A new method to recognize objects by means of multiscale features and Hopfield neural networks is proposed in this paper. The feature vector consists of the multiscale wavelet transformed extremal evolution. The evolution contains the information of the contour primitives in a multiscale manner, which can be used to discriminate dominant points, hence a good initial state of the Hopfield network can be obtained. Such good initiation enables the network to converge more efficiently. A new normalization scheme, wavelet normalization, was developed to make our method scale invariant and to reduce the distortion resulting from normalizing the object contours. The Hopfield neural network was employed as a global processing mechanism for feature matching. The Hopfield network was modified to guarantee unique and more stable matching results. A new matching evaluation scheme, which is computationally efficient, was proposed to evaluate the goodness of matching. Images of industrial tools were used to test the performance of the proposed method under noisy, occluded and affine conditions. Experimental results have shown that our method is robust and more efficient than the Mokhtarian-Mackworth's method.
All Science Journal Classification (ASJC) codes
- Control and Systems Engineering
- Signal Processing
- Computer Vision and Pattern Recognition
- Electrical and Electronic Engineering