1 February 1992 Object recognition using neural networks and high-order perspective-invariant relational descriptions
Author Affiliations +
The task of 3-D object recognition can be viewed as consisting of four modules: extraction of structural descriptions, hypothesis generation, pose estimation, and hypothesis verification. The recognition time is determined by the efficiency of each of the four modules, but particularly on the hypothesis generation module which determines how many pose estimates and verifications must be done to recognize the object. In this paper, a set of high-order perspective-invariant relations are defined which can be used with a neural network algorithm to obtain a high-quality set of model-image matches between a model and image of a robot workstation. Using these matches, the number of hypotheses which must be generated to find a correct pose is greatly reduced.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Kenyon R. Miller, Kenyon R. Miller, John F. Gilmore, John F. Gilmore, } "Object recognition using neural networks and high-order perspective-invariant relational descriptions", Proc. SPIE 1607, Intelligent Robots and Computer Vision X: Algorithms and Techniques, (1 February 1992); doi: 10.1117/12.57098; https://doi.org/10.1117/12.57098


Qualitative three-dimensional shape from stereo
Proceedings of SPIE (January 31 1991)
Extraction of shape-based properties
Proceedings of SPIE (October 05 1998)
Object Recognition by a Hopfield Neural Network
Proceedings of SPIE (February 28 1990)
Fast Automated Object Detection Using Signature Parsing
Proceedings of SPIE (February 28 1990)

Back to Top