Character recognition with fuzzy features and fuzzy regions
Document Type
Conference Proceeding
Publication Date
12-1-1997
Abstract
We propose a method for character recognition using fuzzy features and fuzzy regions in a neural network. The method is robust to noise and distorting, scaling, and shifting of the patterns within their pixel frames, yet it is mathematically simple. The fuzzy neural network presented in this paper consists of three layers: A layer for feature extraction, for regional emphasis of features, and for classification. We extract features from regions of the characters in which they are most likely to occur. To make the system robust, these regions are fuzzified, giving higher weight to areas where the features are most likely to occur and lower to areas where the features are rare. Sample patterns from the literature have been used for training of the network to obtain the minimal set of distinguishing features with their associated measures and to determine the optimal slopes of these linear regions. The network has been tested using patterns from the literature. Its performance is comparable for distorted and noisy patterns and superior for shifted, partial, and down-scaled samples.
Publication Source (Journal or Book title)
Annual Conference of the North American Fuzzy Information Processing Society - NAFIPS
First Page
166
Last Page
171
Recommended Citation
Mertooetomo, E., & Chen, J. (1997). Character recognition with fuzzy features and fuzzy regions. Annual Conference of the North American Fuzzy Information Processing Society - NAFIPS, 166-171. Retrieved from https://repository.lsu.edu/eecs_pubs/2423