KR101388236B1 - Face recognition system using camera glasses - Google Patents

Face recognition system using camera glasses Download PDF

Info

Publication number
KR101388236B1
KR101388236B1 KR1020130011165A KR20130011165A KR101388236B1 KR 101388236 B1 KR101388236 B1 KR 101388236B1 KR 1020130011165 A KR1020130011165 A KR 1020130011165A KR 20130011165 A KR20130011165 A KR 20130011165A KR 101388236 B1 KR101388236 B1 KR 101388236B1
Authority
KR
South Korea
Prior art keywords
information
face
facial
unit
glasses
Prior art date
Application number
KR1020130011165A
Other languages
Korean (ko)
Inventor
윤영기
Original Assignee
윤영기
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 윤영기 filed Critical 윤영기
Priority to KR1020130011165A priority Critical patent/KR101388236B1/en
Application granted granted Critical
Publication of KR101388236B1 publication Critical patent/KR101388236B1/en

Links

Images

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
    • G06K9/00221Acquiring or recognising human faces, facial parts, facial sketches, facial expressions
    • G06K9/00288Classification, e.g. identification
    • 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
    • G06K9/00597Acquiring or recognising eyes, e.g. iris verification
    • 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
    • G06K9/36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
    • G06K9/58Image preprocessing, i.e. processing the image information without deciding about the identity of the image using optical means
    • GPHYSICS
    • G02OPTICS
    • G02BOPTICAL ELEMENTS, SYSTEMS, OR APPARATUS
    • G02B27/00Optical systems or apparatus not provided for by any of the groups G02B1/00 - G02B26/00, G02B30/00
    • G02B27/01Head-up displays
    • G02B27/017Head mounted
    • G02B2027/0178Eyeglass type, eyeglass details G02C
    • 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
    • G06K9/36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
    • G06K9/46Extraction of features or characteristics of the image
    • G06K9/48Extraction of features or characteristics of the image by coding the contour of the pattern contour related features or features from contour like patterns, e.g. hand-drawn point-sequence
    • G06K2009/485Extraction of features or characteristics of the image by coding the contour of the pattern contour related features or features from contour like patterns, e.g. hand-drawn point-sequence using a gradient analysis

Abstract

Disclosed is a face recognition system used as an assistive device for people with prosopagnosia or used for entrance control or fugitive warrant. To this end, provided is a face recognition device comprising a face information collection unit collecting face information through local area communications; a pattern correction unit correcting the slope of eye information included in the collected face information, and extracting pattern correction information; a face digitization unit digitizing a feature value of face elements based on the face information; and a pattern information transmission unit searching for the extracted pattern correction information and the digitized face elements in a database, and transmitting a result and recognition information to a portable terminal, or search for face figure information in an external face recognition system. [Reference numerals] (121) Face information collection unit; (122) Pattern correction unit; (123) Face digitization unit; (124) Pattern information transmission unit; (126) Control unit; (AA) Face information inquiry system

Description

Facial recognition system using camera glasses {FACE RECOGNITION SYSTEM USING CAMERA GLASSES}

The present invention relates to a facial recognition system, and more particularly, a facial recognition system that is portable and used as an auxiliary tool for people with facial recognition disorders, or for access control or a place where a person can access a place. It is about.

Recent cameras are often mounted on glasses for special purposes. Such spectacle cameras have been used to photograph objects in front of glasses or to recognize faces.

In this way, the glasses equipped with the camera do not recognize the faces of those persons in order to prevent illegal entry with a forgery certificate if only the specific persons of the immigration office are allowed to enter, and do not rely on the memory of the person for arranging the criminal. It is used to recognize a criminal's face for the purpose of making an arrangement.

As a device using the eyeglasses equipped with the camera, a pupillary distance measuring method and a measuring device are disclosed in 0031978 published on April 06, 2005. However, since the published patent only measures the pupil distance of the eyeball, there is a problem that it is very limited to be used as an immigration office or a range designation program described above.

The present invention has been made to solve the above-described problem, by identifying the person (winner) through eye-tracking the eye of the wearer in the camera glasses to recognize the face information, the face information measured based on the above The purpose of the present invention is to provide a facial recognition system using camera glasses, which can be used to correct people and correct eye information.

In order to accomplish the objects of the present invention as described above and to carry out the characteristic functions of the present invention described below, features of the present invention are as follows.

According to an aspect of the present invention, a facial recognition system including a glasses equipped with a camera and a facial recognition device that is used to identify the winner after acquiring tracking information and photographed image information of the wearer's eye from the glasses, the facial recognition system The apparatus may include: a face information collector configured to collect the face information through short-range communication and extract a person (winner) through eyeball tracking information from the image information; A pattern corrector for extracting pattern correction information by correcting a slope from the eyeball information included in the collected facial information; A facial digitizer configured to digitize the characteristic values of facial elements based on the facial information; And a pattern information transmission unit configured to transmit pattern recognition information generated by a result of searching the extracted pattern correction information and the digitized face elements in a database or a result of comparison with a pattern extracted from an image for comparison to a mobile terminal. A facial recognition system using camera glasses is provided.

Here, the pattern correction unit according to an aspect of the present invention may extract the pattern correction information by correcting the inclination of the left and right, the vertical angle of the eyeball included in the eyeball information.

In addition, the facial digitizing unit according to an aspect of the present invention, the upper and lower, the left and right ratio of the face, the ratio of the jawline below the ear, the left and right ratio of the eye, the head and nose, the shape of the eyes, the ratio of the distance between the mouth and eyes and the size of the eye Characteristic values of facial elements, such as the size ratio of the mouth, can be quantified.

As described above, according to the present invention, by quantifying the characteristic value of the facial element based on the face information, extracting the pattern correction information and using it to identify the person (winner) by complementing the existing personal authentication to further strengthen personal security Giving effect.

In particular, the present invention has the effect of identifying the person (winner) through a faster and more accurate search by quantifying the ratio of the eyeball included in the eye information and the facial elements such as eyes, nose, mouth of each face.

1 is a schematic view of a face recognition system 100 using camera glasses 110 according to an embodiment of the present invention.
2 is a diagram exemplarily showing camera glasses 110 according to an embodiment of the present invention.
3 is a block diagram showing the configuration of the facial recognition apparatus 120 according to an embodiment of the present invention.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings, so that those skilled in the art can easily carry out the present invention. In the drawings, like reference numerals refer to the same or similar functions throughout the several views.

1 is a view schematically showing a face recognition system 100 using the camera glasses 110 according to an embodiment of the present invention, Figure 2 is an exemplary camera glasses 110 according to an embodiment of the present invention It is a figure shown.

As shown in FIG. 1, the facial recognition system 100 according to an exemplary embodiment of the present invention includes a camera glasses 110, a facial recognition device 120, and a portable terminal 130.

First, the camera glasses 110 according to the present invention are glasses mounted with the camera 111, the camera 111 is used to be mounted around the spectacle frame of the glasses. In this way, the camera 111 mounted on the glasses not only photographs the front image but also tracks the eye of the wearer.

As a result, the captured front image and the eye tracking information of the wearer are transmitted to the face recognition apparatus 120 to be described later through the local area network. In this case, the facial information includes not only eyes, noses and mouths but also information on the entire face.

On the other hand, the local area network means any one of the methods, such as wired, NFC communication, Bluetooth communication, WiFi communication, not limited to this, of course, various communication methods are used.

Next, the facial recognition apparatus 120 according to the present invention identifies the person (winner) that the wearer wants to know by using the image information and eye tracking information received from the camera glasses 110 through the local area network as described above. Extract the information. The extracted facial image is processed as facial information, and image information and eye tracking information included in the facial information are received. Therefore, the face recognition apparatus 120 performs a process of correcting through information such as eyes (eyes), nose, mouth, forehead, jaw, and ears and digitizing them with characteristic values. This process will be described in more detail later in FIG. 3.

As a result, the facial recognition apparatus 120 according to the present invention may be utilized for access control or nomination for criminals by quickly searching each person's facial characteristics through the calibrated information and digitized information. Used for this purpose gives the advantage of more accurate identification of a person based on a personal certificate to identify the person.

The corrected information and the digitized information thus obtained are used as a means for authenticating a person, and then informs the result of the user's portable terminal 130 through the local area network. In this case, it is preferable that the corrected information and the digitized information are used for authentication, and in particular, the result of the digitized information and the recognized information is transmitted to the portable terminal 130.

The mobile terminal 130 displays the result of the digitized information and the recognized information sent from the facial recognition device 120 on the display screen, thereby recognizing the person who owns the mobile terminal 130 through the facial characteristics of the winner. It helps to know the result. Meanwhile, the portable terminal 130 may be a portable terminal of a person who acted as a spectacle camera, or may be a portable terminal of a winner or a portable terminal of a monitor.

Hereinafter, each configuration of the face recognition device 120 will be described in more detail. 3 is a block diagram showing the configuration of the facial recognition apparatus 120 according to an embodiment of the present invention.

As shown in FIG. 3, the facial recognition apparatus 120 according to an exemplary embodiment of the present invention may include a face information collecting unit 121, a pattern correcting unit 122, a face digitizing unit 123, and a pattern information transmitting unit ( 124, a database 125, and a controller 126.

First, the face information collector 121 according to the present invention collects the front image captured by the camera glasses 110 and information tracked by the wearer's eye through short-range communication.

 Facial information such as eyes, nose, mouth, ear, forehead, and chin, which are facial information of a person focused on the eye, is extracted from the collected images.

Next, the pattern corrector 122 according to the present invention utilizes eyeball information included in facial information collected by the facial information collector 121. That is, pattern correction information is extracted by correcting the inclination of each element (eg, eye (eye), nose, mouth, forehead, etc.) included in the eye information by using eye information included in the face information.

More specifically, the pattern correction unit 122 according to the present invention can extract the pattern correction information by correcting the inclination of the left and right, the vertical angle of the eyeball included in the eyeball information.

Therefore, the face information photographed by the camera glasses 110 is converted into more accurate pattern correction information and digitized, and compared with the data previously stored in the database 125 (for example, the face information of the subject) to face a person (winner). You will recognize this faster and more accurately.

Or by comparing the pattern extracted from the image for the purpose of comparison rather than the database 125 is to recognize the person (winner) accurately.

Next, the face digitizing unit 123 according to the present invention digitizes the feature value of the face element based on the face information collected by the face information collecting unit 121 described above.

More specifically, the facial digitizing unit 123 according to the present invention is the upper and lower, the left and right ratio of the face, the ratio of the jawline below the ear, the ratio of the left and right of the eye, the ratio of the head and nose, the ratio of the distance between the mouth and eyes and the size of the eye It is quantified by a characteristic value that distinguishes facial elements such as the size ratio of the mouth.

When the ratio between facial elements included in the facial information is quantified as a characteristic value, the corresponding person (winner) can be identified by comparing with the facial element information previously stored in the database 125.

Next, the pattern information transmitter 124 according to the present invention uses the pattern correction information extracted by the pattern corrector 122 and the facial elements digitized by the face digitizer 123 as described above. To search for a person (winner) and transmit the recognition information, which is a result of comparing the pattern information extracted from the search result or the image for comparison, to the mobile terminal 130 and the capacity of the database previously stored in the mobile device. Due to the limitation, in order to inquire more facial information, the computerized system that analyzes facial information through a communication network inquires in real time the numerical information of the face, and receives the inquired result and transmits it to the mobile terminal 130.

The extracted pattern recognition information includes a result of comparing and analyzing the face of the person (winner). For example, it may include results of comparative analysis such as whether the distance between the eye and the incidence is different or the eye is exactly matched.

As such, the extracted pattern recognition information is transmitted to the mobile terminal 130 through the mobile communication network. In this case, the mobile terminal 130 may be used for identification of the person (winner), access control, and various purposes in the case of the watcher's terminal, and may be used for checking the face pattern of the person. .

As a result, the monitor can help identify and take action from a distance, and can be used for arranging the nominee.

On the other hand, as described above, the extracted pattern recognition information is of course used to open and close the door by identifying the person through the face information. Therefore, even if there is no monitor, the entrance of a person (winner) can be automatically controlled or a person (operator) can be controlled by manual operation at a remote location.

Lastly, the controller 126 according to the present invention controls the data flow between the face information collecting unit 121, the pattern correcting unit 122, the face digitizing unit 123, the pattern information transmitting unit 124, and the database 125. And controls data flow between the camera glasses 110, the face recognition device 120, and the portable terminal 130. Therefore, each function of the face recognition apparatus 120 is to perform a unique function.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the exemplary embodiments or constructions. You can understand that you can do it. The embodiments described above are therefore to be considered in all respects as illustrative and not restrictive.

100: facial recognition system 110: camera glasses
120: facial recognition apparatus 121: facial information collection unit
122: pattern correction unit 123: facial digitizing unit
124: pattern information transmission unit 125: database
126 control unit 130 mobile terminal

Claims (4)

  1. A facial recognition system including a glasses equipped with a camera and a facial recognition device that acquires images captured from the glasses and eye tracking information of a wearer, and extracts facial information of a winner using eye tracking information to identify the winner.
    The face recognition device,
    A face information collecting unit for receiving the image captured by the glasses camera and eye tracking information of the wearer through short-range communication and collecting face information of a winner to be searched using the eye tracking information;
    A pattern corrector for extracting pattern correction information by correcting a slope from the eyeball information included in the collected facial information;
    A facial digitizer configured to quantify characteristic values of facial elements based on the facial information; And
    When the extracted pattern correction information and the digitized face elements are searched in the face information previously stored in the database, the recognition information which is a result of the search is transmitted to the mobile terminal, and when more facial information is retrieved than the previously stored face information, A pattern information transmission unit for querying the digitized facial information in a facial retrieval system; Lt; / RTI >

    The facial information collection unit,
    By recognizing the movement and state of the eyeball of the wearer, the human face is extracted from the image of the glasses camera,

    The pattern correction unit,
    Facial recognition system using a camera glasses, characterized in that for extracting the pattern correction information by correcting the inclination of the left and right, up and down angle of the eyeball included in the eyeball information.
  2. delete
  3. delete
  4. The method of claim 1,
    The face digitizing unit,
    Numerical values of facial elements including top and bottom, left and right ratios, sub-ear jaw ratios, left and right ratios of eyes, head and nose shapes, distances between mouth and eyes, size ratios of eyes, and size ratios of mouths Facial recognition system using a camera glasses, characterized in that.
KR1020130011165A 2013-01-31 2013-01-31 Face recognition system using camera glasses KR101388236B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020130011165A KR101388236B1 (en) 2013-01-31 2013-01-31 Face recognition system using camera glasses

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020130011165A KR101388236B1 (en) 2013-01-31 2013-01-31 Face recognition system using camera glasses

Publications (1)

Publication Number Publication Date
KR101388236B1 true KR101388236B1 (en) 2014-04-23

Family

ID=50658461

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020130011165A KR101388236B1 (en) 2013-01-31 2013-01-31 Face recognition system using camera glasses

Country Status (1)

Country Link
KR (1) KR101388236B1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015177102A1 (en) * 2014-05-19 2015-11-26 Agt International Gmbh Face recognition using concealed mobile camera
KR20160038689A (en) * 2014-09-30 2016-04-07 넥시스 주식회사 Method and program for confirmation of identity by wearable glass device

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20050031978A (en) * 2003-09-30 2005-04-06 펜탁스 가부시키가이샤 Method and device for measuring pupil distance
JP2010061265A (en) * 2008-09-02 2010-03-18 Fujifilm Corp Person retrieval and registration system
KR20100065065A (en) * 2008-12-05 2010-06-15 한국전자통신연구원 Glasses type headset apparatus, control system for robot including the same and control method for robot thereof
KR20120127790A (en) * 2011-05-16 2012-11-26 경북대학교 산학협력단 Eye tracking system and method the same

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20050031978A (en) * 2003-09-30 2005-04-06 펜탁스 가부시키가이샤 Method and device for measuring pupil distance
JP2010061265A (en) * 2008-09-02 2010-03-18 Fujifilm Corp Person retrieval and registration system
KR20100065065A (en) * 2008-12-05 2010-06-15 한국전자통신연구원 Glasses type headset apparatus, control system for robot including the same and control method for robot thereof
KR20120127790A (en) * 2011-05-16 2012-11-26 경북대학교 산학협력단 Eye tracking system and method the same

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015177102A1 (en) * 2014-05-19 2015-11-26 Agt International Gmbh Face recognition using concealed mobile camera
KR20160038689A (en) * 2014-09-30 2016-04-07 넥시스 주식회사 Method and program for confirmation of identity by wearable glass device
KR101661556B1 (en) * 2014-09-30 2016-10-04 넥시스 주식회사 Method and program for confirmation of identity by wearable glass device

Similar Documents

Publication Publication Date Title
US9412011B2 (en) Warning a user about adverse behaviors of others within an environment based on a 3D captured image stream
US10762367B2 (en) Systems and methods of biometric analysis to determine natural reflectivity
US9256721B2 (en) Mobile wireless hand-held biometric capture, processing and communication system and method for biometric identification
KR20160026791A (en) Facial recognition authentication system including path parameters
US20160335495A1 (en) Apparatus and method for acquiring image for iris recognition using distance of facial feature
US8600121B2 (en) Face recognition system and method
EP1629415B1 (en) Face identification verification using frontal and side views
KR20170000128A (en) Mobile electric document system of multiple biometric
US8761458B2 (en) System for iris detection, tracking and recognition at a distance
US6950536B2 (en) High volume mobile identity verification system and method using tiered biometric analysis
DE60209050T2 (en) Apparatus and method for adjusting the focus position in an iris recognition system
JP4177598B2 (en) Face image recording apparatus, information management system, face image recording method, and information management method
KR100649303B1 (en) Apparatus of taking pictures in iris recognition system based on both of eyes's images
JP5043097B2 (en) Person identification method by eyelash analysis
JP4734980B2 (en) Face authentication device and control method therefor, electronic device equipped with face authentication device, face authentication device control program, and recording medium recording the program
JP2014085796A (en) Information processing device and program
US20160063314A1 (en) Image processing apparatus for facial recognition
KR101426952B1 (en) Information processing apparatus, information processing method, person identification apparatus, and method of producing/updating dictionary data in person identification apparatus
JP4085959B2 (en) Object detection device, object detection method, and recording medium
CN102622588B (en) Dual-certification face anti-counterfeit method and device
CN106716451A (en) Iris recognition device, manufacturing method therefor, and application thereof
JP4696610B2 (en) Subject authentication device, face authentication device, mobile phone, and subject authentication method
KR100831122B1 (en) Face authentication apparatus, face authentication method, and entrance and exit management apparatus
US20160012217A1 (en) Mobile terminal for capturing biometric data
US10205883B2 (en) Display control method, terminal device, and storage medium

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
E701 Decision to grant or registration of patent right
GRNT Written decision to grant
FPAY Annual fee payment

Payment date: 20170222

Year of fee payment: 4

FPAY Annual fee payment

Payment date: 20180209

Year of fee payment: 5

FPAY Annual fee payment

Payment date: 20200204

Year of fee payment: 7