Modified Hybrid Feature Set for Assamese Character and Anglo-Assamese Hand Written Numeral Recognition
Kandarpa Kumar Sarma · International journal of imaging and robotics · 2008
Neural numeral recognition in two different languages as an extension of an Optical Character Recognition (OCR) system requires a unique feature set capturing relevant details of the input profiles. The performance of such a recognition system both during training and testing depends on the feature set. The work deals with the design of a combined character and numeral recognition system using a hybrid feature set applied earlier to the recognition of Assamese characters. The work also deals with the use of a modified version of this hybrid feature set derived for handwritten numeral recognition of two languages namely Assamese and English using a neural network. The set aims to maximize recognition performance, improve robustness and invariance to shape and size in presence of noise.