Tolerance of Pattern Storage Network for Storage and Recalling of Compressed Image using SOM

In this paper we are studying the tolerance of Hopfield neural network 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. This study also explores the tolerance in Hopfield neural network for reducing the effect of false minimas in the recalling process. Besides this the capabilities of learning rules for pattern storage is also analyzed. This study also exhibits the analysis as pattern storage networks for feature vectors obtained from SOM with FFT and DWT