Spatio partitioning of character image for automatic recognition of digits

Abstract

In the running word, there is growing demand for the software systems to recognize characters in computer system when information is scanned through paper documents as we have number of newspapers and books which are in printed format related to different subjects the current capacity to translate paper documents quickly and accurately into machine readable form using optical character recognition technology augments the opportunities in document searching and storing as well as automated documents processing. A fast response in translating large collections of image-based electronic documents into structured electronics documents is still a problem. As an enhancement to the optical character recognition [1] (OCR) technology, I would like to propose a framework that recognize a printed digits in the character image using “spatio partitioning method”. The proposed system is efficiently recognize the digits from 0 to 9 different font size based on the new concept of feature extraction and which is classified under decision tree classifier, efficiency and time complexity of the proposed system also described. Partitioning is based on the pixel distribution of the character image; the pixel distribution describes the patter of the characters that is by spatially distributed foreground pixel.