Performance enhancement of the pattern recalling efficiency of Hopfield neural network using genetic algorithm for cursive handwritten character recognition
Sonal Bansal, Rinku Sharma Dixit · International Journal of Applied Pattern Recognition · 2016
In this paper, we are describing the implementation of recalling cursive handwritten characters extracted through a series of segmentation steps performed on a cursive handwritten sentences done using Hopfield neural network and genetic algorithm (GA). The feature extraction has been performed using segmentation algorithm. A novel algorithm for handwriting segmentation has been proposed to get isolated characters as patterns. These patterns are stored in Hopfield neural network using Hebbian learning rule and the recalling is done using Hopfield neural network and evolutionary algorithm. GA is an evolutionary algorithm and is used to enhance the pattern recalling efficiency of Hopfield networks. The observation made from the simulated results is that our segmentation algorithm segments the word image into characters. Later on, these characters will be fed into Hopfield neural network for the pattern recognition. The recall efficiency of the Hopfield neural network can be sufficiently enhanced when supported with GAs.