Description

Iris based authentication system is essentially a pattern recognition technique that makes use of iris patterns, which are statistically unique, for the purpose of personal identification. In this study, a novel method for recognition of iris patterns is considered by using a combination of support vector machine and Hamming distance. The zigzag collarette area of the iris is selected for iris feature extraction because it captures the most important areas of iris complex pattern and higher recognition rate is achieved. The proposed approach also used parabola detection and trimmed Gaussian filter for the purpose of eyelid and eyelash detection & removal, respectively. Individual recognition using Iris is most commonly employed in all the place. This requires some special cameras to take the Iris image and the obtained iris images were classified based on the features extracted. Only identification of person is not the application of Iris recognition. It can be developed to do many process. In this process the race of the person is identified. Also the input iris is fake or original is also identified. The iris image captured from the cameras were taken. Some Iris recognition system fails because some of the recognition systems identifies the iris image in photos, also some of the recognition systems identifies the fake iris images generated by some attackers. An iris recognition system that identifies the fake iris images are much needed. The proposed iris recognition system identifies the fake and original iris images. In order to identify fake and original iris image SIFT descriptors were derived from the input iris images. Before this process the iris image is preprocessed by resizing the iris image and then filtering the iris image using Gaussian filter. The preprocessed iris image is then normalized. The normalization process identifies the iris and pupil region in the image correctly and it reshapes the identified positions. The normalization process improves the efficiency. The Gabor features identifies the corner points in the iris image and then the extracted points were used to generate the codebook. The code book generation processes is done using Hierarchical Visual Code book generation method. The input iris image is then identified to be fake or original, Asian or Non-Asian using Support Vector Machine classifier.