Devanagari Character Recognition: A Short Review

Abstract

Optical character recognition is a vital task in the field of pattern recognition. English character recognition has been extensively studied by many researchers but in case of Indian languages which are complicated; the research work is very limited. Devanagari is an indian script used by huge number of indian people. Devanagari forms the basis for several indian languages including Hindi, Sanskrit, Kashmiri, Marathi and so on. This article presents a review of earlier research work related to devanagari character recognition along with some applications of optical character recognition system.

A Review of Handwritten Character Recognition

“…Local or adaptive threshold uses different values for each pixel according to the local area information [8]. In degraded document images, where considerable background noise or variation in contrast and illumination exists, there exist many pixels that cannot be easily classified as foreground or background.…”

“…Devnagari was originally developed for Sanskrit language; but then it was accepted to write many Indian languages like Hindi, Marathi, Nepali, Bhojpuri, Marwari, etc. [8]. Most of other North Indian scripts like Gujarati and Punjabi are inherited from Devnagari script.…”

“…Thus, it does not have any external information, thus making the recognition process difficult. Offline recognition may be used for printed or handwritten documents [8]. …”

“…On the basis of data acquisition techniques, OCR activity can be divided in two major categories: Online Optical Character Recognition and Offline Optical Character Recognition [8]. Offline method can further be divided in two sub categoriesPrinted and Handwritten.…”

Traditional Mongolian Script Feature Extraction based on Black Pixels in Bounding Box

“…For India script recognition some methods are proposed in [1][2][3]. For example, [3] discusses the various feature mining techniques and classifiers like power arc fitting, parabola arc fitting, diagonal feature extraction, transition feature extraction, K-NN classifier (K-nearest neighbor) and SVM classifier foroffline handwritten Gurmukhi character recognition.…”