Optical character recognition: A comprehensive study of hybrid methods

Article type: Research Article

Authors: Sharma, Abhishek A.^{; *} | Sane, Madhavi H. | Gandhe, Sanjay T.

Affiliations: Sardar Patel Institute of Technology Munshi Nagar, Andheri West, Mumbai – 400062, India

Correspondence: [*] Corresponding author. Tel.: +91 98 33214483; Fax: +91 22 28771665; E-mail: [email protected]

Abstract: The problem of Optical Character Recognition (OCR) is methodically treated in this paper. The paper discusses some traditional methods like template matching and neural networks that are employed by the more advanced and artificially intelligent systems. Though K-PCA, a non-intelligent system, provides better accuracy, it was found to occur at the cost of more processing time. Neural Networks provide a trade-off between processing time and accuracy.

DOI: 10.3233/KES-2011-0225

Journal: International Journal of Knowledge-based and Intelligent Engineering Systems, vol. 15, no. 4, pp. 247-254, 2011