Paper Title

Performance Evaluation of Fuzzy Logic and Back Propagation Neural Network for Hand Written Character Recognition

Authors

Heba M. Abduallah and Safaa S. Mahdi

Abstract

Fuzzy c-mean is one of the efficient tools used in character recognition. Back propagation neural network is another powerful that may be used in such field. A comparison between fuzzy c-mean and BP neural network classifiers are presented in this research to obtain the performance of both classifiers. The comparison was based on recognition efficiency; this efficiency was evaluated as the ratio of the number of assigned characters with unknown one to the number of character set related to that character. The fuzzy C-mean and BP neural network algorithms were tested on a set of hand written and machine printed dataset named Chars74K dataset using Matlab (2016 b) programming language and the result was that neural network classifier gave 82% recognition efficiency while fuzzy c –mean gave 78%. Neural network classifier is more superior than fuzzy C-mean in recognition due to the limitations of processing time of fuzzy C-mean that requires smaller image size and eventually this will cause less efficiency.

Keywords

Fuzzy c-mean, character recognition, Back propagation neural network, recognition efficiency & Chars74K dataset 

Volume Url

https://airccse.org/journal/ijesa/current2018.html

Pdf Url

https://wireilla.com/papers/ijesa/8418ijesa02.pdf