Title :
Challenges in OCR of Devanagari documents
Author :
Kompalli, Suryaprakash ; Nayak, Sankalp ; Setlur, Srirangaraj ; Govindaraju, Venu
Author_Institution :
CEDAR, Univ. at Buffalo, Amherst, NY, USA
fDate :
29 Aug.-1 Sept. 2005
Abstract :
OCR of Devanagari script presents a wide range of challenges that are not seen in Latin based scripts. This paper outlines the implementation of a neural network based Devanagari OCR. Experimental results on a standard data set are reported and analyzed.
Keywords :
document handling; natural languages; neural nets; optical character recognition; Devanagari OCR documents; Latin based scripts; neural network; standard data set; Character generation; Character recognition; Frequency; Image segmentation; Neural networks; Optical character recognition software; Optical computing; Robustness; Software libraries; Venus;
Conference_Titel :
Document Analysis and Recognition, 2005. Proceedings. Eighth International Conference on
Print_ISBN :
0-7695-2420-6
DOI :
10.1109/ICDAR.2005.70
