Curve Matching and Character Recognition by Using B-Spline Curves

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.