An Efficient Invariant Image Recognition Methodology using Wavelet Compressed Zernike Moments Denoised through Self Organizing Maps

Abstract

A new method for extracting feature sets with improved classification performance in image recognition applications is presented in this paper. The main idea is to propose a procedure for obtaining surrogates of the compressed versions of reliable and denoised feature sets without affecting significantly their reconstruction and recognition properties. The surrogate feature vector is of lower dimensionality and thus more appropriate for pattern recognition tasks. The proposed feature extraction method (FEM) combines the advantages of the multiresolution analysis, which is based on the wavelet theory, with the high discriminative nature of Zernike moment sets and the denoising features of Self Organized Topological Maps (SOM). The resulted feature vector is used as a classification feature, in order to achieve high recognition rates in a typical pattern recognition system. The results of the experimental study support the validity and the strength of the proposed method.