Title :
2D shape analysis base on perceptual hierarchy
Author_Institution :
Dept. of Math. Stat. & Comput. Sci., Dalhousie Univ., Halifax, NS
Abstract :
A novel approach for the recognition of 2D shapes is presented based on the perceptual organization of descriptive-boundary primitives of objects. The system has three components: (1) a set of partition and grouping rules for extracting and manipulating the primitives, (2) a control structure of the processes and (3) a representation scheme based on a perceptual hierarchy
Keywords :
edge detection; feature extraction; image representation; object recognition; visual perception; 2D shape analysis; control structure; descriptive-boundary primitives; edge partitioning; grouping rules; human visual system; object recognition; partition rules; perceptual hierarchy; perceptual organization; primitives extraction; primitives manipulation; representation scheme; Computer vision; Control systems; Humans; Image analysis; Layout; Mathematics; Psychology; Retina; Shape; Statistics;
Conference_Titel :
Digital Signal Processing Workshop Proceedings, 1996., IEEE
Conference_Location :
Loen
Print_ISBN :
0-7803-3629-1
DOI :
10.1109/DSPWS.1996.555501
