6 August 1993 Recognizing 3D articulated-line-drawing objects
Author Affiliations +
Proceedings Volume 2056, Intelligent Robots and Computer Vision XII: Active Vision and 3D Methods; (1993) https://doi.org/10.1117/12.150191
Event: Optical Tools for Manufacturing and Advanced Automation, 1993, Boston, MA, United States
This paper deals with recognition of three-dimensional (3D) polyhedral objects from two- dimensional (2D) line-drawing images. A new scheme is presented, which is aimed at learning, representing, and recognizing complicated 3D polyhedral objects such as concave, self-occluded and articulated objects, yet with only very few learning samples and can distinguish objects with very similar patterns. Several examples are illustrated.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Patrick S. P. Wang, Patrick S. P. Wang, "Recognizing 3D articulated-line-drawing objects", Proc. SPIE 2056, Intelligent Robots and Computer Vision XII: Active Vision and 3D Methods, (6 August 1993); doi: 10.1117/12.150191; https://doi.org/10.1117/12.150191


Qualitative three-dimensional shape from stereo
Proceedings of SPIE (January 31 1991)
Hough transform for 3-D object recognition
Proceedings of SPIE (February 29 1992)
Adaptive neural methods for multiplexing oriented edges
Proceedings of SPIE (January 31 1991)
The Vision By Pattern Aggregation - V.P.A.- System
Proceedings of SPIE (December 10 1985)

Back to Top