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：2013
卷号：3
期号：11
出版社：S.S. Mishra
摘要：Human can understand the problem of recognition well by visualising but machine of today are not par with this skill of the machine or computer. But as research is going on day by day there is need of the efficient machine recognition system like cursive handwriting detection. In this paper we are dealing with the unique method to identify cursive handwriting detection using artificial neural network (ANN). We use deterministic approach for this problem using artificial neural network. Principle component analysis (PCA) is used for feature extraction of the input cursive handwritten words by 5 people of which 10 samples for ea ch individual tested. Artificial neural network the popular artificial intelligence technique is used for recognising the wa velet component cursive handwritten words. There is also a special error function for increasing the efficiency of the system which enhances accuracy from 76% to 82% .Matlab 7.10 is used for the simulation of the object. In this paper we are dealing with t he words directly instead of characters like in optical character recognition (OCR).
