Center for Biometrics and Security Research
Home | News | Team | Projects | Research | Standards | Demos | Databases | Parteners | Contact      ÖÐÎÄ
SEARCH£º        
 
Note on CASIA-IrisV3

¡¡¡¡1.Introduction

          With fast development of iris image acquisition technology, iris recognition is expected to become a fundamental component of modern society, with wide application areas in national ID card, banking, e-commerce, welfare distribution, biometric passport, and forensics, etc. Since 1990s, research on iris image processing and analysis has achieved great progress.
           However, performance of iris recognition systems in unconstrained environments is still far from perfect. Iris localization, nonlinear normalization, occlusion segmentation, liveness detection, large-scale identification and many other research issues all need further investigation. The success of investigations into such issues often depends on the availability of carefully designed iris image databases of sufficient size. Such publicly available datasets are however very limited. Therefore we are pleased to release to the public domain CASIA Iris Image Database V3.0 (or CASIA-IrisV3 for short) in order to further promote research and progress on iris recognition.

¡¡¡¡2.Brief Descriptions and Statistics of the Database

          CASIA-IrisV3 includes three subsets which are labeled as CASIA-IrisV3-Interval, CASIA-IrisV3-Lamp, CASIA-IrisV3-Twins. CASIA-IrisV3 contains a total of 22,051 iris images from more than 700 subjects. All iris images are 8 bit gray-level JPEG files, collected under near infrared illumination. Some statistics and features of each subset are summarized in Table 1. Almost all subjects are Chinese except a few in CASIA-IrisV3-Interval. Because the three data sets were collected in different times, only CASIA-IrisV3-Interval and CASIA-IrisV3-Lamp have a small overlap in subjects.

¡¡¡¡2.1 CASIA-IrisV3-Interval and CASIA V1.0

        Iris images of CASIA-IrisV3-Interval were captured with our self-developed iris camera (Fig.1a). CASIA-IrisV3-Interval is a superset of CASIA V1.0 which has been requested by and released to more than 1,500 researchers/teams from 70 countries and regions (as of June 2006). CASIA V1.0 contains 756 iris images from 108 subjects. In order to protect our IPR in the design of our iris camera (especially the NIR illumination scheme), the pupil regions of all iris images in CASIA V1.0 were automatically detected and replaced with a circular region of constant intensity to mask out the specular reflections from the NIR illuminators (see Fig. 2). Such editing clearly makes iris boundary detection much easier but has minimal or no effects on other components of an iris recognition system, such as feature extraction and classifier design. As patents have been granted to us on the design of the iris camera, we are now happy to release the original unmasked images. The availability of CASIA-IrisV3-Interval may make CASIA V1.0 obsolete.

¡¡¡¡2.2 CASIA-IrisV3-Lamp and CASIA-IrisV3-Twins

        Both CASIA-IrisV3-Lamp and CASIA-IrisV3-Twins were collected using OKI¡¯s hand-held iris sensor (Fig.1b). A lamp was turned on/off close to the subject to introduce more intra-class variations when we collected CASIA-IrisV3-Lamp. CASIA-IrisV3-Twins contains iris images from 100 pairs of twins.


(a) Iris camera developed at CASIA

(b) Iris camera from OKI
Figure 1 Iris image sensors used in CASIA V3.0 construction


(a) An image from CASIA V1.0

(b) An image from CASIA-IrisV3-Interval
Figure 2 Example images from CASIA V1.0 and CASIA-IrisV3-Interval.

Table 1 Statistics of CASIA-IrisV3

Characteristics CASIA-IrisV3-Interval CASIA-IrisV3-Lamp CASIA-IrisV3-Twins
Sensor Self-developed OKI¡¯s IRISPASS-h OKI¡¯s IRISPASS-h
Environment Indoor Indoor with lamp on/off Outdoor
Session Most of the images were captured in two sessions, with at least one month interval One One
No. of subjects 249 411 200
No. of classes 396 819 400
No. of images 2655 16213 3183
Resolution 320*280 640*480 640*480
Features Very good image quality with extremely clear iris texture details Nonlinear deformation due to variations of visible illumination The first publicly available twins¡¯iris image dataset
Total A total of 22051 iris images from more than 700 subjects and 1500 eyes

¡¡¡¡3.Image Formats and Download Instructions

          The images of the first two subsets are stored as: SubsetName\YYY\E\SXYYYENN.jpg X: the index of subset YYY: the unique identifier of subject in each subset. E: ¡®L¡¯ denotes left eye and ¡®R¡¯ denotes right eye NN: the index of image in the class. The images of CASIA-IrisV3-Twins are stored as: CASIA-IrisV3-Twins\XX\YE\S3XXYENN.jpg XX: the index of family Y:?the identifier to one of twins E: ¡®L¡¯ denotes left eye and ¡®R¡¯ denotes right eye NN: the index of image in the class.
          Researchers requesting this database should follow the following steps:
lDownload the application form at the website: http://www.cbsr.ia.ac.cn/english/Databases.asp.
lFill an application form.
lSend the form via email to casia_iris@nlpr.ia.ac.cn.
lCheck your email to find a login account and a password of our website after one day, if your application has been approved.
lDownload the CASIA Iris Image Database from our website with the authorized account within 48 hours.

¡¡¡¡4.Copyright Note and Contacts

             The database is released for research and educational purposes. We hold no liability for any unde
-sirable consequences of using the database. All rights of the CASIA database are reserved. Any person or organization is not permitted to distribute, publish, copy, or disseminate this database. In all documents and papers that report experimental results based on this database, our efforts in constructing the datab
-ase should be acknowledged as: ¡°Portions of the research in this paper use the CASIA-IrisV3 collected by the Chinese Academy of Sciences¡¯ Institute of Automation (CASIA)¡± and a reference to "CASIA-IrisV3, http:
//www.cbsr.ia.ac.cn/IrisDatabase.htm" should be included. A copy of all reports and papers that are for public or general release that use the CASIA-IrisV3 should be forwarded upon release or publication to


Professor Tieniu Tan
Center for Biometrics and Security Research
National Laboratory of Pattern Recognition
Institute of Automation, Chinese Academy of Sciences
P.O.Box 2728
Beijing 100190
China

or send electronic copies to znsun@nlpr.ia.ac.cn. Questions regarding this database can be addressed to Dr. Zhenan Sun at


Dr. Zhenan Sun
Center for Biometrics and Security Research
National Laboratory of Pattern Recognition
Institute of Automation, Chinese Academy of Sciences
P.O.Box 2728
Beijing 100190
China
Tel: +86 10 8261 0278
Fax: +86 10 6255 1993
Email: znsun@nlpr.ia.ac.cn

¡¡¡¡Publications:

[1]     T. Tan and L. Ma, ¡°Iris Recognition: Recent Progress and Remaining Challenges¡±, Proc. of SPIE, Vol. 5404, pp. 183-194, 12-13 Apr 2004, Orlando, USA.
[2]     L. Ma, T. Tan, Y. Wang and D. Zhang, ¡°Personal Identification Based on Iris Texture Analysis¡±, IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), Vol. 25, No. 12, pp.1519-1533, 2003.
[3]     Li Ma, Tieniu Tan, Yunhong Wang and Dexin Zhang, ¡°Efficient Iris Recognition by Characterizing Key Local Variations¡±, IEEE Trans. on Image Processing, Vol. 13, No.6, pp. 739- 750, 2004.
[4]     L. Ma, T. Tan, D. Zhang and Y. Wang, ¡°Local Intensity Variation Analysis for Iris Recognition, Pattern Recognition¡±, Vol.37, No.6, pp. 1287-1298, 2004.
[5]     Zhenan Sun, Yunhong Wang, Tieniu Tan, Jiali Cui, ¡°Improving Iris Recognition Accuracy via Cascaded Classifiers¡±, IEEE Transactions on Systems, Man, and Cybernetics-Part C£¬Volume 35, Issue 3, 2005, pp.435 - 441.
[6]     Zhenan Sun, Tieniu Tan, Yunhong Wang, ¡°Robust Encoding of Local Ordinal Measures: A General Framework of Iris Recognition¡±, Proceedings of International Workshop on Biometric Authentication (BioAW), Lecture Notes in Computer Science, Vol.3087, 2004, pp. 270-282.
[7]     Zhenan Sun, Yunhong Wang, Tieniu Tan, Jiali Cui, ¡°Improving Iris Recognition Accuracy via Cascaded Classifiers¡±, Proceedings of the 1st International Conference on Biometric Authentication, Lecture Notes in Computer Science, Vol.3072, 2004, pp. 418-425.
[8]     Zhenan Sun, Yunhong Wang, Tieniu Tan, Jiali Cui, ¡°Robust Direction Estimation of Gradient Vector Field for Iris Recognition¡±, Proceedings of the 17th International Conference on Pattern Recognition, Vol.2, 2004, pp.783-786.
[9]     Zhenan Sun, Yunhong Wang, Tieniu Tan, Jiali Cui, ¡°Cascading Statistical And Structural Classifiers For Iris Recognition¡±, Proceedings of IEEE International Conference on Image Processing, 2004, pp.1261-1264.
[10]     Zhenan Sun, Tieniu Tan, Yunhongwang, ¡°Iris Recognition Based on Non-local Comparisons¡±, Proceedings of the 5th Chinese Conference on Biometric Recognition, Lecture Notes in Computer Science, Vol.3338, 2004, pp. 67-77.
[11]     Zhenan Sun, Tieniu Tan, and Xianchao Qiu, "Graph Matching Iris Image Blocks with Local Binary Pattern", Proceedings of International Conference on Biometrics, Lecture Notes in Computer Sciences, Vol. 3832, 2005, pp. 366-372.
[12]     Xianchao Qiu, Zhenan Sun, Tieniu Tan, ¡°Global Texture Analysis of Iris Images for Ethnic Classification¡±, Proceedings of International Conference on Biometrics, Lecture Notes in Computer Sciences, Vol. 3832, 2005, pp. 411 - 418.
[13]     Zhuoshi Wei, Tieniu Tan, Zhenan Sun, Jiali Cui, ¡°Robust and Fast Assessment of Iris Image Quality¡±, Proceedings of International Conference on Biometrics, Lecture Notes in Computer Sciences, Vol. 3832, 2005, pp. 464 - 471.
[14]     Jiali Cui, Li Ma, Yunhong Wang, Tieniu Tan and Zhenan Sun, ¡°An Appearance-Based Method for Iris Detection¡±, Proc. of the 6th Asian Conference on Computer Vision (ACCV), Vol.2, pp.1091-1096, 2004, Korea.
[15]     Jiali Cui, Yunhong Wang, Junzhou Huang, Tieniu Tan, Zhenan Sun and Li Ma, ¡°An Iris Image Synthesis Method Based on PCA and Super-Resolution¡±, Proc. of the 17th IAPR International Conference on Pattern Recognition (ICPR), Vol. 4, pp. 471-474, 23-26 August 2004, Cambridge, UK.
[16]     Jiali Cui, Li Ma, Yunhong Wang, Tieniu Tan and Zhenan Sun, ¡°A Fast and Robust Iris Localization Method Based on Texture Segmentation¡±, Proc. of SPIE, Vol. 5404, pp. 401-408, 2004, USA.
[17]    Jiali Cui, Yunhong Wang, Li Ma, Tieniu Tan and Zhenan Sun, ¡°An Iris Recognition Algorithm Using Local Extreme Points¡±, Proceedings of the 1st International Conference on Biometric Authentication, Lecture Notes in Computer Science, Vol.3072, 2004, pp. 442-449.
[18]     Jiali Cui, Yunhong Wang, Tieniu Tan and Zhenan Sun, ¡°Fast Recursive Mathematical Morphological Transforms¡±, Proc. of the 3rd International Conference on Image and Graphics (ICIG), pp. 422-425, 2004, Hong Kong.
[19]     Junzhou Huang, Tieniu Tan, Li Ma, and Yunhong Wang, Phase Correlation Based Iris Image Registration Model, Journal of Computer Science and Technology, Vol.20, No.3, pp.419-425, May 2005.
[20]     L. Ma, Y. Wang and T. Tan, ¡°Iris Recognition Based on Multichannel Gabor Filtering¡±, Proc. of the 5th Asian Conference on Computer Vision (ACCV), Vol. I, pp.279-283, Jan 22-25, 2002, Melbourne, Australia.
[21]     L. Ma, Y. Wang and T. Tan, ¡°Iris Recognition Using Circular Symmetric Filters¡±, Proc. of IAPR International Conference on Pattern Recognition£¨ICPR£©, Vol. II, pp. 414-417, August 11-15, 2002, Quebec, Canada.
[22]     J. Z. Huang, L. Ma, T. N. Tan and Y. H. Wang, ¡°Learning-Based Enhancement Model of Iris¡±, Proc. of British Machine Vision Conference (BMVC), pp. 153-162, 2003.
[23]     J. Z. Huang, L. Ma, and Y. H. Wang and T. N. Tan, ¡°Iris Model Based on Local Orientation Description¡±, Proc. of the 6th Asian Conference on Computer Vision (ACCV), Vol.2, pp. 954-959, 2004, Korea.
[24]     J. Z. Huang, Y. H. Wang, T. N. Tan and J. L. Cui, ¡°A New Iris Segmentation Model¡±, Proc. of the 17th IAPR International Conference on Pattern Recognition (ICPR), Vol. 3, pp. 554-557, 23-26 August 2004, Cambridge, UK.
[25]    J. Z. Huang, Y. H. Wang, J. L. Cui and T. N. Tan, ¡°Noise Removal and Impainting Model for Iris Image¡±, Proc. of IEEE International Conference on Image Processing (ICIP), pp. 869-872, 2004, Singapore.
[26]     Yuqing He, Yangsheng Wang and Tieniu Tan, ¡°Iris Image Capture System Design For Personal Identification¡±, Proceedings of the 5th Chinese Conference on Biometric Recognition, Lecture Notes in Computer Science, Vol.3338, 2004, pp. 546-552.

¡¡  Introduction
¡¡  Iris Databases
¡¡  Gait Databases
¡¡  Face Databases
¡¡  Fingerprint Databases
¡¡  Palmprint Databases
¡¡  Handwriting Databases






Copy rigth All right reserved 2005 Center for Biometrics and Security Research
Center for Biometrics and Security Research 12th Floor,Institute of Automation chinese Academy of Sciences
P.O.Box2728Beijing 100080 P.R.China
Tel:010-62632259 Fax:010-62632259 E-MAIL:hjzhang@cbsr.ia.ac.cn