期刊名称：International Journal of Advanced Research in Computer Engineering & Technology (IJARCET)
印刷版ISSN：2278-1323
出版年度：2014
卷号：3
期号：9
页码：3138-3142
出版社：Shri Pannalal Research Institute of Technolgy
摘要：It is observed that the text extraction suffers from the drawback of size and rotation of the text appeared on the images and the scanning device has to be focused on the textual area of the image. This engages the person using the application software. However, this can be automated if the algorithm is designed in way so as to identify the text area on the image either at some orientation or at different sizes. In this paper an algorithm is proposed which can very effectively extract characters from the image, irrespective of the size, rotation and font of the character. The system is first trained using extracted features of each character and then the system is tested, if the system properly identify all the characters no further training is required otherwise the system is trained again.
关键词：Character Recognition; Feature Extraction; ; Neural Network; Back propagation
