Downloads: 125
Research Paper | Computer Science Engineering | Volume 2 Issue 12, December 2013 | Pages: 157 - 161 | Bangladesh
Enhancing the Character Segmentation Accuracy of Bangla OCR using BPNN
Abstract: Bangla is one of the most popular scripts in the world, the second most popular language in the Indian subcontinent. About 200 million people of eastern India and Bangladesh use this language, making it fourth most popular in the world. We study and examine the various kinds of problems or limitations that arise during the segmentation of Bangla characters and try to minimize that problems or limitations. The main aim of this proposed research is to improving the character segmentation (line, word, and character segmentations) accuracy of Bangla Optical Character Recognition (OCR) system by using Artificial Neural Network as a Back Propagation Neural Network (BPNN) algorithm.
Keywords: Artificial Neural Network, character segmentation, line segmentation, optical character recognition, pre-processing, word segmentation
How to Cite?: Shamim Ahmed, Mohammod Abul Kashem, "Enhancing the Character Segmentation Accuracy of Bangla OCR using BPNN", Volume 2 Issue 12, December 2013, International Journal of Science and Research (IJSR), Pages: 157-161, https://www.ijsr.net/getabstract.php?paperid=02013559, DOI: https://dx.doi.org/10.21275/02013559