22 October 1993 Perceptual grouping by local group-tree research
Author Affiliations +
Proceedings Volume 2094, Visual Communications and Image Processing '93; (1993) https://doi.org/10.1117/12.157999
Event: Visual Communications and Image Processing '93, 1993, Cambridge, MA, United States
Abstract
Perceptual grouping, or perceptual organization, is the process of grouping local image features, such as line segments and regions, into groups (`perceptual chunks') that are likely to have come from the same object. Such an operation is essential to reliable and robust object recognition since the local features are often fragmented and cannot be matched directly to object models. In this paper, a novel approach to the problem of perceptual grouping is described. In this approach, perceptual grouping is accomplished in two steps. First, connections between local features are established or rejected according to which such connections would lead to good global groupings. This is done by performing a tree search of all the possible global groups associated with each potential connection. Second, perceptual groups are generated by propagating local connections and by local competition. The efficacy of this approach is demonstrated on the grouping of line segments in synthetic and real-world images.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jun Zhang, Jun Zhang, Yong Yan, Yong Yan, } "Perceptual grouping by local group-tree research", Proc. SPIE 2094, Visual Communications and Image Processing '93, (22 October 1993); doi: 10.1117/12.157999; https://doi.org/10.1117/12.157999
PROCEEDINGS
12 PAGES


SHARE
RELATED CONTENT

Towards relative gradient and its applications
Proceedings of SPIE (March 03 2015)
Neural net range image segmentation for object recognition
Proceedings of SPIE (September 01 1993)
Color image segmentation: a review
Proceedings of SPIE (February 26 2010)
Decision-making strategies in contour tracing
Proceedings of SPIE (July 31 1992)
Connectionist learning procedure for edge detector
Proceedings of SPIE (January 31 1992)

Back to Top