Fitting models to distributed representations of vision

Authors:
Sourabh A. Niyogi
Affiliations:
Department of Electrical Engineering and Computer Science, MIT Media Laboratory, Cambridge, MA
Venue:
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 1
Year:
1995

Citing 11
Cited 0

Computational vision and regularization theory

Nature
Analyzing oriented patterns

Computer Vision, Graphics, and Image Processing
The Computation of Visible-Surface Representations

IEEE Transactions on Pattern Analysis and Machine Intelligence
The Design and Use of Steerable Filters

IEEE Transactions on Pattern Analysis and Machine Intelligence
Generic Neighborhood Operators

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Three-Frame Algorithm for Estimating Two-Component Image Motion

IEEE Transactions on Pattern Analysis and Machine Intelligence
Object discrimination based on depth-from-occlusion

Neural Computation
Distributed representation and analysis of visual motion

Distributed representation and analysis of visual motion
Steerable-Scalable Kernels for Edge Detection and Junction Analysis

ECCV '92 Proceedings of the Second European Conference on Computer Vision
Detecting kinetic occlusion

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Computing stereo disparity and motion with known binocular cell properties

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

Many representations in early vision can be constructed by performing orientation analysis along several sampling dimensions. Texture is often oriented in space, motion is oriented in space-time, and stereo is oriented in space-disparity. In these modalities, we can construct distributed representations with oriented energy measures used in models of biological vision. Surface models of orientation, velocity, and disparity can easily be fit to distributed representations of texture, motion, and stereo by combining tools of orientation analysis and regularization. We describe base representation construction and model fitting processes in these domains.