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：2930-2935
出版社：Shri Pannalal Research Institute of Technolgy
摘要：This paper presents a new improved technique on English OCR techniques. English OCR system is compulsory to convert numerous published books of English into editable computer text files. Latest research in this area has been able to grown some new methodologies to overcome the complexity of English writing style. Still these algorithms have not been tested for complete characters of English Alphabet. Hence, a system is required which can handle English text and identify characters. The propose algorithm is verified by considering various noises like salt and pepper, Gaussian and Poison and it found that proposed algorithm along with bilateral filter provide better results The proposed algorithm used templates and use correlation to match the letters. Developed algorithm is designed and implemented in MATLAB and tested on various images. The proposed strategy has achieved 97.3 % (average) accuracy which was 94.33 % in Huang and Lin (2012) [16].
