AI Based Character Recognition

Nimish Kumar


Abstract- In this paper we propose an approach for recognizing an English alphabet using their structural features. One of its major applications is Optical Character Recognition (OCR). Scanners produce bitmap images of the documents which are not edited by word processors. Rather than trying to match a bitmap to the stored letters, feature extraction attempts to recognize letters by condensing the scanned letters to their basic "Features" which are compared to a list of features stored in the program's code. To convert a .BMP file into equivalent text file we need to process the file. The whole paper consists of reading bitmap file and marking blocks, thinning the available bitmap block, extracting the feature points from the bitmap block along with their approximate position in the block, checking if there are circles or some enclosed regions in the bitmap and matching the feature points with ideal feature point set of each alphabet and if it matches with any one of them then recognizes the bitmap block as that character. The experimental results show improvement as it verifying most of the characters.


Keywords- Feature Extraction, Optical Character Recognition (OCR), Bit Map Images, Thinning, Pattern Matching.

Full Text:



  • There are currently no refbacks.

Subscribe to Print Journals

 IJAIKD is currently Indexed By  Journal Seek