Perceptual grouping based on iterative multi-scale tensor voting

Authors:
Leandro Loss;George Bebis;Mircea Nicolescu;Alexei Skourikhine
Affiliations:
Computer Vision Laboratory, University of Nevada, Reno;Computer Vision Laboratory, University of Nevada, Reno;Computer Vision Laboratory, University of Nevada, Reno;Space and Remote Sensing Sciences Group, Los Alamos National Laboratory
Venue:
ISVC'06 Proceedings of the Second international conference on Advances in Visual Computing - Volume Part II
Year:
2006

Citing 6
Cited 2

Three-dimensional object recognition from single two-dimensional images

Artificial Intelligence
Trace Inference, Curvature Consistency, and Curve Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Extraction of early perceptual structure in dot patterns: integrating region, boundary, and component gestalt

Computer Vision, Graphics, and Image Processing
Inference of Surfaces, 3D Curves, and Junctions from Sparse, Noisy, 3D Data

IEEE Transactions on Pattern Analysis and Machine Intelligence
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
Computational Framework for Segmentation and Grouping

Computational Framework for Segmentation and Grouping

Iterated tensor voting and curvature improvement

Signal Processing
An iterative multi-scale tensor voting scheme for perceptual grouping of natural shapes in cluttered backgrounds

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a new approach for perceptual grouping of oriented segments in highly cluttered images based on tensor voting. Segments are represented as second-order tensors and communicate with each other through a voting scheme that incorporates the Gestalt principles of visual perception. An iterative scheme has been devised which removes noise segments in a conservative way using multi-scale analysis and re-voting. We have tested our approach on data sets composed of real objects in real backgrounds. Our experimental results indicate that our method can segment successfully objects in images with up to twenty times more noise segments than object ones.