Discusses a novel neural network architecture for use in image representation and processing. In general methods for using neural networks for image processing have been largely derived from the use of conventional techniques. The neural network demonstrated in this paper, however, provides a new way of abstracting and consequently processing the image data. This is achieved by treating the image as a two-dimensional surface and training a network to learn an approximation to the parametric equation which describes this surface. To achieve this goal an image approximation neural network is proposed. This network has a modular architecture to allow the encoding and integration of several separate image regions. A technique for using IAN networks to perform affine image processing operations quickly and in a scale independent manner is derived and demonstrated.<>
Image processing using an image approximation neural network
Proceedings of 1st International Conference on Image Processing ; 3 ; 912-916 vol.3
1994-01-01
421817 byte
Conference paper
Electronic Resource
English
Image Processing using an Image Approximation Neural Network
British Library Conference Proceedings | 1994
|Image signal processor, image processing device and neural network image processing system
European Patent Office | 2020
|Application of Neural Network in Image Processing
British Library Online Contents | 2003
|