Issue No. 06 - June (1992 vol. 14)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.141553
<p>A data-driven system for segmenting scenes into objects and their components is presented. This segmentation system generates hierarchies of features that correspond to structural elements such as boundaries and surfaces of objects. The technique is based on perceptual organization, implemented as a mechanism for exploiting geometrical regularities in the shapes of objects as projected on images. Edges are recursively grouped on geometrical relationships into a description hierarchy ranging from edges to the visible surfaces of objects. These edge groupings, which are termed collated features, are abstract descriptors encoding structural information. The geometrical relationships employed are quasi-invariant over 2-D projections and are common to structures of most objects. Thus, collations have a high likelihood of corresponding to parts of objects. Collations serve as intermediate and high-level features for various visual processes. Applications of collations to stereo correspondence, object-level segmentation, and shape description are illustrated.</p>
computerised picture processing; computerised pattern recognition; scene segmentation; data-driven system; boundaries; surfaces; perceptual organization; geometrical regularities; edge groupings; collated features; abstract descriptors; 2-D projections; stereo correspondence; shape description; computerised pattern recognition; computerised picture processing
R. Mohan and R. Nevatia, "Perceptual Organization for Scene Segmentation and Description," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 14, no. , pp. 616-635, 1992.