Object recognition using B-Spline wavelets

An algorithm based on the dyadic B-Spline wavelet transform to recognise planar objects under a similarity transformation (translation, rotation and scaling) is presented. The algorithm consists of two stages: constructing the representation and the matching process. The representation is a set of curvature waveforms of an object contour viewed at different resolution levels. In the matching procedure, only extrema on the representation are used. This makes the process efficient and less sensitive to small variations on the representation. Experimental results show that the representation is robust and, combined with the matching algorithm, it efficiently classifies unknown objects.