Devnagari Handwriting Recognition System using Dynamic Time Warping Algorithm

Abstract

Online handwriting recognition is gaining renewed interest owing to the increase of pen computing applications and new pen input devices. The recognition of Devnagari characters is different from western handwriting recognition and poses a special challenge. This paper is an overview of the technical status and the development in online Devnagari recognition system which starts few years back. The objective of this paper is to develop a system which can recognize a handwritten Devnagari character, written with the help of stylus or a digital pen. To develop the system, dynamic time warping (DTW) technique is considered. In dynamic time warping the entered character is processed in terms of time sequences x and y as a function of time. The time sequence of the character to be recognized is compared with that of all the characters stored in a code file. The distance between them is calculated. The character from the code file which gives minimum distance is considered as the recognized character. In order to improve the recognition rate, along with DTW algorithm, additional feature vectors can be used. In this paper, line extraction algorithm is developed.