Analysis of Pattern Storage Network with Simulated Annealing for Storage and Recalling of Compressed Image Using SOM

Abstract

In this paper, we are analyzing the SOM-HNN for storage and recalling of fingerprint images. The feature extraction of these images is performed with FFT, DWT, and SOM. These feature vectors are stored as associative memory in Hopfield Neural Network with Hebbian learning and Pseudoinverse learning rules. The objective of this study is to determine the optimal weight matrix for efficient recalling of the memorized pattern for the presented noisy or distorted and incomplete prototype patterns from the Hopfield network using Simulated Annealing. This process minimizes the effect of false minima in the recalling process.