Character Recognition Using Neural Network Learned by Artificial Bee Algorithm

Bassim Jumaa,Ayad Naser,Maryam Khalaf

doi:10.25195/ijci.v41i1.96

Bassim Jumaa, Ayad Naser + Show 1 more

Open Access

https://doi.org/10.25195/ijci.v41i1.96

Copy DOI

Abstract

Character Recognition is the text recognition system that allows hard copies of written or printed text to be renderedinto editable, soft copy versions. In this paper, work has been performed to recognize pattern using multilayer perceptronlearning by Artificial Bee algorithm (ABC) that simulates the intelligent foraging behavior of a honey bee swarm. MultilayerPerceptron (MLP) trained with the standard back propagation (BP) algorithm normally utilizes computationally intensivetraining algorithms. One of the crucial problems with the BP algorithm is that it can sometimes yield the networks withsuboptimal weights because of the presence of many local optima in the solutions space. The suggested method is to use ABC forlearn the Neural Networks, to solve text character recognition problem, by update the Neural Networks weights. A comparisonstudies are made between ABC and BP methods in NN learning to specify which is better in solving character recognitionproblem.

Highlights

Humans have developed highly sophisticated skills for sensing their environment and taking actions according to what they observe, e.g., recognizing a face, understanding spoken words, reading handwriting and distinguishing fresh food from its smell
Satish L., CH.V.Sarma[11],2013, proposed an efficient Hybrid Particle Swarm Optimization and Back prediction, pattern recognition, associative memories, classification, optimization and general mapping.= The back propagation learning algorithm can be divided into two phases: propagation and weight propagation algorithm to enhance the performance of Artificial update
The multi-layer perceptrons established for relevant purposes are trained with Artificial Bee Colony (ABC) algorithm and back propagation (BP) algorithm, respectively, through the selected training set

Summary

Introduction

Humans have developed highly sophisticated skills for sensing their environment and taking actions according to what they observe, e.g., recognizing a face, understanding spoken words, reading handwriting and distinguishing fresh food from its smell. Satish L., CH.V.Sarma[11],2013, proposed an efficient Hybrid Particle Swarm Optimization and Back prediction, pattern recognition, associative memories, classification, optimization and general mapping.= The back propagation learning algorithm can be divided into two phases: propagation and weight propagation algorithm to enhance the performance of Artificial update. 1. Forward propagation of a training pattern's input through the neural network in order to generate the propagation's output activations. 2. Backward propagation of the propagation's output activations through the neural network using the training pattern target in order to generate the deltas of all output and hidden neurons. The Artificial Bee Colony (ABC) algorithm is a swarm based meta-heuristic algorithm that was introduced by Karaboga in 2005 (Karaboga, 2005) for optimizing numerical problems It was inspired by the intelligent foraging behavior of honey bees. In order to calculate the fitness values of solutions we employed the following equation (eq 3):

The Artificial Bee Colony lgorithm

Fitness Criterion

Training the ANN by using ABC

Comparison Results between ABC and BP

Conclusions