Feature Extraction of Gurmukhi Script and Numerals: A Review of Offline Techniques

Offline Isolated handwritten Gurmukhi character recognition has been a very intensive area of research during last decades due to it is wide range of solution to real world problems. A lot of work has been done in languages like Chinese, Arabic, Devnagari, Urdu and English (1-3). Research on the different stages of OCR of Gurmukhi script is being carried out by the authors and their M.Tech students at Punjabi University, Patiala. A preliminary work was done by Sanjeev Kumar (4) and Khushwant Kaur (5) under the guidance of one of the authors, Lehal, developing a feature based Gurmukhi recognition script system. The count and location of local features such as endpoints, T-points, cross points and loops were used to identify isolated Gurmukhi characters A neural networks based Gurmukhi recognition system has been developed by Goyal et.al. (6). Range free skew detection algorithms for de-skewing Gurumukhi machine printed text skewed at any angle, have been developed by Lehal and Madan (7) and Lehal and Dhir (8). If different classifiers cooperate with each other, group decisions may reduce errors drastically and achieve a higher performance. In this survey, focuses on the various techniques used for recognition of isolated offline handwritten characters in Gurmukhi script. The whole process consists of two stages. The first, feature extraction stage analyzes the set of isolated characters and selects a set of features that can be used to uniquely identify characters. The performance depends heavily on what features are being used.