Bengali handwritten character recognition using modified syntactic method
Mohammad Badiul Islam, Mollah Masum Billah Azadi, Md. Abdur Rahman, M. M. A. Hashem · QUT ePrints (Queensland University of Technology) · 2005
Several approaches have been proposed to recognize handwritten Bengali characters using different curve fitting algorithms and curvature analysis. In this paper, a new algorithm (Curve-fitting Algorithm) to identify various strokes of a handwritten character is developed. The curve-fitting algorithm helps recognizing various strokes of different patterns (line, quadratic curve) precisely. This reduces the error elimination burden heavily. Implementation of this Modified Syntactic Method demonstrates significant improvement in the recognition of Bengali handwritten characters.