Recognition of Off-line Modi Script : A Structure Similarity Approach
Abhinav Ramteke, Girish Katkar · 2013
The subject of character & handwriting recognition has a great potential in data and has received considerable attention in recent years. Several methods for recognition of Latin, Chinese, and Arabic etc. scripts have been proposed. Among Indian script, some pioneering work has been done on Bengali, Devnagiri, Oriya, Telugu, Urdu scripts and OCR systems for this script are ready for commercialization. Modi script is a cursive typescript of Devnagiri characters. Two major differences between the alphabets and cursive characters can be stated. Cursive script recognition has the context information in a one dimensional way, but graphical alphabets usually are bi-dimensional.In this paper, some structural similarities of standard characters and handwritten characters in Modi script are verified using measured structure similarity approach. The performance rate is found to be 91 to 97 percent which is more promising than other methods.