SLP Header

Enhanced Iris code Modelling Using Canny Edge Detection

IJCSEC Front Page

Abstract
Daugman is the most influential iris recognition algorithm.. In this paper we are introduce the new technique bit pair attributes based secure key, its central ray, being a rough representation of the original biometric signal. The central ray is an expected ray and also an optimal ray of an objective function on a group of distributions. This algorithm is derived from geometric properties of a convex polyhedral cone but does not rely on any prior knowledge. These experimental results indicate that, without a thorough security analysis, convex polyhedral cone templates cannot be assumed secure. Additionally, the simplicity of the algorithm implies that even junior hackers without knowledge of advanced image processing and biometric databases can still break into protected templates and reveal relationships among templates produced by different recognition methods. V The extraordinary market success of Iris Code relies heavily on its computational advantages, including extremely high matching speed for large-scale identification and automatic threshold adjustment based on image quality many methods modified from IrisCode were proposed for iris and user attributes based recognition. This paper refers to these methods as generalized Iris Codes.
Index Terms:Canny edge detection, Iris Codes, Gabor Filter
I.Introduction
Iriscode1 has over 100 million users from approximately 170 countries [1]. As of 4 January 2012, the total number of people just in India who have had their iris patterns enrolled by Iris Code is 103 million. The Unique Identification Authority of India is enrolling about one million persons per day, at 40,000 stations, and they plan to have the entire population of 1.2 billion people Enrolled within 3 years [33]. The extraordinary market success of Iris Code relies heavily on its computational advantages, including extremely high matching speed for large-scale identification and automatic threshold adjustment based on image quality (e.g., number of effective bits) and database size [1]–[3]. In the last two decades, this algorithm influenced many researchers [4]– [15]. Many methods modified from IrisCode were proposed for iris, palmprint, and finger-knuckle recognition. This paper refers to these methods as generalized Iris Codes (GIrisCode) [4].
The simplest modification replaced the Gabor filters in IrisCode with other linear filters or transforms. A more complex mod- ification used a clustering scheme to perform feature extrac- tion and a special coding table to perform feature encoding [4]–[5]. With these modifications, feature value precision could be increased, and many Iris Code computational advan- tages could be retained. Another modification replaced the Gabor filters in Iris Code with random vectors to con- struct cancelable biometrics for template protection [16]–[17]. A complete understanding of Iris Code is thus necessary. Though many research papers regarding iris recognition have been published, our understanding of this important algorithm remains incomplete. Daugman indicated that the imposter distribution of IrisCode follows a binomial distribution, and the bits “0” and “1” in Iris Code are equally probable [1].Hollingsworth et al.2 analyzed bit stability in their iris codes and detected the best bits for enhancing recognition perfor- mance [18]. Kong and his coworkers theoretically derived the following points: IrisCode is a clustering algorithm with four prototypes and a compression algorithm; the Gabor function can be regarded as a phase-steerable filter; the locus of a Gabor function is a two-dimensional ellipse with respect to a phase parameter and can often be approximated by a circle; the bitwise hamming distance can be considered a bitwise phase distance; and Gabor filters can be utilized as a Gabor atom detector, and the magnitude and phase of a target Gabor atom can be approximated by the magnitude and phase of the corresponding Gabor response [4], [19]–[20]. Using these theoretical results and information from iris image data- bases, Kong designed an algorithm to reconstruct iris images from Iris Codes [20]. Nevertheless, the geometric structure of Iris Codes has never been studied. This paper primarily aims to provide a deeper understanding of the geometric structures of Iris Code and its variants and secondarily seeks to analyze the potential security and privacy risks from this geometric information.

References:

  1. J. G. Daugman, “High confidence visual recognition of persons by a test of statistical independence,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 15, no. 11, pp. 1148–1161, Nov. 1993.
  2. J. Daugman, “How iris recognition works,” IEEE Trans. Circuits Syst. Video Technol., vol. 14, no. 1, pp. 21–30, Jan. 2004.
  3. J. Daugman, “New methods in iris recognition,” IEEE Trans. Syst. Man, Cybern. B, Cybern., vol. 37, no. 5, pp. 1167–1175, Oct. 2007.
  4. A. W. K. Kong, D. Zhang, and M. Kamel, “An analysis of IrisCode,” IEEE Trans. Image Process., vol. 19, no. 2, pp. 522–532, Feb. 2010.
  5. A. W. K. Kong and D. Zhang, “Competitive coding scheme for palmprint verification,” in Proc. Int. Conf. Pattern Recognit., vol. 1. 2004, pp. 520–523.
  6. A. K. Jain, S. Prabhakar, L. Hong, and S. Pankanti, “Fiterbank-based fingerprint matching,” IEEE Trans. Image Process., vol. 9, no. 5, pp. 846–859, May 200
  7. Z. Sun, T. Tan, Y. Wang, and S. Z. Li, “Ordinal palmprint representation for personal identification,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., vol. 1. May 2005, pp. 279–284.
  8. L. Ma, T. Tan, Y. Wang, and D. Zhang, “Efficient iris recognition by characterizing key local variations,” IEEE Trans. Image Process., vol. 13, no. 6, pp. 739–750, Jun. 2004.
  9. Z. Sun and T. Tan, “Ordinal measures for iris recognition,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 31, no. 12, pp. 2211–2226, Dec. 2009.