Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 2 of 2
Full-Text Articles in Engineering
Parallel Image Segmentation Using A Hopfield Neural Network With Annealing Schedule For Neural Gains, Yungsik Kim, Sarah A. Rajala
Parallel Image Segmentation Using A Hopfield Neural Network With Annealing Schedule For Neural Gains, Yungsik Kim, Sarah A. Rajala
Sarah A. Rajala
Neural network architectures have been proposed as new computer architectures and a Hopfield neural network has been shown to find good solutions very fast in solving complex optimization problems. It should be noted, however, that a Hopfield neural network with fixed neural gains only guarantees to find local optimum solutions, not the global optimum solution. Image segmentation, like other engineering problems, can be formalized as an optimization problem and implemented using neural network architectures if an appropriate optimization function is defined. To achieve a good image segmentation, the global or the nearly global optimum solutions of the appropriate optimization function …
Optimum Displacement Estimates Using Mean Field Annealing, Ikhlas M. Abdelqader, Sarah A. Rajala, Griff L. Bilbro, Wesley E. Snyder
Optimum Displacement Estimates Using Mean Field Annealing, Ikhlas M. Abdelqader, Sarah A. Rajala, Griff L. Bilbro, Wesley E. Snyder
Sarah A. Rajala
In this paper a new algorithm to estimate dense displacement fields from a sequence of images is developed. The algorithm is based on modeling the displacement fields as Markov Random fields. The Markov Random fields-Gibbs equivalence is then used to convert the problem into one of finding an appropriate energy function that describes the motion and any constraints imposed on it. Mean field annealing, a technique which finds global minima in nonconvex optimization problems, is used to minimize the energy function, and solve for the optimum displacement fields. The algorithm results in accurate estimates even for scenes with noise or …