Optical Character Recognition of Bangla Characters using neural network: A better approach

This is a complete Optical Character Recognition system for printed Bangla text with a perspective of implementation. Suggestions have been made on the basis of the problems confronted in developing the software. This paper describes the efficient ways involving line and word detection, zoning, character separations and character recognition. Employing Skewness correction, thinning and better approach in scaling have obviously enhanced the performance of the OCR system in comparison with the existing ones. Application of neural network in detection of characters has made the process even faster with optimum performance.