期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2013
卷号：2
期号：12
页码：3105-3110
出版社：Shri Pannalal Research Institute of Technolgy
摘要：Handwritten character recognition is constantly a frontier area of study in the field of pattern recognition and image processing and there is a large requirement for OCR on hand written credentials. Even though, adequate studies have performed in foreign scripts like Chinese, Japanese and Arabic characters, simply a very little work can be traced for handwritten disposition recognition of Indian scripts particularly for the South Indian scripts. A hybrid HMM/ANN (Hidden Markov Model/ Artificial Neural Network) system for recognizing unconstrained offline handwritten text lines has been proposed by Salvador Espanaet. Al [13]. The key features of the recognition system are the novel approach to pre- processing and recognition, which are both based on ANNs. The pre-processing is based on using MLPs (Multilayer Perceptron): To clean and enhance the images, to automatically classify local extreme in order to correct the slope and to normalize the size of the text line images, and to perform a non uniform slant correction. The recognition is based on hybrid optical HMM/ANN models, where an MLP is used to estimate the emission probabilities. In this paper Multilayer Perceptron model is applied to handwritten TELUGU script.
