Publication Type : Book Chapter
Publisher : Springer-Verlag,
Source : Book Chap in Guide to OCR in Indic Scripts, Springer-Verlag, Springer London, London, p.97–124 (2010)
Url : https://doi.org/10.1007/978-1-84800-330-9_5
ISBN : 9781848003309
Campus : Bengaluru
School : Department of Computer Science and Engineering, School of Engineering
Department : Computer Science
Year : 2010
Abstract : India is a land of many languages and consequently one often encounters documents that contain elements in multiple languages and scripts. This chapter presents an approach towards designing a bilingual OCR that can process documents containing both English and Kannada scripts which are used by the Kannada language of the southern Indian state of Karnataka. We report an efficient script identification scheme for discriminating Kannada from Roman script. We also propose a novel segmentation and recognition scheme for Kannada, which could possibly be applied to many other Indian languages as well.
Cite this Research Publication : R. S. Umesh, Peeta Basa Pati, and Ramakrishnan, A. G., “Design of a Bilingual Kannada–English OCR”, in Book Chap in Guide to OCR in Indic Scripts, Springer-Verlag, V. Govindaraju and Setlur, S. (Ranga), Eds. London: Springer London, 2010, pp. 97–124.