期刊名称：International Journal of Image Processing (IJIP)
电子版ISSN：1985-2304
出版年度：2014
卷号：8
期号：4
页码：178-185
出版社：Computer Science Journals
摘要：This paper presents a research work in identification of script from trilingual Indian documents. This paper proposes a classification algorithm based on structural and contour features. The proposed system identifies the script of languages like English, Tamil and Hindi. 300 word images of the above mentioned three scripts were tested and 98.6% accuracy was obtained. Performance comparison with various existing methods is discussed.
