The book is suitable for advanced courses in computer vision and image processing. In addition to providing an overall view of computational vision, it contains extensive material on topics that are not usually covered in computer vision texts (including parallel distributed processing and neural networks) and considers many real applications.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Distributed and Multiscale Representations
9 other sections not shown
Other editions - View all
active perception algorithm analysis and/or approach architecture Assume behavior characteristic cojoint cojoint representations complexity components computational vision concept conformal mapping consider constraints coordinates corresponding cytoarchitecture defined depth map derived difference of Gaussians discussed in Section distributed computation domain edge edge detection energy environment equation estimate example filter Fourier transform frequency function Gabor Gabor filters Gaussian geometric given global gradient graph heat equation image representations implemented input integration interpretation intrinsic invariant iterative Kalman filter Laplacian learning linear matching matrix memory methods minimization motion neural neurons nodes object recognition operator optical flow optimal orientation output paradigm parallel pattern PDP models pixels plane problem projection reprojection resolution result robot rotation sensory signal SIMD simulated annealing smoothing solution space spatial spatiotemporal specific spectrogram spectrum stimulus structure suggested surface task texture theory tion uncertainty vector velocity visual system Wigner distribution yields zero