A Novel Ear Recognition Process Using Appearance Shape Model, Fisher Linear Discriminant Analysis and Contourlet Transform

Biometric authentication using ear images becoming popular nowadays in the field of security surveillance to identify a person. In this paper image processing techniques are used to study about the characteristics of several databases Ear images and to extract the features and data's from that Ear images. Ear is a stable biometric its appearance will not change even for long years. This paper explained about Contourlet transform and Appearance shape model (ASM) for feature extraction and, Fisher linear discriminant analysis (FLDA) is done for classification, ear matching. Here the feature extraction was done by both the Transform and Appearance shape model methods, So that the feature extraction result must be good. The proposed method has been evaluated on IIT Delhi Ear database of 50 Ear images from 10 persons and also tested on our own ear databases that are collected using webcam. The experimental results indicate that contourlet transform improves the overall performance when compared to Principal component analysis. The comparisons between the two feature extraction methods were done and its results were shown.