OBJECTIVE[/b]
The objective of our project is to provide authentication based on iris recognition. A novel iris recognition method is presented. In the method, the iris features are extracted using the oriented separable wavelet transforms (directionlets) and they are compared in terms of a weighted Hamming distance. The feature extraction and comparison are shift-, size- and rotation-invariant to the location of iris in the acquired image. The generated iris code is binary, whose length is fixed (and therefore commensurable), independent of the iris image, and comparatively short. The novel method shows a good performance when applied to a large database of irises and provides reliable identification and verification. At the same time, it preserves conceptual and computational simplicity and allows for a quick analysis and comparison of iris samples.
PROPOSED SYSTEM
Iris recognition using directionlets.
Provide short binary code of the iris features, fixed length, independent of iris image.
It includes
region localization
feature extraction
feature comparison


ARCHITECTURAL DESIGN
FUNCTIONAL MODULES
Region localization
Feature extraction
Feature comparision
Iris recognition
REGION LOCALIZATION
Estimated by maximization of radial derivative of circular integrals over the iris image.
Parameters obtained using only the left and right 90 degree cones.
FEATURE EXTRACTION
Filtering iris image
Sampling wavelet coefficients.
Generating binary code.
FILTERING IRIS IMAGE
Smoothing – iterative low-pass filtering applied along horizontal and vertical directions.
Directional filtering-one step of high-pass filtering along a single direction.
SAMPLING
Directional subbands are sampled.
Iris features are captured along both radial and angular directions.
Sampling coordinates are given in a polar coordinate system and rounded to nearest integer to avoid interpolation.
GENERATING BINARY CODE
Binary code consists of the retained coefficients.
Corresponding bit is 1 if retained coefficients value greater or equal to 0 .
Otherwise it is 0.
FEATURE COMPARISON
Calculate a weighted Hamming distance score between two binary codes generated.
Distance score normalized so that it lies between 0 and 1.
In case of self-distance it is 0.
ALGORITHM USED
2D Wavelet transform.
Mapping the pixel value into 2D array.
Preprocessing .
Applying discrete wavelet transform.
Thresholding.

CONCLUSION
Method is shift-,size and rotation invariant to iris image.
Iris images are compared in the identification and verification modes.
Provides shorter iris codes.
Computational complexity low in all phase.

REFERENCES
J.Daugman, ”High confidence visual recognition of persons by a test of statistical independence ”,IEEE Trans. Inform. Forensics and Security vol1,no.2,pp.125-143,jun 2006.
“Probing the uniqueness and randomness of iris codes:results from 200billion iris pair comparisons”, proc. IEEE,vol.94,no.11,pp.1927-1935,nov 2006.
Vladan Velisavljevic,””Directionlets:Anisotropic multi-directional representation with seperable filtering”, IEEE trans. Image processing, vol.15,no.7,pp.1916-1933,jul 2006.
S. Mallat, “Zero-crossings of a wavelet transform,” IEEE Trans. Inform. Theory, vol. 37, no. 4, pp. 1019–1033, Jul. 1991.
K. Miyazawa, K. Ito, T. Aoki, K. Kobayashi, and H. Nakajima, “An effective approach for iris recognition using phase-based image
matching,” IEEE Trans. Pattern Anal. Machine Intell., vol. 30, no. 10, pp. 1741–1756, Oct. 2008.