Embedding Gravitational Search Algorithms in Convolutional Neural Networks for OCR applications

Abstract

This paper presents aspects concerning embedding Gravitational Search Algorithms (GSAs) in Convolutional Neural Networks (CNNs) for Optical Character Recognition (OCR) systems. The GSAs are used in combination with the Back Propagation (BP) algorithm as optimization algorithms in the training process of a specific CNN architecture for OCR applications. The new algorithm consists of applying first the GSA and next the BP in order to ensure performance improvements by avoiding the algorithms' traps in local minima. A performance analysis for a given benchmark application shows the advantages of our algorithm over the classical BP algorithm for a six layer CNN dedicated to OCR applications.