Title :
Symbolic representation of Kannada characters for recognition
Author :
Vikram, N.T. ; Gowda, K. Chidananda ; Urs, Shalini R.
Author_Institution :
Int. Sch. of Inf. Manage., Mysore
Abstract :
Kannada is a south Indian language, and one of the official languages of India. In this paper we propose a novel character representation scheme based symbolic data analysis, with Kannada as a case study. Symbolic data analysis (SDA) is a new domain in data management and knowledge discovery. SDA based methods have not been exploited for OCR of now. The proposed representation scheme is efficient in capturing the variations in font style and invariant to size. We also propose a similarity measure for recognition purpose.
Keywords :
data analysis; natural language processing; optical character recognition; Kannada character recognition; OCR; south Indian language; symbolic data analysis; symbolic representation; Character recognition; Data analysis; Discrete cosine transforms; Image segmentation; Knowledge management; Optical character recognition software; Pattern recognition; Principal component analysis; Support vector machine classification; Support vector machines;
Conference_Titel :
Networking, Sensing and Control, 2008. ICNSC 2008. IEEE International Conference on
Conference_Location :
Sanya
Print_ISBN :
978-1-4244-1685-1
Electronic_ISBN :
978-1-4244-1686-8
DOI :
10.1109/ICNSC.2008.4525329
