Handbook of Computational Sciences

10Handwritten Character Recognition and Genetic Algorithms

Magesh Kasthuri¹* and Vigneshwar Manoharan²

¹Wipro Limited, Bengaluru, India

²R & D and Academic Initiatives, CBAS Corp, India

Abstract

Handwriting recognition principally entails optical character recognition. However, a complete handwriting recognition system also handles formatting, performs correct segmentation into characters, and finds Offline character recognition. The field of character recognition is classified into Online and offline recognition based on the way recognition is carried out. Off-line handwriting recognition involves the automatic conversion of text in an image into letter codes, which are usable within computer and text-processing applications. The data obtained by this form can be regarded as a static representation of handwriting. Off-line handwriting recognition is comparatively difficult, as different people have different handwriting styles. There are two major techniques and devices in this regard called OCR and ICR. OCR, which is termed Optical Character Recognition, is based on a legacy model where character recognition is based on optical scanning. ICR, which is termed Intelligent Character recognition, is a modern engine, which has a different pattern of character recognition including but not limited to handwritten character recognition. In addition, as of today, OCR engines are primarily focused on machine-printed text, and ICR is for hand “printed” text. Though there are many OCR/ICR ...