A cellular neural network framework for shape representation and matching

A framework to represent target shapes and extract them from distorted images is proposed and its potential is demonstrated by some basic computer simulations. The proposed system consists of an array of cells. Each of the cells contains a neural network describing a template shape and a set of parameters for the affine transformation of the template shape. During the template shape learning phase, the connection weights of the neural network are trained so that an approximation is obtained for the template shape. In the shape matching phase, an additional layer which stores a set of affine parameters is used. With the rest of the connection weights fixed, the affine parameters are updated by a backpropagation-based algorithm so that the best shape matching is obtained. It is confirmed that the neural network is effective for shape representation and the cellular neural network locates target shapes with accurate poses in sample images.

[1]  Anil K. Jain,et al.  Object Matching Using Deformable Templates , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Lilly Spirkovska,et al.  Higher-order neural networks applied to 2D and 3D object recognition , 1994, Machine Learning.

[3]  L.O. Chua,et al.  Cellular neural networks , 1993, 1988., IEEE International Symposium on Circuits and Systems.

[4]  A. Ardeshir Goshtasby,et al.  Curve Fitting by a Sum of Gaussians , 1994, CVGIP Graph. Model. Image Process..

[5]  James S. Duncan,et al.  Parametrically deformable contour models , 1989, Proceedings CVPR '89: IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[6]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Dana H. Ballard,et al.  Generalizing the Hough transform to detect arbitrary shapes , 1981, Pattern Recognit..

[8]  Pau-Choo Chung,et al.  Polygonal approximation using a competitive Hopfield neural network , 1994, Pattern Recognit..