Abstract—This paper is devoted to presenting a novel algorithm for curve matching and character recognition. This algorithm is based on constructing and comparing B-spline curves of object boundaries. At first, the dominant points are calculated on the objects boundary by using Local Curvature Maximum (LCM), then, control points are obtained by using B-spline least square fitting technique. Curve matching and character recognition is done by comparing result B-spline curves. The result from proposed method shows good accuracy besides low computational complexity of proposed method for curve matching and character recognition.
Index Terms—B-Spline curves, curve matching, characterr ecognition, control points, parametric values.
Hamed Tirandaz is with the Mechatronics Engineering Department, Sabzevar Tarbiat Moallem University, Sabzevar, Iran,(e-mail: firstname.lastname@example.org.)
Abbas Nasrabadi is with the Mechatronics Engineering Department, Sabzevar Tarbiat Moallem University, Sabzevar, Iran (e-mail: email@example.com.)
Javad Haddadnia is with the Electrical Engineering Department, Sabzevar Tarbiat Moallem University, Sabzevar, Iran (e-mail: firstname.lastname@example.org).
Cite: H. Tirandaz, A. Nasrabadi, J. Haddadnia, "Curve Matching and Character Recognition by Using B-Spline Curves," International Journal of Engineering and Technology vol. 3, no. 2, pp. 183-186, 2011.