SYSTEM AND METHOD FOR ARABIC OMNI FONT WRITTEN OPTICA CHARACTER RECOGNITION

摘要

Optical character recognition system and method are disclosed for Arabic scripts. The system is based on Hidden Markov Models (HMM), an approach that has proven to be very successful in the area of automatic speech recognition. The system is divided into two subsystems, the trainer subsystem based on Hidden Markov Models (HMM) and the recognizer subsystem comprising a feature extractor (M4) providing a series of feature vectors to the vector quantizer module (M5) and using the Viterbi algorithm to recognize input bitmaps to output characters. The system uses a speciel histogram-based algorithm for lines & words decomposition.