Iris recognition systems capture an image from an individual's eye. The iris in the image is then segmented and normalized for feature extraction process. The performance of iris recognition systems highly depends on segmentation and normalization. For instance, even an effective feature extraction method would not be able to obtain useful information from an iris image that is not segmented or normalized properly. This thesis is to enhance the performance of segmentation and normalization processes in iris recognition systems to increase the overall accuracy. <br /><br /> The previous iris segmentation approaches assume that the boundary of pupil is a circle. However, according to our observation, circle cannot model this boundary accurately. To improve the quality of segmentation, a novel active contour is proposed to detect the irregular boundary of pupil. The method can successfully detect all the pupil boundaries in the CASIA database and increase the recognition accuracy. <br /><br /> Most previous normalization approaches employ polar coordinate system to transform iris. Transforming iris into polar coordinates requires a reference point as the polar origin. Since pupil and limbus are generally non-concentric, there are two natural choices, pupil center and limbus center. However, their performance differences have not been investigated so far. We also propose a reference point, which is the virtual center of a pupil with radius equal to zero. We refer this point as the linearly-guessed center. The experiments demonstrate that the linearly-guessed center provides much better recognition accuracy. <br /><br /> In addition to evaluating the pupil and limbus centers and proposing a new reference point for normalization, we reformulate the normalization problem as a minimization problem. The advantage of this formulation is that it is not restricted by the circular assumption used in the reference point approaches. The experimental results demonstrate that the proposed method performs better than the reference point approaches. <br /><br /> In addition, previous normalization approaches are based on transforming iris texture into a fixed-size rectangular block. In fact, the shape and size of normalized iris have not been investigated in details. In this thesis, we study the size parameter of traditional approaches and propose a dynamic normalization scheme, which transforms an iris based on radii of pupil and limbus. The experimental results demonstrate that the dynamic normalization scheme performs better than the previous approaches.
Cite this work
Ehsan Mohammadi Arvacheh (2006). A Study of Segmentation and Normalization for Iris Recognition Systems. UWSpace. http://hdl.handle.net/10012/2846
John Daugman OBE FREng
Professor of Computer Vision and Pattern Recognition
short biographical sketch
- Computer vision, pattern recognition, neural computing, wavelet codes, chess algorithms.
- Daugman J (2017) "Biometric entropy" (summary of IAPR Award Lecture). IAPR Newsletter (July 2017), 39(3), pp 4-5. PDF
- Daugman J and Downing C (2017) "Iris image quality metrics with veto power and nonlinear importance tailoring." Chapter 4 in: Iris and Periocular Biometric Recognition (C Rathgeb and C Busch, eds), IET Publishing, ISBN: 978-1-78561-168-1, pp 83-100. PDF
- Daugman J and Downing C (2016) "Searching for doppelgängers: assessing the universality of the IrisCode impostors distribution." IET Biometrics (Jan 2016), pp 1-11. Online at IET Digital Library, or download PDF
- Daugman J (2015) "Information Theory and the IrisCode." IEEE Trans. Info.Foren.Sec11(2), pp 400-409. (PDF)
- Hao F, Daugman J, Zielinski P (2008) "A fast search algorithm for a large fuzzy database." IEEE Trans. Information Forensics and Security 3(2), pp 203-212. ( PDF)
- Daugman J (2007) "New methods in iris recognition." IEEE Trans. Systems, Man, Cybernetics B 37(5), pp 1167-1175. ( PDF)
- Daugman J (2006) "Probing the uniqueness and randomness of IrisCodes: Results from 200 billion iris pair comparisons." Proceedings of the IEEE, 94(11), pp 1927-1935. ( PDF)
- Daugman J (2003) "Demodulation by complex-valued wavelets for stochastic pattern recognition." Int'l Journal of Wavelets, Multi-resolution and Information Processing, 1(1), pp 1-17. ( PDF)
- Daugman J (2003) "The importance of being random: Statistical principles of iris recognition." Pattern Recognition, 36(2), pp 279-291. ( PDF)
- Daugman J (2002) "Gabor wavelets and statistical pattern recognition." The Handbook of Brain Theory and Neural Networks, 2nd ed., MIT Press (M. Arbib, editor), pp 457-463.
- Daugman J (2001) "Statistical richness of visual phase information." Int'l Journal of Computer Vision,45(1), pp 25-38.
- Daugman J and Downing C (2001) "Epigenetic randomness, complexity, and singularity of human iris patterns." Proceedings of the Royal Society, B, 268, Biological Sciences, pp 1737 - 1740. (PDF)
- Daugman J (2001) "Brain metaphor and brain theory." Chapter 2 in Philosophy and the Neurosciences, edited by W. Bechtel et al. Oxford: Blackwell Publishers. (Scanned PDF here)
- Daugman J (2000) "Biometric decision landscapes." Technical Report No. TR482, University of Cambridge Computer Laboratory. (PDF)
Iris RecognitionAll other links on this page relate to IRIS RECOGNITION, a practical application of the work in computer vision, wavelets, and statistical pattern recognition.
- A billion persons enrolled: International deployments of these iris recognition algorithms.
- Flagship deployment in India (Update: now 1.25 Billion citizens enrolled) (short article, PDF).
- History of iris recognition.
- General introduction (purpose, principle, current applications).
- "How Iris Recognition Works"(.pdf reprint: J. Daugman (2004), IEEE Trans. CSVT 14(1), pp. 21 - 30.)
- An iris with its "IrisCode" (and localization graphics). More examples of IrisCodes.
- Detailed colour iris image, and another.
- What iris patterns reveal in infrared light.
- Some pictures and examples of deployments of the Daugman algorithms.
- Summary of statistical results from 200 billion iris cross-comparisons (spanning 152 nationalities in the UAE border-crossing database). More detailed report with full Probability Tables available here.
- Examples of deployments at airports and border-crossings(.pdf article from Encyclopedia of Biometrics, 2010).
- "Effect of Severe Image Compression on Iris Recognition Performance"(.pdf reprint: J. Daugman and C. Downing (2008), IEEE Trans. Inform. Foren. & Secur. 3(1), pp. 52 - 61.)
- A large "watch-list" national security deployment of these algorithms.
- Interview in BioSocieties (2008) about biometrics, anonymity, privacy, and the Liberal State.
- Iris matching engine, and search speed.
- Decision environment (separability of same vs different iris patterns).
- Performance of these algorithms compared to other biometrics(UK National Physical Laboratory test report, 2001).
- Mathematical explanation of "IrisCodes" and iris recognition.
- Independence of bits across IrisCodes.
- Binomial Distribution of unrelated IrisCodes (histogram of 9.1 million raw Hamming Distances).
- 9.1 million comparisons between unrelated IrisCodes (with rotations for best match).
- Quantile-Quantile comparison between the data and binomial theory (9.1 million comparisons).
- Why false match probability does not accumulate in large database searches.
- What about genetically identical iris patterns (e.g. identical twins)?
- Anatomy, physiology, and development of the iris.
- Operators for localizing the iris within an image.
- Advantages and disadvantages of the iris for identification.
- Statistical demands of identification vs verification.
- Is there advantage in combining multiple biometrics?
- Links to some licensees and users of these algorithms; and partial list of applications.
- Iris cameras that use these algorithms.
- How these algorithms identified the National Geographic Afghan girl, 18 years later.
- What about "iridology?"
- More humour: "Iris recognition and The Simpsons Movie"
- Cartoons about iris recognition from the British press.
Back to top.