Iris Recognition System Based on Feature Level Fusion.

Multibiometric systems utilize the evidence presented by multiple biometric sources (e.g., face and fingerprint, multiple fingers of a single user, multiple matchers, etc.) in order to determine or verify the identity of an individual. Information from multiple sources can be consolidated in several distinct levels. But fusion of two different biometric traits are difficult due to (i) the feature sets of multiple modalities may be incompatible (e.g., minutiae set of fingerprints and eigen-coefficients of face); (ii) the relationship between the feature spaces of different biometric systems may not be known; (iii) concatenating two feature vectors may result in a feature vector with very large dimensionality leading to the `curse of dimensionality problem, huge storage space and different processing algorithm. Also if we are use multiple images of single biometric trait, then it doesn’t show much variations. So in this paper, we present a efficient technique of feature-based fusion in a multimodal system where left eye and right eye are used as input. Iris recognition basically contains iris location, feature extraction, and identification. This algorithm uses canny edge detection to identify inner and outer boundary of iris. Then this image is feed to Gabor wavelet transform to extract the feature and finally matching is done by using indexing algorithm. The results from the analysis of works indicate that the proposed technique can lead to substantial improvement in performance.