Abstract—This paper presents a method to recognize online handwritten Gurmukhi characters. Gurmukhi is the script of Punjabi language which is widely spoken across the globe. The proposed method is called small line segments and based on idea of chain code and elastic matching techniques. Using this method, we have obtained an overall recognition rate of 94.59%for a set of 2460 Gurmukhi characters collected from 60 writers. In recognizing a single stroke, the average speed using this method is approximately 0.156 seconds.
Index Terms—Online handwriting recognition, preprocessing, Feature extraction, chain code, elastic matching.
Anuj Sharma is with the Center for Advanced Study in Mathematics, Panjab University, Chandigarh (INDIA).
Dr. R. Kumar is with the School of Mathematics and Computer Applications, Thapar University, Patiala (INDIA).
Prof. R. K. Sharma is with the School of Mathematics and Computer Applications, Thapar University, Patiala (INDIA).
[PDF]
Cite: Anuj Sharma, R. Kumar and R. K. Sharma, "Recognizing Online Handwritten Gurmukhi Characters using Comparison of Small Line Segments," International Journal of Computer Theory and Engineering vol. 1, no. 2, pp. 131-135, 2009.
Copyright © 2008-2024. International Association of Computer Science and Information Technology. All rights reserved.
