CN1144152C - Identification method based on iris recognition - Google Patents
Identification method based on iris recognition Download PDFInfo
- Publication number
- CN1144152C CN1144152C CNB991108256A CN99110825A CN1144152C CN 1144152 C CN1144152 C CN 1144152C CN B991108256 A CNB991108256 A CN B991108256A CN 99110825 A CN99110825 A CN 99110825A CN 1144152 C CN1144152 C CN 1144152C
- Authority
- CN
- China
- Prior art keywords
- iris
- image
- recognition
- shell
- adopt
- 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.)
- Expired - Lifetime
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000000605 extraction Methods 0.000 claims abstract description 8
- 238000004458 analytical method Methods 0.000 claims abstract description 6
- 238000003708 edge detection Methods 0.000 claims abstract description 4
- 238000001914 filtration Methods 0.000 claims abstract description 4
- 210000001747 pupil Anatomy 0.000 claims abstract description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 239000005338 frosted glass Substances 0.000 abstract description 5
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000003909 pattern recognition Methods 0.000 abstract description 2
- 210000000554 iris Anatomy 0.000 description 77
- 230000001105 regulatory effect Effects 0.000 description 4
- 238000005286 illumination Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000013020 embryo development Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 210000000720 eyelash Anatomy 0.000 description 1
- 210000000744 eyelid Anatomy 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000001579 optical reflectometry Methods 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Collating Specific Patterns (AREA)
Abstract
基于虹膜识别的身份鉴定方法与装置是基于模式识别技术采用机电装置的身份鉴定方法。该装置由外壳及放在外壳内壁第一圆台上的毛玻璃圆片，在第二层圆台上装有两个红外发射管及两个发光二极管，外壳下端与CCD连接。虹膜图像被采集并输入到计算机，用图像二值化提取出瞳孔与虹膜的交界圆，再采用高斯低通滤波的方法结合边缘检测提取出虹膜外圆边界，然后使用Hough变换求出外圆参数。采用纹理分析、聚类方法完成虹膜的特征提取和识别。
The identity authentication method and device based on iris recognition is an identity authentication method using electromechanical devices based on pattern recognition technology. The device consists of a shell and a frosted glass disc placed on the first round table on the inner wall of the shell, two infrared emitting tubes and two light-emitting diodes are arranged on the second round table, and the lower end of the shell is connected with the CCD. The iris image is collected and input to the computer, and the boundary circle between the pupil and the iris is extracted by image binarization, and then the outer circle boundary of the iris is extracted by using Gaussian low-pass filtering method combined with edge detection, and then the outer circle parameters are obtained by Hough transform . The feature extraction and recognition of iris is accomplished by using texture analysis and clustering methods.
Description
The present invention proposes the method for the identity discriminating of a kind of small portable ray machine electric installation and the real recognition technology of employing mould.
The main method of carrying out identification traditionally is to use key, password, certificate etc.These methods have significant limitation.Such as key lose easily, certificate may be forged, password passes into silence easily, or the like.In fact, people itself is the most reliable password.Carrying out identification based on biology, the behavioural characteristic of human body is the research direction of a hot topic in recent years.
Be used for carrying out feature that identity differentiates for example fingerprint, sound, iris, face picture and behavioural characteristic person's handwriting etc. for example of biological characteristic is arranged.Iris recognition is the method for a kind of people's of identification of just having risen recent years identity.It is compared with other authentication identifying method, has three significant advantages:
1. uniqueness: through a large amount of long-term observations, different people has different irises, even same individual's right and left eyes, its iris also has many difference.The basic structure of iris is by gene-determined, but the fine structure of iris is the environment decision during by embryonic development, so nature produces the possibility of two identical irises and small.
2. unchangeability: iris is in life later in the nepionic (about two years old), changes very little.Therefore it can be used as a kind of stable biological characteristic.
3. non-infringement: as a kind of and mutual device of people, man-machine close friend is a very important requirement.Use fingerprint recognition, person's handwriting identification or voice recognition to come the method for identity verification that a common characteristic is all arranged, promptly require tested object to do certain action or contact with equipment.They are called as and have infringement.And iris recognition does not need object to do specific action, can not carry out contact type measurement yet, can finish the function of data acquisition and identification under the situation that the user does not discover, and this has very big meaning in actual use.
Iris recognition is the highest a kind of authentication identifying method of discrimination up to now.An automatic iris authentication system comprises registration, verifies and discerns three kinds of operations.System deposits its iris feature in database by registration, judges that by checking whether subject's identity conforms to the identity that he claims, by discerning the identity of pointing out the subject automatically.
Iris recognition comprises four steps: Image Acquisition, Iris Location, feature propose and pattern match.Wherein, obtaining of iris image is the first step in the iris recognition, also is the most difficult step simultaneously.Because the special nature of iris: area is little, and darker in color makes common camera can't shoot the iris image that can be used for discerning at all.The iris color of different ethnic groups has very big difference, and white iris color is shallow, and texture is remarkable, and yellow's iris then mostly is dark brown, and texture is very not obvious.Use infrared illumination to address this problem well.Original infrared iris image acquiring device mostly is large complicated and expensive precision apparatus greatly, as the product of the IrisScan company of the U.S..
The objective of the invention is to design the iris image acquiring device that a kind of small-sized, simple and easy, flexible, low cost can clear collection iris image, and adopt the real recognition technology of mould to finish feature extraction and the identification that the image pre-service is Iris Location, iris.
Technical essential of the present invention as shown in Figure 1, iris image acquiring device is made of shell 1, frosted glass ring plate 2, infrared transmitting tube 3, light emitting diode 4, regulated power supply 5, resistance 6, lead, CCD camera 7 etc.It is characterized in that on the ground floor round platform of the inwall of shell 1, a slice frosted glass ring plate 2 being housed, at second layer round platform two infrared transmitting tubes 3 and two light emitting diodes 4 are housed symmetrically, the line of two infrared transmitting tubes 3 and the line of light emitting diode can be orthogonal, and the lower end of shell 1 is connected with the CCD camera.The circuit of image collecting device is to be connected in series with resistance 6 after two infrared transmitting tubes 3 are connected in parallel as shown in Figure 2, is connected in series with another resistance 6 after two light emitting diodes 4 are connected in parallel again, and they are connected with regulated power supply 5 respectively.Use this device to finish the 1st step of iris recognition, iris image obtains.The image that obtains as shown in Figure 4.
The 2nd step, the pre-service of image is an Iris Location: the iris image by the deriving means collection can not only comprise iris usually, the other parts that often also have eyes, such as eyelid, eyelashes, the white of the eye etc., and in highly non-infringement system, since the subject is not done requirement, thus may also can in image, comprise other thing, such as glasses, other organ of people's face etc.Therefore, before carrying out iris recognition, must determine the position of iris earlier, detect the position of iris in image.Because the inside and outside circular boundary of iris is a decentraction, so need to extract respectively.It is the boundary of pupil and iris that the present invention uses image binaryzation to extract interior circle earlier, and the method jointing edge Detection and Extraction that re-use Gauss's low-pass filtering go out the border of outer ring.Use the method for Hough conversion to obtain the parameter of cylindrical then.The result as shown in Figure 5.
The 3rd step, the feature extraction of iris: adopt the textural characteristics of the method extraction iris of texture analysis,, can reach good recognition effect in conjunction with the local feature analysis.
The 4th step, the characteristic matching of iris: iris feature that extracts and the iris feature of having registered in the database that exists are compared, determine the proprietary identity of iris.Can adopt the method for various clusters, as neural network etc.
The invention has the advantages that:
1. iris image acquisition device is simple in structure, and is light, can make up with common CCD camera, obtains iris image clearly.Use infrared illumination, can clearly shoot the detail textures of iris, solved the problem that the general visible illumination can not realize.The infrared light supply that uses is sightless, to the user without any dazzling sense of discomfort.Use the frosted glass ring plate can eliminate the high light reflectivity point of light source on the iris effectively, reduced the noise of iris image.In conjunction with software algorithm, this device can be finished the function of distinguishing true and false iris.The cost of this device is extremely low.
2. it is compared with other authentication identifying method, has three significant advantages: 1) uniqueness: the fine structure of iris is the environment decision during by embryonic development, so nature produces the possibility of two identical irises and small.2) unchangeability: iris is in life later about about two years old of nepionic, changes very little.Therefore it can be used as a kind of stable biological characteristic.3) non-infringement: and iris recognition does not need object to do specific action, can not carry out contact type measurement yet, can finish the function of data acquisition and identification under the situation that the user does not discover, this has very big meaning in actual use.
3. iris recognition is the highest a kind of authentication identifying method of discrimination up to now.
Description of drawings:
Fig. 1 is the structural drawing of iris image acquiring device.1-outer wall, 2-frosted glass ring plate, 3-infrared transmitting tube, 4-light emitting diode, 7-CCD camera.
Fig. 2 is the circuit theory diagrams of iris image acquiring device.3-infrared transmitting tube, 4-light emitting diode, 5-regulated power supply, 6-resistance.
Fig. 3 is the identification system based on iris.
Fig. 4 is for using the part iris image sample that the present invention gathered.
Fig. 5 is the process flow diagram of iris authentication system.
Fig. 6 is the experimental result of Iris Location.
Embodiment:
The present invention can be used in the identification system based on iris.The workflow of iris authentication system such as Fig. 5 know and show, comprise four steps: Image Acquisition, Iris Location, feature propose and pattern match.
It is as follows to describe the iris image acquisition device use in conjunction with Fig. 3: the upper end of this device is buckled on subject's the eyes, controls regulated power supply to regulate the brightness of light emitting diode by computing machine.The CCD camera is taken the iris image under the infrared tube irradiation, and the input computing machine.The algorithm that computing machine calls iris recognition carries out pattern-recognition to the iris image that obtains, and finishes the function of identity authentication.The image of the different irises that obtain with this device therefrom can clearly reflect the difference of iris texture as shown in Figure 4.Can utilize this iris image gathering system to set up iris database, the various occasions that are applied to discriminate one's identification.
Use image binaryzation to extract interior circle (being the boundary of pupil and iris) earlier, the method jointing edge Detection and Extraction that re-use Gauss's low-pass filtering go out the border of outer ring.Use the method for Hough conversion to obtain the parameter of cylindrical then.Experimental result as shown in Figure 6.Adopt the textural characteristics of the method extraction iris of texture analysis,, can reach good recognition effect in conjunction with the local feature analysis.Adopt the method for various clusters,, iris feature that extracts and the iris feature of having registered in the database that exists are compared, determine the proprietary identity of iris as neural network etc.
Claims (1)
1. identity identifying method based on iris recognition, it is characterized in that, iris image is input to computing machine by the iris image of CCD camera collection, adopt image binaryzation to extract the boundary circle of pupil and iris earlier, adopt the method jointing edge Detection and Extraction of Gauss's low-pass filtering to go out iris outer circumferential edge circle again, use the method for Hough conversion to obtain the cylindrical parameter then, adopt the method for texture analysis to extract the textural characteristics of iris, the identification that clustering method is finished iris.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB991108256A CN1144152C (en) | 1999-07-22 | 1999-07-22 | Identification method based on iris recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB991108256A CN1144152C (en) | 1999-07-22 | 1999-07-22 | Identification method based on iris recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN1282048A CN1282048A (en) | 2001-01-31 |
| CN1144152C true CN1144152C (en) | 2004-03-31 |
Family
ID=5274717
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB991108256A Expired - Lifetime CN1144152C (en) | 1999-07-22 | 1999-07-22 | Identification method based on iris recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1144152C (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7436986B2 (en) * | 2003-03-25 | 2008-10-14 | Bausch & Lomb Incorporated | Positive patient identification |
| CN100378750C (en) * | 2003-09-25 | 2008-04-02 | 派昂公司 | System and method for three-dimensional reconstruction of a tubular organ |
| CN1298283C (en) * | 2003-11-18 | 2007-02-07 | 清华大学 | Iris image collecting method |
| FR2864290B1 (en) * | 2003-12-18 | 2006-05-26 | Sagem | METHOD AND DEVICE FOR RECOGNIZING IRIS |
| JP3966309B2 (en) * | 2004-07-14 | 2007-08-29 | 松下電器産業株式会社 | Pupil detection device and iris authentication device |
| CN100369045C (en) * | 2004-12-31 | 2008-02-13 | 中国科学院自动化研究所 | Fast customs clearance method based on biological passport |
| CN100433043C (en) * | 2006-04-18 | 2008-11-12 | 南京大学 | Automatic tracking invasive iris image collection device |
| CN101539990B (en) * | 2008-03-20 | 2011-05-11 | 中国科学院自动化研究所 | Method for selecting and rapidly comparing robust features of iris images |
| US20170180614A1 (en) * | 2015-12-17 | 2017-06-22 | Intel Corporation | Iris imaging |
| CN112394507A (en) * | 2020-10-21 | 2021-02-23 | 天津中科智能识别产业技术研究院有限公司 | Iris imaging depth of field extension method based on liquid lens |
-
1999
- 1999-07-22 CN CNB991108256A patent/CN1144152C/en not_active Expired - Lifetime
Also Published As
| Publication number | Publication date |
|---|---|
| CN1282048A (en) | 2001-01-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sun et al. | Improving iris recognition accuracy via cascaded classifiers | |
| Vatsa et al. | Comparison of iris recognition algorithms | |
| CN102419819B (en) | Face image recognition method and system | |
| CN111462379A (en) | Access control management method, system and medium containing palm vein and face recognition | |
| CN105956520B (en) | A kind of PID personal identification device and method based on multi-mode biometric information | |
| CN105224906B (en) | Palm vein recognition intelligent system | |
| US20060280340A1 (en) | Conjunctival scans for personal identification | |
| CN1627317A (en) | Method for obtaining image of human faces by using active light source | |
| CN1144152C (en) | Identification method based on iris recognition | |
| Chirchi et al. | Iris biometric recognition for person identification in security systems | |
| CN101196987A (en) | On-line palmprint, palm vein image identification method and its special acquisition device | |
| CN105975938A (en) | Smart community manager service system with dynamic face identification function | |
| KR20050025927A (en) | The pupil detection method and shape descriptor extraction method for a iris recognition, iris feature extraction apparatus and method, and iris recognition system and method using its | |
| Aleem et al. | Fast and accurate retinal identification system: Using retinal blood vasculature landmarks | |
| CN102496007A (en) | Human body identity identification instrument | |
| CN101464945A (en) | Identification characteristic identification method based on finger back arthrosis veins | |
| Liu et al. | A practical iris acquisition system and a fast edges locating algorithm in iris recognition | |
| WO2017173639A1 (en) | Personal recognition device and method on the basis of multi-mode biological recognition information | |
| CN109086692A (en) | A kind of face identification device and method | |
| CN1423227A (en) | Indentity identifying method and apparatus with iris identifying function | |
| Mohammed et al. | Conceptual analysis of Iris Recognition Systems | |
| Ibitayo et al. | Development Of Iris Based Age And Gender Detection System | |
| Conti et al. | A novel iris recognition system based on micro-features | |
| CN2392219Y (en) | Iris image collecting device | |
| Falohun et al. | Remote Access Control System Using Iris Signature |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| REG | Reference to a national code |
Ref country code: HK Ref legal event code: GR Ref document number: 1039807 Country of ref document: HK |
|
| ASS | Succession or assignment of patent right |
Owner name: ZHONGKEHONGBA TECH CO., LTD., BEIJING Free format text: FORMER OWNER: RESEARCH INST. OF AUTOMATION, CHINESE ACADEMY OF SCIENCES Effective date: 20111209 |
|
| C41 | Transfer of patent application or patent right or utility model | ||
| COR | Change of bibliographic data |
Free format text: CORRECT: ADDRESS; FROM: 100080 HAIDIAN, BEIJING TO: 100190 HAIDIAN, BEIJING |
|
| TR01 | Transfer of patent right |
Effective date of registration: 20111209 Address after: 100190 1, 95 East Zhongguancun Road, Beijing, Haidian District, 501 Patentee after: Zhongkehongba Tech Co., Ltd., Beijing Address before: 100080, No. 1, South Haidian District, Beijing, Zhongguancun Patentee before: Institute of Automation, Chinese Academy of Sciences |
|
| CX01 | Expiry of patent term |
Granted publication date: 20040331 |
|
| CX01 | Expiry of patent term |