A general purpose model for image operations based on multilayer perceptrons

In this paper, we investigate the use of multilayer perceptrons with recurrent connections as the general purpose modules for image processing in parallel architectures. The networks are trained to carry out classification rules in image transformation. The training patterns can be derived from user-defined transformations or from loading the pair of a sample image and its target image when the prior knowledge of transformations is unknown. Applications of our model include image smoothing, enhancement, edge detection, noise removal, morphological operations, image filtering, etc. With a number of stages stacked up together we are able to apply a series of operations on the image. That means, by providing various sets of training patterns the system can adapt itself to the concatenated transformation. Besides, recurrent connections from output of the last stage to input of the first stage allow a repeated sequence of operations to be used.