|National Conference "MEDHA 2012"
|Foundation of Computer Science USA
|MEDHA - Number 1
|Authors: D. N. Besekar
D. N. Besekar . Special Approach for Recognition of Handwritten MODI Scripts Vowels. National Conference "MEDHA 2012". MEDHA, 1 (September 2012), 48-52.
The ambient study had been performed on foreign language like Arebic, chineses Japanese etc. efforts on India script is still immature. OCR of MODI script language is still not available as it is cursive type and old language i. e. Shivkalin and Peshwekalin. the challenges of recognition of character is even high in handwritten domain , due to the varying writing style of each individual. In this paper we propose a system for recognition of offline handwritten MODI script Vowels. the proposed method uses chain code and image centroid for the purpose of extracting features and a two layer feed forward network with scaled conjugate gradient for classification.