CN107992866B - Biopsy method based on video flowing eye reflective spot - Google Patents
Biopsy method based on video flowing eye reflective spot Download PDFInfo
- Publication number
- CN107992866B CN107992866B CN201810267873.7A CN201810267873A CN107992866B CN 107992866 B CN107992866 B CN 107992866B CN 201810267873 A CN201810267873 A CN 201810267873A CN 107992866 B CN107992866 B CN 107992866B
- Authority
- CN
- China
- Prior art keywords
- reflective spot
- image
- iris
- reflective
- video flowing
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 15
- 238000001574 biopsy Methods 0.000 title claims abstract description 12
- 238000001514 detection method Methods 0.000 claims abstract description 25
- 238000001727 in vivo Methods 0.000 claims abstract description 15
- 210000001747 pupil Anatomy 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 abstract description 4
- 238000000926 separation method Methods 0.000 abstract description 2
- 210000000554 iris Anatomy 0.000 description 45
- 238000005516 engineering process Methods 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 241000209202 Bromus secalinus Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 210000003786 sclera Anatomy 0.000 description 1
Classifications
-
- 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
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
-
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
At present user's eyes are illuminated using point light source during majority iris capturing equipment acquisition iris image, the iris image of such iris capturing equipment acquisition, in the highlighted reflective spot of user's eye generally existing light source, the invention discloses a kind of biopsy methods based on video flowing eye reflective spot, when iris capturing program carries out iris capturing, In vivo detection is carried out by reflective spot information in image, the reflective spot information includes reflective spot average gray, size and position, eye reflective spot information when the present invention takes full advantage of iris capturing, can eyes image and living human eye be printed with effective district separation matter, it is small with calculation amount, the advantages of detection speed is fast.
Description
Technical field
The present invention relates to technical field of image processing, more particularly to a kind of In vivo detection based on video flowing eye reflective spot
Method.
Background technology
Mainstream Algorithm of Iris Recognition at present, misclassification rate are generally less than hundred a ten thousandths, because with high accuracy, rainbow
Film identification technology is often applied in the scene of high security level, such as：Bank, hospital, prison；In this case, it identifies non-
Live body prevents other people from stealing iris information and cheats iris authentication system with artificial eye, is just particularly important.
Most iris capturing equipment illuminate user's eyes by point light source, the iris acquired using such iris capturing equipment
Image, in the highlighted reflective spot of user's eye generally existing light source, existing iris recognition biopsy method, not to reflective spot
Information is made full use of.
Invention content
The present invention is intended to provide a kind of calculation amount is small, the fast iris recognition biopsy method of detection speed, utilization is reflective
Point average gray information carries out In vivo detection, includes the following steps.
When iris capturing program carries out iris capturing, In vivo detection is carried out by reflective spot information in image, it is described anti-
Luminous point information includes reflective spot average gray；Iris capturing equipment carries out survey light to ocular in video streaming image, default
Frame carries out Image Acquisition with preset low exposure compensating, obtains and exposes relatively low image, is averaged according to low exposure image reflective spot
Whether gray scale reaches preset value, judges whether current identification object is live body, if average gray is higher than preset value, passes through inspection
It surveys；The low exposure compensating refers to that reach -2ev using eyes image is exposed as standard, is arrived in image pixel gray level section for 0
In the case of 255, the preset value of the reflective spot average gray is 200.
The reflective spot information further includes the size of reflective spot, if there is the reflective spot less than pre-set dimension in image,
Detection passes through.The reflective spot information further includes reflective spot position, and the reflective spot position refers to reflective spot and pupil and iris
Relative position, if reflective spot position changes between each frame of video flowing, pass through detection.
Biopsy method the present invention is based on video flowing eye reflective spot has that required calculation amount is small, and detection speed is fast
Advantage carries out papery printing deception iris authentication system for iris image of stealing most common at present, has good detection
Effect.
Description of the drawings
Fig. 1 is the In vivo detection flow diagram based on video flowing eye reflective spot.
Specific embodiment
The present invention proposes a kind of biopsy method based on video flowing eye reflective spot, below in conjunction with the accompanying drawings to this hair
It is bright to be described in further detail：
S101：Human eye area whether there is reflective spot：
At present user's eyes, the reflective spot are illuminated using point light source during majority iris capturing equipment acquisition iris image
Refer to, the iris image acquired using such iris capturing equipment is universal in the sclera, iris and pupil image of user's eye
The highlighted reflective spot of existing light source, the reflective spot have following characteristics：
1st, reflective spot and peripheral region contrast are higher than contrast preset value in image；Reflective spot in preferred the present embodiment
With the calculation formula of peripheral region contrast for C=| Smax-Smin |/（Smax+Smin）* 100%, wherein C are reflective spot and week
Region contrast is enclosed, Smax is the gray value of the highest pixel of brightness in reflective spot, and Smin is predeterminable area around reflective spot
The gray value of the minimum pixel of interior brightness；
2nd, single reflective spot size is less than size preset value；
3rd, reflective spot average gray is higher than gray scale preset value in image, the situation for being 0 to 255 in image pixel gray level section
Under, the gray scale preset value of the reflective spot average gray is 200；The reflective spot average gray refers in image institute in reflective spot
There is the average gray of pixel.
If there is no reflective spots for the iris image of acquisition, this frame image is not handled.
S102：Whether reflective spot quantity meets preset value：
Reflective spot is since the point light source of iris capturing equipment is reflected in user's eye surface and is generated, so for difference
Iris capturing equipment, provisioned point light source quantity is different, and the quantity of reflective spot also can be different, iris capturing equipment point light source
Position, setting angle, light source power and can also influence the quantity of reflective spot in acquired iris image using distance, therefore
For different iris capturing equipment, can corresponding preset value be set in In vivo detection algorithm, it is preferred that anti-in the present embodiment
The preset value of luminous point quantity is that reflective spot quantity is less than five in one eye, can also further set one or several determine
Value, for example reflective spot quantity is two, three or five in one eye, and reflective spot quantity meets preset value.
S103：Whether low exposure acquisition image, reflective spot average gray are more than preset value：
Preferred S102 detects three frame pictures after passing through, and is acquired, sentenced with the exposure standard of ocular -2ev
It whether there is the reflective spot higher than gray threshold in disconnected low exposure image, if so, detection passes through.In image pixel gray level section
In the case of being 0 to 255, preferably default gray threshold is 200.This judgment method can be with effective district separation matter reflective spot and work
Body reflective spot, for the iris image of papery printing, paper surface and there is no reflective spot during actual acquisition, the papery is reflective
Point refers to that iris image has reflective spot and is printed to paper in itself, therefore the papery reflective spot can be when exposing reduction, ash
Degree is substantially reduced；And live body reflective spot is iris capturing equipment point light source in the reflective of user's eye, is exposed in a certain range
It reduces, reflective spot average gray will not be substantially reduced, acceptable to be substantially reduced living human eye reflective spot average gray
Exposure reduce range by iris capturing equipment point light source quantity and position, setting angle, light source power and use away from
From etc. factors influence, when the exposure standard of ocular is reduced to -2ev under normal conditions, live body reflective spot average gray is still
More than 200.
S104：Whether reflective spot position changes：
Iris capturing program judges video flowing, and continuously whether reflective spot position changes between a few frame images, if so,
Detection passes through；In iris capturing, slightly rotated since living human eye is always subconscious, reflective spot and iris and pupil
Relative position will change, this judgment method can effectively distinguish living human eye and still image；Preferably, in this reality
It applies in example iris capturing program and obtains continuous 20 frame image, and reflective spot position is between judging each frame of the 20 frame image
It is no to change.
In another embodiment of the invention, the reflective spot change in location, by controlling iris capturing equipment infrared lamp
It generates, preferred iris capturing equipment front is evenly distributed a row 6 infrared lamps, 6 infrared during normal acquisition iris image
Lamp all lights.During In vivo detection, an infrared lamp, and then iris capturing journey are lighted during acquiring each frame iris image at random
Sequence continuously acquires a few frame images, and the relative position of reflective spot and iris and pupil changes feelings between each frame of In vivo detection Algorithm Analysis
It is sequentially corresponding whether condition is lighted with infrared lamp, if so, detection passes through.Preferably, iris capturing program in the present embodiment
Continuous 6 frame image is obtained, and whether reflective spot position changes between judging each frame of the 6 frame image.Next into
Row normal acquisition carries out the image collected human eye positioning, and image segmentation, coding extraction, completes iris registration or iris is known
Not.
Further, the present invention can also detect whether reflective spot size reaches threshold value：
Iris capturing program carries out picture collection with normal exposure, if there is the reflective spot less than pre-set dimension in image,
Then detection passes through.It preferably presets reflective spot size and is up to 20 pixels, the reflective spot pre-set dimension is by using iris
Collecting device acquisition living human eye image actual measurement determines, by the shadow for using distance, lens focus, image sensor resolutions
Ring, for distinct device the present invention is based on the biopsy method of video flowing reflective spot reflective spot pre-set dimension may have compared with
Big difference.
In embodiment, in order to ensure the accuracy of In vivo detection, in addition to being lived using reflective spot average gray information
Physical examination is surveyed, and also further In vivo detection is done by the information such as the size of reflective spot, position in iris image, in other embodiment
In, also can In vivo detection only be carried out by the comparison of reflective spot average gray information；Or in letters such as size, the positions of reflective spot
One or more are selected in breath, and In vivo detection is carried out together with the half-tone information of reflective spot.It should be appreciated that based on this implementation is changed
Example detecting step puts in order or deletes the present embodiment detecting step, and all other embodiments obtained belong to this hair
The range of bright protection.
Claims (4)
1. a kind of biopsy method based on video flowing eye reflective spot when iris capturing program carries out iris capturing, leads to
The reflective spot information crossed in the iris image of acquisition carries out In vivo detection, it is characterised in that the reflective spot information includes reflective spot
Average gray, iris capturing equipment carry out survey light to video streaming image ocular, in default frame with preset low exposure compensating
Image Acquisition is carried out, obtains and exposes relatively low image, whether preset value is reached according to low exposure image reflective spot average gray, is sentenced
Whether disconnected current identification object is live body, if average gray is higher than preset value, judges that current identification object is live body, passes through work
Physical examination is surveyed；If average gray is equal to or less than preset value, judges that current identification object is not live body, do not pass through In vivo detection.
2. the biopsy method according to claim 1 based on video flowing eye reflective spot, it is characterised in that described low
Exposure compensating refers to that reach -2ev using eyes image is exposed as standard.
3. the biopsy method according to claim 1 or 2 based on video flowing eye reflective spot, it is characterised in that with institute
State the image of low exposure compensating shooting, in the case of being 0 to 255 in image pixel gray level section, the reflective spot average gray
Preset value be 200.
4. the biopsy method according to claim 1 based on video flowing eye reflective spot, it is characterised in that described anti-
Luminous point information further includes reflective spot position, and the reflective spot position refers to the relative position of reflective spot and pupil and iris, to regarding
The reflective spot position of the successive frame of frequency stream preset quantity is judged, if reflective spot position changes between each frame, is passed through
In vivo detection.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2017111261579 | 2017-11-15 | ||
| CN201711126157 | 2017-11-15 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107992866A CN107992866A (en) | 2018-05-04 |
| CN107992866B true CN107992866B (en) | 2018-06-29 |
Family
ID=62040457
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810267873.7A Active CN107992866B (en) | 2017-11-15 | 2018-03-29 | Biopsy method based on video flowing eye reflective spot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107992866B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108647650B (en) * | 2018-05-14 | 2021-07-09 | 北京大学 | A method and system for face living detection based on corneal reflection and optical coding |
| CN109657531A (en) * | 2018-09-18 | 2019-04-19 | 深圳先牛信息技术有限公司 | A kind of human face in-vivo detection method and detection device based on hot spot on eyeball |
| CN111241878A (en) * | 2018-11-29 | 2020-06-05 | 上海聚虹光电科技有限公司 | Iris living body detection method based on infrared lamp flicker |
| CN111241880A (en) * | 2018-11-29 | 2020-06-05 | 上海聚虹光电科技有限公司 | Iris living body detection method based on infrared lamp flicker |
| CN112801067B (en) * | 2021-04-13 | 2021-08-03 | 北京万里红科技股份有限公司 | Method for detecting iris light spot and computing equipment |
| CN114253614A (en) * | 2021-11-25 | 2022-03-29 | 上海齐感电子信息科技有限公司 | Control method and control system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104537292A (en) * | 2012-08-10 | 2015-04-22 | 眼验有限责任公司 | Method and system for spoof detection for biometric authentication |
| CN104781830A (en) * | 2012-11-19 | 2015-07-15 | 虹膜技术公司 | Method and apparatus for identifying living eye |
| CN104834908A (en) * | 2015-05-07 | 2015-08-12 | 惠州Tcl移动通信有限公司 | Image exposure method for mobile terminal based on eye pattern recognition and exposure system |
| CN105354545A (en) * | 2015-10-28 | 2016-02-24 | 广东欧珀移动通信有限公司 | Iris information collection method and collection system |
| US9594969B1 (en) * | 2015-11-19 | 2017-03-14 | Intel Corporation | Iris recognition including liveness testing |
| CN107111704A (en) * | 2014-10-30 | 2017-08-29 | 达美生物识别科技有限公司 | System and method based on biological recognition system fraud detection in iris |
| CN107423699A (en) * | 2017-07-14 | 2017-12-01 | 广东欧珀移动通信有限公司 | Liveness detection method and related products |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8260008B2 (en) * | 2005-11-11 | 2012-09-04 | Eyelock, Inc. | Methods for performing biometric recognition of a human eye and corroboration of same |
| KR101286454B1 (en) * | 2012-02-29 | 2013-07-16 | 주식회사 슈프리마 | Fake face identification apparatus and method using characteristic of eye image |
| US9767358B2 (en) * | 2014-10-22 | 2017-09-19 | Veridium Ip Limited | Systems and methods for performing iris identification and verification using mobile devices |
-
2018
- 2018-03-29 CN CN201810267873.7A patent/CN107992866B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104537292A (en) * | 2012-08-10 | 2015-04-22 | 眼验有限责任公司 | Method and system for spoof detection for biometric authentication |
| CN104781830A (en) * | 2012-11-19 | 2015-07-15 | 虹膜技术公司 | Method and apparatus for identifying living eye |
| CN107111704A (en) * | 2014-10-30 | 2017-08-29 | 达美生物识别科技有限公司 | System and method based on biological recognition system fraud detection in iris |
| CN104834908A (en) * | 2015-05-07 | 2015-08-12 | 惠州Tcl移动通信有限公司 | Image exposure method for mobile terminal based on eye pattern recognition and exposure system |
| CN105354545A (en) * | 2015-10-28 | 2016-02-24 | 广东欧珀移动通信有限公司 | Iris information collection method and collection system |
| US9594969B1 (en) * | 2015-11-19 | 2017-03-14 | Intel Corporation | Iris recognition including liveness testing |
| CN107423699A (en) * | 2017-07-14 | 2017-12-01 | 广东欧珀移动通信有限公司 | Liveness detection method and related products |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107992866A (en) | 2018-05-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107992866B (en) | Biopsy method based on video flowing eye reflective spot | |
| US11132536B2 (en) | Living body detection device, living body detection method, and recording medium | |
| US8081254B2 (en) | In-camera based method of detecting defect eye with high accuracy | |
| WO2011105004A1 (en) | Pupil detection device and pupil detection method | |
| WO2022037397A1 (en) | Endoscope system and method for detecting when tail end of endoscope comes into contact with tissue | |
| JP4452836B2 (en) | Method and apparatus for detecting pupils | |
| KR101123834B1 (en) | Method and camera device for determination of photograph cheating using controllable ir light | |
| WO2005002441A1 (en) | Organism eye judgment method and organism eye judgment device | |
| US11375133B2 (en) | Automatic exposure module for an image acquisition system | |
| JP2917953B2 (en) | View point position detection device | |
| US20170372136A1 (en) | Image processing method and system for iris recognition | |
| CN108009534B (en) | Biopsy method based on pupil gray scale | |
| KR102267162B1 (en) | Eye tracking system for mild cognitive impairment | |
| JP2007025758A (en) | Human face image extraction method and apparatus | |
| CN106934349A (en) | Dual camera is imaged and iris capturing identification integration apparatus | |
| CN112041783B (en) | Method, system and computer storage medium for controlling exposure time | |
| US11570370B2 (en) | Method and system for controlling an eye tracking system | |
| JP2002000567A (en) | Method of measuring pupil center position and method of detecting view point position | |
| WO2010133099A1 (en) | Target detecting method and system and stereovision system | |
| CN113011222A (en) | Living body detection system and method and electronic equipment | |
| US20160228054A1 (en) | Organ imaging device | |
| JP4134653B2 (en) | Eye position detection apparatus and method | |
| JP7343020B2 (en) | information processing equipment | |
| JPH1172697A (en) | Method and device for detecting observer's point position | |
| WO2015068495A1 (en) | Organ image capturing device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |