Image Recognition using Bidirectional Associative Memory and Fuzzy Image Enhancement

Abstract

This paper presents image classification and recognition with the help Fuzzy Logic (FL) model and Artificial Neural Network that exploits two techniques FIE and BAM. The proposed FIE and BAM model uses FIE to remove impulsive and smooth non impulsive noise, and to enhance the edges or other salient structures in the input image. After that the image is provided to the BAM to classify and recognize an input vector. The BAM is to store pattern pairs so that when n-dimensional vector is presented as input, the BAM recalls mdimensional vector Y, but when Y is presented as input, the BAM recalls X, also this model allows besides correct recall of noisy patterns, perfect recall of all trained patterns, with no ambiguity and no conditions. The FIE and BAM model has been prepared in MATLAB platform. The paper evaluates the effectiveness of the model.