Ear Recognition System using Radon Transform and Neural Network

摘要

Ear recognition system is one among the many evolving cutting edge technologies in the field of security surveillance. This paper presents an ear recognition system based on the Radon transform combined with Principal Component Analysis (PCA) for feature extraction, and integration of Multi-class Linear Discriminant Analysis (LDA) and Self -Organizing Feature Maps (SOM) for classification. Radon transform is used to extract the directional features of an image by projection of an image matrix for different orientations. The experimental result shows that the verification of an ear recognition system tested on two different public ear databases is accurate and speed.