point module 231, face contour line and eye midpoint for extracting face-image;
Judge module 232, for determining whether to be character graphics according to ratio,
The vertical range at the distance between ratio=eye midpoint/eye midpoint line midpoint to face contour.
Optionally, face contour line and eye midpoint of the resolution cell 23 specifically for extraction face-image, with eye Point is origin, and 360 rays are gone out in 360 ° of uniform emissions, and 360 intersection points obtained between 360 rays and face contour line are sat Mark, 360 distances between datum point and 360 intersecting point coordinates calculate 360 summations of distance, and such as summation is in personage's face In portion's threshold range, then facial image is confirmed as.
Found by studying, existing face is bigger than animal, the value of so distance that its sampling is obtained typically all compares It is larger, it is possible to maloperation is avoided, it is this kind of to distinguish humans and animals, child's maloperation can also be avoided, because not During adult, the face of child is also to be unable to reach above-mentioned requirements.
Optionally, whether it is face that resolution cell 23 is additionally operable to according to 360 Distance Judgments, specially:
Xn=| Dn-Dn-1|;
Work as XnDuring less than given threshold, it is defined as face, otherwise for non-face;Wherein, LnIt is that origin and n-th intersection point are sat The distance between mark,It is 360 averages of distance.
Optionally, whether it is face that resolution cell 23 is additionally operable to according to 360 Distance Judgments, specially:
Wherein, γ is empirical coefficient, is specifically as follows 0.15.When the side-play amount (mov) for calculating is more than offset threshold, Cumulative amount adds 1, when cumulative amount is more than 100, is defined as face, otherwise for non-face.
Presently preferred embodiments of the present invention is the foregoing is only, is not intended to limit the invention, it is all in essence of the invention Any modification, equivalent and improvement made within god and principle etc., should be included within the scope of the present invention.

Claims (4)

1. a kind of method that video verification prevents mobile phone misoperation, it is characterised in that methods described comprises the following steps:
Obtain the photo of operator;
The face-image of operator is extracted from photo;
Whether the feature resolution by the face-image is character image;
Character image, then open smart machine in this way;
Whether the feature resolution by the face-image is that character image is specially:
Face contour line and the eye midpoint of face-image are extracted, with eye midpoint as origin, 360 is gone out in 360 ° of uniform emissions Ray, obtains 360 intersecting point coordinates between 360 rays and face contour line, between datum point and 360 intersecting point coordinates 360 distances, calculate 360 summations of distance, such as summation then confirms as facial image in character facial threshold range; Whether the feature resolution by the face-image is that character image is specially:
Face contour line and the eye midpoint of face-image are extracted, determine whether to be character graphics according to ratio,
The vertical range at the distance between ratio=eye midpoint/eye midpoint line midpoint to face contour;
Whether described be face according to 360 Distance Judgments, specially:
m o v = γ * 2 L ‾ 2 Σ n = 1 360 ( L n - L ‾ ) 2 n - 1
Wherein, γ is empirical coefficient, and mov is side-play amount, and n is the numbering of intersection point;LnFor between origin and n-th intersecting point coordinate Distance,It is 360 averages of distance;
When the side-play amount for calculating is more than offset threshold, cumulative amount adds 1, when cumulative amount is more than 100, it is determined that being people Face, otherwise for non-face.
2. method according to claim 1, it is characterised in that according to 360 Distance Judgments whether be face, specially:
D n = | L n 2 - L ‾ 2 |
Xn=| Dn-Dn-1|;
Work as XnDuring less than given threshold, it is defined as face, otherwise for non-face;Wherein, LnFor origin and n-th intersecting point coordinate it Between distance,It is 360 averages of distance.
3. a kind of intelligent end device, it is characterised in that described device includes:
Acquiring unit, the photo for obtaining operator;
Extraction unit, the face-image for extracting operator from photo;
Whether resolution cell, be character image for the feature resolution by the face-image;
Opening unit, for when it is character image that resolution cell is told, then opening smart machine;
Face contour line and eye midpoint of the resolution cell specifically for extraction face-image, with eye midpoint as origin, Go out 360 rays in 360 ° of uniform emissions, obtain 360 intersecting point coordinates between 360 rays and face contour line, calculate former 360 distances between point and 360 intersecting point coordinates, calculate 360 summations of distance, and such as summation is in character facial threshold range It is interior, then confirm as facial image;The resolution cell is specifically included:
Middle point module, face contour line and eye midpoint for extracting face-image;
Judge module, for determining whether to be character graphics according to ratio,
The vertical range at the distance between ratio=eye midpoint/eye midpoint line midpoint to face contour;
Whether it is face that the resolution cell is additionally operable to according to 360 Distance Judgments, specially:
m o v = γ * 2 L ‾ 2 Σ n = 1 360 ( L n - L ‾ ) 2 n - 1
Wherein, γ is empirical coefficient, and mov is side-play amount, and n is the numbering of intersection point;LnFor between origin and n-th intersecting point coordinate Distance,It is 360 averages of distance;
When the side-play amount for calculating is more than offset threshold, cumulative amount adds 1, when cumulative amount is more than 100, it is determined that being people Face, otherwise for non-face.
4. device according to claim 3, it is characterised in that the resolution cell is additionally operable to according to 360 Distance Judgments Whether it is face, specially:
D n = | L n 2 - L ‾ 2 |
Xn=| Dn-Dn-1|;
Work as XnDuring less than given threshold, it is defined as face, otherwise for non-face;Wherein, LnFor origin and n-th intersecting point coordinate it Between distance,It is 360 averages of distance.
CN201480001806.0A 2014-11-15 2014-11-15 Video verification prevents the method and device of mobile phone misoperation Active CN104541230B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2014/091214 WO2016074249A1 (en) 2014-11-15 2014-11-15 Method and apparatus for preventing faulty operation of mobile phone by means of video verification

Publications (2)

Publication Number Publication Date
CN104541230A CN104541230A (en) 2015-04-22
CN104541230B true CN104541230B (en) 2017-07-04

Family

ID=52855800

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201480001806.0A Active CN104541230B (en) 2014-11-15 2014-11-15 Video verification prevents the method and device of mobile phone misoperation

Country Status (2)

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

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102629955A (en) * 2012-03-30 2012-08-08 上海华勤通讯技术有限公司 Face recognition mobile telephone and implementation method thereof
CN102970411A (en) * 2012-10-24 2013-03-13 康佳集团股份有限公司 Smart phone screen locking and unlocking control method based on face detection and smart phone
CN103716456A (en) * 2013-12-10 2014-04-09 柳州译海网络科技有限公司 Mobile phone unlocking method based on face feature information

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102542299B (en) * 2011-12-07 2015-03-25 惠州Tcl移动通信有限公司 Face recognition method, device and mobile terminal capable of recognizing face
KR20140071802A (en) * 2012-12-04 2014-06-12 주식회사 엘지유플러스 Shortcut information execution system and method of mobile terminal based face recognition

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102629955A (en) * 2012-03-30 2012-08-08 上海华勤通讯技术有限公司 Face recognition mobile telephone and implementation method thereof
CN102970411A (en) * 2012-10-24 2013-03-13 康佳集团股份有限公司 Smart phone screen locking and unlocking control method based on face detection and smart phone
CN103716456A (en) * 2013-12-10 2014-04-09 柳州译海网络科技有限公司 Mobile phone unlocking method based on face feature information

Also Published As

Publication number Publication date
CN104541230A (en) 2015-04-22
WO2016074249A1 (en) 2016-05-19

Similar Documents

Publication Publication Date Title
CN103065134B (en) A kind of fingerprint identification device and method with information
US20170032224A1 (en) Method, device and computer-readable medium for sensitive picture recognition
CN104966016B (en) Mobile terminal child user cooperatively judges and the method for limitation operating right
CN105956518A (en) Face identification method, device and system
CN103440458B (en) A kind of method of heuristic static identification Android system malicious code
CN105975980A (en) Method of monitoring image mark quality and apparatus thereof
CN106557747B (en) The method and device of identification insurance single numbers
CN106295482A (en) The update method of a kind of face database and device
CN105447522A (en) Complex image character identification system
EP3564855A1 (en) Method and device for license plate positioning
CN107944380A (en) Personal identification method, device and storage device
CN103488966A (en) Intelligent mobile phone capable of identifying real-name ticket information
CN105920824A (en) Method for recording movement times by adopting intelligent terminal and intelligent terminal used for recording movement times
CN106022272A (en) Front face determining method and device
CN107977659A (en) A kind of character recognition method, device and electronic equipment
CN105975157B (en) A kind of classifying indication method and system based on mobile terminal application icon shape
CN110415212A (en) Abnormal cell detection method, device and computer readable storage medium
CN110222791A (en) The checking method and device of sample markup information
CN104541230B (en) Video verification prevents the method and device of mobile phone misoperation
CN104408736A (en) Characteristic-similarity-based synthetic face image quality evaluation method
CN104584030B (en) Verification application method and device based on face recognition
CN107862195A (en) A kind of electrical screen service condition monitoring method and system based on recognition of face
Simha et al. Recognition of numbers and position using image processing techniques for solving sudoku puzzles
CN106156591A (en) A kind of smart phone user Transparent Authentication method under cloud environment
CN110781284A (en) Knowledge graph-based question and answer method, device and storage medium

Legal Events

Date Code Title Description
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information

Address after: 518000 Nanshan District Shenzhen software industry base, building A, block 5, level 503, level 505 and level 1702, No. 17, No. first

Applicant after: Shenzhen Miki Intelligent Technology Co., Ltd.

Address before: 518000 T2-A3_2, South District, Nanshan District hi tech Zone, Guangdong, Shenzhen

Applicant before: Shenzhen Sanmu Commutication Technology Co., Ltd.

CB02 Change of applicant information
GR01 Patent grant
GR01 Patent grant