Invariant 2D object recognition using the wavelet modulus maxima

Abstract

In this paper, a technique is proposed to recognize 2D objects under translation, rotation, and scale transformations. The technique is based on the continuous wavelet transform and neural networks. Experimental results are presented and compared with some traditional methods. The experimental results showed that this refined technique was successful in classifying the objects under consideration and that it outperformed those traditional methods especially in the presence of noise.