Optical Character Recognition of 10 × 10 Size Binary Images

Abstract

Ten binary images of size 10 × 10 for each of the decimal numbers from 0 to 9 are considered for the simulation setup. Applying different processing techniques on these images, information contents were extracted. Initially, no noise was added in these images and character recognition of 100% was obtained. After that, noise is added in these images (i.e., images were distorted) but even then 9 out of 10 images were successfully recognized. In other words, approximately 90% successful character recognition was obtained.

Keywords: Optical character recognition (OCR), Euclidean distance