Translator Disclaimer
1 February 1992 Qualitative descriptors for digital contour segments (Invited Paper)
Author Affiliations +
Earlier studies of the human vision system suggest that a complex object may be recognized from the qualitative features associated with its boundary. Since the human vision system uses qualitative features for object recognition, it is extremely robust to deformation caused by noise, obstruction, scale change, or optical distortion. We considered various qualitative descriptors for digital images. The descriptors developed in this research are based on the estimated curvature function from digital boundaries and can discriminate features such as straightness of a contour segment, perpendicularity of two contour segments, parallelness of two straight contour segments, parallelness of two curved contour segments in a global sense, and the direction of convergence if two straight contour segments are not parallel. We demonstrated that the qualitative descriptors developed in this paper can be applied for identification of elementary shapes, such as cylinders, bricks, cones, etc. We also discussed the recognition of more complex shapes after decomposing them into simpler components.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Kathryn Shaker Baummer, Kie Bum Eom, and Murray H. Loew "Qualitative descriptors for digital contour segments (Invited Paper)", Proc. SPIE 1610, Curves and Surfaces in Computer Vision and Graphics II, (1 February 1992);


Adaptive chain coding for arbitrary curves
Proceedings of SPIE (November 01 1992)
Complexity of computing nice viewpoints of objects in space
Proceedings of SPIE (October 23 2000)
Dynamic search of Gaussian segmentation
Proceedings of SPIE (September 30 1996)
Approximation of sweep surfaces by tensor product NURBS
Proceedings of SPIE (February 01 1992)

Back to Top