Trace Inference, Curvature Consistency, and Curve Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
The Design and Use of Steerable Filters
IEEE Transactions on Pattern Analysis and Machine Intelligence
1994 Special Issue: Putative strategies of scene segmentation in monkey visual cortex
Neural Networks - Special issue: models of neurodynamics and behavior
Local parallel computation of stochastic completion fields
Neural Computation
A neural model of contour integration in the primary visual cortex
Neural Computation
A Comparison of Measures for Detecting Natural Shapes in Cluttered Backgrounds
International Journal of Computer Vision - Special issue on computer vision research at NEC Research Institute
Orientation, scale, and discontinuity as emergent properties of illusory contour shape
Proceedings of the 1998 conference on Advances in neural information processing systems II
Invertible Orientation Bundles on 2D Scalar Images
SCALE-SPACE '97 Proceedings of the First International Conference on Scale-Space Theory in Computer Vision
Toward discrete geometric models for early vision
Toward discrete geometric models for early vision
A computational approach to illusory contour perception based on the tensor voting technique
CIARP'05 Proceedings of the 10th Iberoamerican Congress conference on Progress in Pattern Recognition, Image Analysis and Applications
From stochastic completion fields to tensor voting
DSSCV'05 Proceedings of the First international conference on Deep Structure, Singularities, and Computer Vision
| Hi-index | 0.00 |
We describe a method for computing the likelihood that a completion joining two contour fragments passes through any given position and orientation in the image plane, that is, a method for completing the boundaries of partially occluded objects. Like computations in primary visual cortex (and unlike all previous models of contour completion in the human visual system), our computation is Euclidean invariant. This invariance is achieved in a biologically plausible manner by representing the input, output, and intermediate states of the computation in a basis of shiftable-twistable functions. The spatial components of these functions resemble the receptive fields of simple cells in primary visual cortex. Shiftable-twistable functions on the space of positions and directions are a generalization of shiftable-steerable functions on the plane.