CN101447025A - Method for identifying iris of large animals - Google Patents
Method for identifying iris of large animals Download PDFInfo
- Publication number
- CN101447025A CN101447025A CNA200810242950XA CN200810242950A CN101447025A CN 101447025 A CN101447025 A CN 101447025A CN A200810242950X A CNA200810242950X A CN A200810242950XA CN 200810242950 A CN200810242950 A CN 200810242950A CN 101447025 A CN101447025 A CN 101447025A
- Authority
- CN
- China
- Prior art keywords
- circle
- iris
- outer boundary
- center
- boundary
- 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.)
- Granted
Links
Images
Abstract
The invention discloses a method for identifying iris of large animals, which belongs to the field of iris identification. The method mainly comprises the following steps: performing threshold variation and edge detection to an iris image to realize pretreatment, positioning the inner boundary circle and the outer boundary circle of the iris area by approximate circle fitting algorithm, determining the feature extraction area through division and normalization of the iris area, and determining the feature code through a 2DGabor filter. On the basis of the method for identifying iris of human eyes, the method solves the problem of noise interference caused by over-long eyelashes of the large animals by combining the eye features of the large animals and selecting the corresponding algorithms, and realizes the positioning of irregular pupil areas, and determination and final identification of iris feature coding of the large animals. The invention can realize effective management and information tracking of the large animals, and individual source tracing of pollution of meat products.
Description
Technical field
The present invention relates to a kind of iris identification method, relate in particular to a kind of method for identifying iris of large animals, belong to the iris recognition field.
Background technology
Biometrics identification technology be according to the mankind itself intrinsic physiology or behavioural characteristic and a kind of technology of discerning, iris is generally believed it is one of the most reliable biological characteristic, has advantages such as uniqueness, stability, collection property and non-infringement.Iris recognition is as a kind of new authentication identifying method, by specific recognizer, can reach high accuracy rate, its misclassification rate is minimum in the various living things feature recognitions according to statistics, these characteristics make iris recognition become very promising authentication identifying method, have extremely application fields, be applicable to and carry out many occasions that security is taken precautions against.The human eye iris recognition technology is extensively paid attention in worldwide in recent years, has obtained development rapidly.
Compare with the human eye iris recognition technology, the iris recognition technology research of larger animal still is in the budding stage, rarely has the people to study.Ear tag or electronic tag are generally all adopted in the authentication of traditional larger animal, and ear tag and electronic tag all easily come off or lose, and bring inconvenience for the management of larger animal.
Summary of the invention
The present invention proposes a kind of method for identifying iris of large animals for the individual traceability that effective management of realizing larger animal and information trace and larger animal meat product pollute.
A kind of method for identifying iris of large animals comprises the steps:
(1) pre-service of iris image:
Realize utilizing rim detection Sobel algorithm detected image edge, then the coordinate of search inner boundary left end point and right endpoint and upper extreme point and lower extreme point in comprising the rectangular area of all internal boundary points after the binaryzation by a secondary eye pattern being looked like to do threshold transformation;
(2) determine the parameter that the iris region inner boundary is round:
With the approximate circle fitting algorithm to above coordinate get average as the center of circle O of inner boundary circle (a, b), choose in the internal boundary points center of circle O apart from the inner boundary circle (a, b) apart from maximal value as inner boundary radius of a circle R;
(3) determine the parameter that the iris region outer boundary is round:
Use the approximate circle fitting algorithm, center of circle O (a of inner boundary circle is just chosen in the center of circle of outer boundary circle, b), outer boundary radius of a circle r adopts the method for ballot statistics to calculate: the center of circle of calculating outer boundary point and outer boundary circle is the center of circle O (a of inner boundary circle, b) distance, establish outer boundary point for (x, y), if outer boundary radius of a circle r ' undetermined is r '
2+ 1〉(x-a
2)+(y-b
2) r '
2-1, add 1 with regard to the counting that makes outer boundary radius of a circle r ' correspondence undetermined, after the outer boundary radius of a circle r ' undetermined of search searches maximal value from minimum value, choose the maximum outer boundary radius of a circle r ' undetermined of count value as outer boundary radius of a circle r;
(4) determine the feature extraction zone:
After having determined the iris region in the eye pattern picture, center of circle O (a of the center of circle of selected outer boundary circle or inner boundary circle, b) two sector regions in left side 90 degree and the right side 90 degree scopes are as carrying out the feature extraction zones, by polar coordinate transform the rectangular area of the regional one-to-one transformation of this feature extraction to 64*256;
(5) determine feature coding:
For the iris region in the eye pattern picture, earlier by MATLAB emulation, obtain the parameter of Gabor wave filter, by changing the Gabor filter parameter, 25-49 the Gabor wave filter of selecting to be fit to eye different texture feature constitutes the 2DGabor filter bank, the rectangular area of system after normalization is divided into the some little rectangular area of 16*16, use the 2DGabor filter bank that these little rectangular areas are carried out feature extraction and carried out convolutional calculation respectively, finally determine 2048 feature codings of this iris image.
The present invention is based on the human eye iris identification method, choose respective algorithms in conjunction with larger animal eye characteristics and solved the long noise problem of larger animal eyelashes, realized the location of irregular pupil region, the definite and final identification of iris of large animals feature coding.The present invention can realize effective management and the information trace of larger animal, and iris information can be entered in the electronic tag, and combined with radio frequency identification technology is realized the individual traceability that the larger animal meat product pollutes.
Description of drawings
Fig. 1 is a FB(flow block) of the present invention.
Fig. 2 is a complete application process flow diagram of the present invention.
Embodiment
Because iris of large animals image acquisition difficulty is bigger, it is bigger influenced by rocking of outdoor light, environment and animal eyes etc., so need iris image is carried out quality assessment and screening, choose quality image better, that can be used for discerning according to certain standard and carry out following processing:
In conjunction with illustrated in figures 1 and 2, a kind of method for identifying iris of large animals comprises the steps:
(1) pre-service of iris image:
Utilize the iris of large animals recognition system to read in iris image and carry out pre-service, check image grey level histogram by iris recognition software, search the trough value between first crest and last crest in the image, with it as threshold value, realize after the binaryzation by image being done threshold transformation, utilize rim detection Sobel algorithm detected image edge, then the coordinate of search inner boundary left end point and right endpoint and upper extreme point and lower extreme point in comprising the rectangular area of all internal boundary points;
(2) determine the parameter that the iris region inner boundary is round:
With the approximate circle fitting algorithm to above coordinate get average as the center of circle O of inner boundary circle (a, b), choose in the internal boundary points center of circle O apart from the inner boundary circle (a, b) apart from maximal value as inner boundary radius of a circle R;
(3) determine the parameter that the iris region outer boundary is round:
Use the approximate circle fitting algorithm, center of circle O (a of inner boundary circle is just chosen in the center of circle of outer boundary circle, b), outer boundary radius of a circle r adopts the method for ballot statistics to calculate: the center of circle of calculating outer boundary point and outer boundary circle is the center of circle O (a of inner boundary circle, b) distance, establish outer boundary point for (x, y), if outer boundary radius of a circle r ' undetermined is r '
2+ 1〉(x-a
2)+(y-b
2) r '
2-1, add 1 with regard to the counting that makes outer boundary radius of a circle r ' correspondence undetermined, after the outer boundary radius of a circle r ' undetermined of search searches maximal value from minimum value, choose the maximum outer boundary radius of a circle r ' undetermined of count value as outer boundary radius of a circle r;
Determine that the iris region center of circle, inside and outside border and radius can realize the location of iris region preferably, solved the larger animal pupil region and had hot spot greatly and mostly for the irregular figure of class ellipse with outer boundary is similar and center of circle problem;
(4) determine the feature extraction zone:
After having determined the iris region in the eye pattern picture, center of circle O (a of the center of circle of selected outer boundary circle or inner boundary circle, b) two sector regions in left side 90 degree and the right side 90 degree scopes are as carrying out the feature extraction zone, the rectangular area of this feature extraction zone one-to-one transformation, remove the long influence of larger animal eyelashes by polar coordinate transform to 64*256;
(5) determine feature coding:
For the iris region in the eye pattern picture, earlier by MATLAB emulation, obtain the parameter of Gabor wave filter, by changing the Gabor filter parameter, 25-49 the Gabor wave filter of selecting to be fit to eye different texture feature constitutes the 2DGabor filter bank, the rectangular area of system after normalization is divided into the some little rectangular area of 16*16, use the 2DGabor filter bank that these little rectangular areas are carried out feature extraction and carried out convolutional calculation respectively, finally determine 2048 feature codings of this iris image.
After determining to generate iris-encoding, carry out the iris information coupling: the iris information coding of generation carries out the information transmission by ODBC and database, from carrying out individual matching inquiry, the output matching result then can be with this iris information input database if there is not the coupling individuality by the comparison Hamming distance.
Claims (1)
1, a kind of method for identifying iris of large animals is characterized in that comprising the steps:
(1) pre-service of iris image:
Realize utilizing rim detection Sobel algorithm detected image edge, then the coordinate of search inner boundary left end point and right endpoint and upper extreme point and lower extreme point in comprising the rectangular area of all internal boundary points after the binaryzation by a secondary eye pattern being looked like to do threshold transformation;
(2) determine the parameter that the iris region inner boundary is round:
With the approximate circle fitting algorithm to above coordinate get average as the center of circle O of inner boundary circle (a, b), choose in the internal boundary points center of circle O apart from the inner boundary circle (a, b) apart from maximal value as inner boundary radius of a circle R;
(3) determine the parameter that the iris region outer boundary is round:
Use the approximate circle fitting algorithm, center of circle O (a of inner boundary circle is just chosen in the center of circle of outer boundary circle, b), outer boundary radius of a circle r adopts the method for ballot statistics to calculate: the center of circle of calculating outer boundary point and outer boundary circle is the center of circle O (a of inner boundary circle, b) distance, establish outer boundary point for (x, y), if outer boundary radius of a circle r ' undetermined is r '
2+ 1〉(x-a
2)+(y-b
2) r '
2-1, add 1 with regard to the counting that makes outer boundary radius of a circle r ' correspondence undetermined, after the outer boundary radius of a circle r ' undetermined of search searches maximal value from minimum value, choose the maximum outer boundary radius of a circle r ' undetermined of count value as outer boundary radius of a circle r;
(4) determine the feature extraction zone:
After having determined the iris region in the eye pattern picture, center of circle O (a of the center of circle of selected outer boundary circle or inner boundary circle, b) two sector regions in left side 90 degree and the right side 90 degree scopes are as carrying out the feature extraction zones, by polar coordinate transform the rectangular area of the regional one-to-one transformation of this feature extraction to 64*256;
(5) determine feature coding:
For the iris region in the eye pattern picture, earlier by MATLAB emulation, obtain the parameter of Gabor wave filter, by changing the Gabor filter parameter, 25-49 the Gabor wave filter of selecting to be fit to eye different texture feature constitutes the 2DGabor filter bank, the rectangular area of system after normalization is divided into the some little rectangular area of 16*16, use the 2DGabor filter bank that these little rectangular areas are carried out feature extraction and carried out convolutional calculation respectively, finally determine 2048 feature codings of this iris image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200810242950XA CN101447025B (en) | 2008-12-30 | 2008-12-30 | Method for identifying iris of large animals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200810242950XA CN101447025B (en) | 2008-12-30 | 2008-12-30 | Method for identifying iris of large animals |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101447025A true CN101447025A (en) | 2009-06-03 |
| CN101447025B CN101447025B (en) | 2011-08-10 |
Family
ID=40742697
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200810242950XA Active CN101447025B (en) | 2008-12-30 | 2008-12-30 | Method for identifying iris of large animals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101447025B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101916363A (en) * | 2010-05-28 | 2010-12-15 | 深圳大学 | Iris characteristic designing and coding method and iris identifying system |
| CN101916362A (en) * | 2010-05-28 | 2010-12-15 | 深圳大学 | Iris positioning method and iris identification system |
| CN102693421A (en) * | 2012-05-31 | 2012-09-26 | 东南大学 | Bull eye iris image identifying method based on SIFT feature packs |
| CN105631816A (en) * | 2015-12-22 | 2016-06-01 | 北京无线电计量测试研究所 | Iris image noise classification detection method |
| CN105631394A (en) * | 2015-05-29 | 2016-06-01 | 宇龙计算机通信科技(深圳)有限公司 | Iris information acquisition method, iris information acquisition device and terminal |
| CN105787939A (en) * | 2016-02-26 | 2016-07-20 | 南京理工大学 | Rapid positioning detection method for PCB circular hole |
| CN106326825A (en) * | 2015-08-26 | 2017-01-11 | 北京巴塔科技有限公司 | Iris edge positioning method |
| CN107506754A (en) * | 2017-09-19 | 2017-12-22 | 厦门中控智慧信息技术有限公司 | Iris identification method, device and terminal device |
| CN107679555A (en) * | 2017-09-14 | 2018-02-09 | 翔创科技（北京）有限公司 | Processing method, computer program, storage medium and electronic equipment is immunized in livestock |
| CN108664915A (en) * | 2018-05-07 | 2018-10-16 | 深圳辉烨通讯技术有限公司 | Personal identification method, device, equipment and storage medium |
| CN109697423A (en) * | 2018-12-19 | 2019-04-30 | 虚拟现实(深圳)智能科技有限公司 | Identify anti-lost method and VR glasses |
| CN110610128A (en) * | 2019-08-05 | 2019-12-24 | 中山市奥珀金属制品有限公司 | Iris identification method based on concentric circle extraction and storage medium |
| CN110781747A (en) * | 2019-09-23 | 2020-02-11 | 杭州电子科技大学 | Eyelash occlusion area pre-detection method based on coefficient of variation |
| CN110786823A (en) * | 2019-12-12 | 2020-02-14 | 新疆医科大学第三附属医院 | Infrared pupil identification measurement method and device, storage medium and terminal equipment |
| CN112163507A (en) * | 2020-09-25 | 2021-01-01 | 北方工业大学 | Lightweight iris recognition system facing mobile terminal |
| CN112287872A (en) * | 2020-11-12 | 2021-01-29 | 北京建筑大学 | Iris image segmentation, positioning and normalization method based on multitask neural network |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100342390C (en) * | 2004-04-16 | 2007-10-10 | 中国科学院自动化研究所 | Identity identifying method based on iris plaque |
| CN101093538B (en) * | 2006-06-19 | 2011-03-30 | 电子科技大学 | Method for identifying iris based on zero crossing indication of wavelet transforms |
-
2008
- 2008-12-30 CN CN200810242950XA patent/CN101447025B/en active Active
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101916363A (en) * | 2010-05-28 | 2010-12-15 | 深圳大学 | Iris characteristic designing and coding method and iris identifying system |
| CN101916362A (en) * | 2010-05-28 | 2010-12-15 | 深圳大学 | Iris positioning method and iris identification system |
| CN102693421A (en) * | 2012-05-31 | 2012-09-26 | 东南大学 | Bull eye iris image identifying method based on SIFT feature packs |
| CN102693421B (en) * | 2012-05-31 | 2013-12-04 | 东南大学 | Bull eye iris image identifying method based on SIFT feature packs |
| WO2013177878A1 (en) * | 2012-05-31 | 2013-12-05 | 东南大学 | Sift feature bag based bovine iris image recognition method |
| CN105631394A (en) * | 2015-05-29 | 2016-06-01 | 宇龙计算机通信科技(深圳)有限公司 | Iris information acquisition method, iris information acquisition device and terminal |
| CN105631394B (en) * | 2015-05-29 | 2019-08-02 | 宇龙计算机通信科技(深圳)有限公司 | Iris information acquisition method, iris information acquisition device and terminal |
| CN106326825A (en) * | 2015-08-26 | 2017-01-11 | 北京巴塔科技有限公司 | Iris edge positioning method |
| CN106326825B (en) * | 2015-08-26 | 2019-08-06 | 北京巴塔科技有限公司 | Iris edge localization method and iris authentication system |
| CN105631816B (en) * | 2015-12-22 | 2018-04-03 | 北京无线电计量测试研究所 | A kind of iris image noise classification detection method |
| CN105631816A (en) * | 2015-12-22 | 2016-06-01 | 北京无线电计量测试研究所 | Iris image noise classification detection method |
| CN105787939A (en) * | 2016-02-26 | 2016-07-20 | 南京理工大学 | Rapid positioning detection method for PCB circular hole |
| CN105787939B (en) * | 2016-02-26 | 2019-05-14 | 南京理工大学 | A kind of quick position finding and detection method for pcb board circular hole |
| CN107679555A (en) * | 2017-09-14 | 2018-02-09 | 翔创科技（北京）有限公司 | Processing method, computer program, storage medium and electronic equipment is immunized in livestock |
| CN107506754A (en) * | 2017-09-19 | 2017-12-22 | 厦门中控智慧信息技术有限公司 | Iris identification method, device and terminal device |
| CN108664915A (en) * | 2018-05-07 | 2018-10-16 | 深圳辉烨通讯技术有限公司 | Personal identification method, device, equipment and storage medium |
| CN109697423A (en) * | 2018-12-19 | 2019-04-30 | 虚拟现实(深圳)智能科技有限公司 | Identify anti-lost method and VR glasses |
| CN110610128A (en) * | 2019-08-05 | 2019-12-24 | 中山市奥珀金属制品有限公司 | Iris identification method based on concentric circle extraction and storage medium |
| CN110610128B (en) * | 2019-08-05 | 2023-10-03 | 张杰辉 | Iris recognition method based on concentric circle extraction and storage medium |
| CN110781747A (en) * | 2019-09-23 | 2020-02-11 | 杭州电子科技大学 | Eyelash occlusion area pre-detection method based on coefficient of variation |
| CN110781747B (en) * | 2019-09-23 | 2022-03-01 | 杭州电子科技大学 | Eyelash occlusion area pre-detection method based on coefficient of variation |
| CN110786823A (en) * | 2019-12-12 | 2020-02-14 | 新疆医科大学第三附属医院 | Infrared pupil identification measurement method and device, storage medium and terminal equipment |
| CN112163507A (en) * | 2020-09-25 | 2021-01-01 | 北方工业大学 | Lightweight iris recognition system facing mobile terminal |
| CN112163507B (en) * | 2020-09-25 | 2024-03-05 | 北方工业大学 | Mobile-end-oriented lightweight iris recognition system |
| CN112287872A (en) * | 2020-11-12 | 2021-01-29 | 北京建筑大学 | Iris image segmentation, positioning and normalization method based on multitask neural network |
| CN112287872B (en) * | 2020-11-12 | 2022-03-25 | 北京建筑大学 | Iris image segmentation, positioning and normalization method based on multitask neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101447025B (en) | 2011-08-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101447025B (en) | Method for identifying iris of large animals | |
| CN101894256B (en) | Iris identification method based on odd-symmetric 2D Log-Gabor filter | |
| Sheela et al. | Iris recognition methods-survey | |
| CN100373396C (en) | Iris identification method based on image segmentation and two-dimensional wavelet transformation | |
| CN102521575B (en) | Iris identification method based on multidirectional Gabor and Adaboost | |
| CN103632136A (en) | Method and device for locating human eyes | |
| CN102902970A (en) | Iris location method | |
| CN105469076B (en) | Face alignment verification method based on multi-instance learning | |
| CN104091147A (en) | Near infrared eye positioning and eye state identification method | |
| CN102147857A (en) | Image processing method for detecting similar round by using improved hough transformation | |
| CN102542281A (en) | Non-contact biometric feature identification method and system | |
| CN101916362A (en) | Iris positioning method and iris identification system | |
| Barpanda et al. | Iris feature extraction through wavelet mel-frequency cepstrum coefficients | |
| CN103870808A (en) | Finger vein identification method | |
| CN103246871B (en) | A kind of imperfect exterior iris boundary localization method strengthened based on image non-linear | |
| CN102332098B (en) | Method for pre-processing iris image | |
| CN106778499A (en) | A kind of method of quick positioning people's eye iris during iris capturing | |
| CN105550646A (en) | Generalized illumination invariant face feature description method based on logarithmic gradient histogram | |
| CN104268502A (en) | Recognition method for human body after vein image feature extraction | |
| Alvarez-Betancourt et al. | A fast iris location based on aggregating gradient approximation using QMA-OWA operator | |
| CN201331763Y (en) | Large animal individual traceable iris recognition middleware | |
| Ezzaki et al. | Iris recognition algorithm based on Contourlet Transform and Entropy | |
| Chung et al. | An Iris Segmentation Scheme Using Delogne--Kåsa Circle Fitting Based on Orientation Matching Transform | |
| CN105069433A (en) | Biological feature recognition method applied to smart city technology field | |
| Punyani et al. | Iris recognition system using morphology and sequential addition based grouping |
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 |