期刊名称：International Journal of Advanced Research In Computer Science and Software Engineering
印刷版ISSN：2277-6451
电子版ISSN：2277-128X
出版年度：2012
卷号：2
期号：5
出版社：S.S. Mishra
摘要：In th is pa per, characte r re cogni tion syste m is impl emen ted u sing artificial neural ne tworks. A data base of printe d En glish alphabet characters is prepared. The characte rs are scanned an d pre-process ed to remove noise and enh ance the quality of images. The enhan ced character images are thresholded, skele tonized and p rune d so as to get final segmente d ch aracters of jus t one pixel lines. Suitable featu res based on geometry of ch aracters are extracted from the segmen ted ch aracter i mage s. These features are used to train th e multilayer back propagati on neural network cl assifier. The network is trained with the help of Levenbe rg-Marqu ard t algori thm. The propose d ch aracter recognition system is then teste d on new unk nown samples of printe d ch aracters. The s ystem performed well and achie ved 93% accuracy rate.
