Off-line constrained vocabulary cursive script recognition using visible features

Abstract

This paper presents a model for off-line cursive script recognition. The method proposed combines both analytical and holistic approaches to solve the problem of cursive script recognition. The emphasis is to create a fast and reliable model for recognition. The holistic approach of extracting feature is used with the analytical approach of segmenting and recognizing the first character. Pre-processing, feature extraction, classifier, and phrase recognition are explained and used in this system. Results from a test set of 1294 images are presented based on three different word recognition methods that are experimented. This system is being used as a system to sort mails that are directed overseas, however, it can also be used for other requirements like word spotting in unconstrained text.