A neural network model for selective attention in visual pattern recognition
Biological Cybernetics
A parallel approach to the picture restoration algorithm of Geman and Geman on an SIMD machine
Image and Vision Computing
Visual reconstruction
Parallel and distributed computation: numerical methods
Parallel and distributed computation: numerical methods
Integration of visual modules: an extension of the Marr paradigm
Integration of visual modules: an extension of the Marr paradigm
Massively parallel computing with the DAP
Massively parallel computing with the DAP
Introduction to the theory of neural computation
Introduction to the theory of neural computation
Parallel and Deterministic Algorithms from MRFs: Surface Reconstruction
IEEE Transactions on Pattern Analysis and Machine Intelligence
Robot Vision
Data Fusion for Sensory Information Processing Systems
Data Fusion for Sensory Information Processing Systems
Parallel Processing for Computer Vision and Display
Parallel Processing for Computer Vision and Display
Computer Vision
Visual Integration and Detection of Discontinuities: The Key Role of Intensity Edges
Visual Integration and Detection of Discontinuities: The Key Role of Intensity Edges
A Theory of Networks for Approximation and Learning
A Theory of Networks for Approximation and Learning
Advances in the cooperation of shape from shading and stereo vision
3DIM'99 Proceedings of the 2nd international conference on 3-D digital imaging and modeling
Hi-index | 0.00 |
The authors describe a neural network approach for combining processing of multiple early vision modules. Energy functions for coupling the computation of intensity contours, optical flow, and stereo disparity are defined. Hopfield neural networks are used for function minimization with deterministic annealing to avoid spurious local minima. Vision integration schemes are developed by extending the work of T.A. Poggio et al. (1988) to include cooperative interactions between different vision modules and the Hebbian adaptation of vision module coupling on a massively parallel computer consisting of 4096 processing elements operated in a single-instruction-multiple-data mode. Simple experiments assess the performance of various integration approaches. The resulting algorithms facilitate fast, robust image segmentation.