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 thi s manuscript handwritten Gurmu khi character recognition for isolated characte rs is proposed. We have use d Gabor Filter base d me thod for featu re extraction. Our database cons ists of 200 samples of each of bas ic 35 characte rs of Gurmukh i s cript collected from diffe rent write rs. These samples are pre -process ed an d normal ized to 32*32 sizes . Th e highest accu racy obtai ned is 94.29% as 5-fold cross validation of wh ole database with S VM classifier used with RBF kernel.
关键词：OCR; Is olate d Handwritte n Gurmu khi Characte r Re cogn ition; Gabor Featu res; Gabor Fi lters; S VM
