期刊名称：International Journal of Computer Science & Technology
印刷版ISSN：2229-4333
电子版ISSN：0976-8491
出版年度：2013
卷号：4
期号：1
页码：109-110
语种：English
出版社：Ayushmaan Technologies
摘要：Recognition of Devanagari numerals is a difficult task.Extensive research has been done on character recognition in the last few decades.In optical character a numeral, character or symbol to be recognized can be machined printed or handwritten character or numeral. There are several approaches that deal with the study of handwritten Devanagari numerals depending on the type of feature extracted and different way of extracting them. In this paper, a new is used for recognition of handwritten Devanagari characters. We explain the segmentation, feature extraction, water reservoir method, and neural network techniques. Feature extraction provides 92% accuracy of numeral recognition; water reservoir provides 94.34% accuracy. We also discuss various problems exist in numeral recognition.
关键词：Segmentation;Handwritten Character;Numeral Recognition; Water Reservoir
