Invariant 2D object recognition using the modulus maxima of a continuous wavelet transform.
Mahmoud I. Khalil, Mohamed M. Bayoumi · NSIP · 1999
In this paper, a technique is proposed to recognize 2D objects under translation, rotation, and scale transformation. The technique is based on the continuous wavelet transform and neural networks. Experimental results are presented and compared with traditional methods. The experimental results showed that this re ned technique was successfully capable of classifying the objects and that it outperformed some traditional methods especially in the presence of noise.