A hierarchical multiple-view approach to three-dimensional object recognition
- 1 January 1991
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 2 (1), 84-92
- https://doi.org/10.1109/72.80293
Abstract
A hierarchical approach is proposed for solving the surface and vertex correspondence problems in multiple-view-based 3D object-recognition systems. The proposed scheme is a coarse-to-fine search process, and a Hopfield network is used at each stage. Compared with conventional object-matching schemes, the proposed technique provides a more general and compact formulation of the problem and a solution more suitable for parallel implementation. At the coarse search stage, the surface matching scores between the input image and each object model in the database are computed through a Hopfield network and are used to select the candidates for further consideration. At the fine search stage, the object models selected from the previous stage are fed into another Hopfield network for vertex matching. The object model that has the best surface and vertex correspondences with the input image is finally singled out as the best matched model. Experimental results are reported using both synthetic and real range images to corroborate the proposed theory.Keywords
This publication has 25 references indexed in Scilit:
- Optimization in Model Matching and Perceptual OrganizationNeural Computation, 1989
- Sensitivity analysis in neural net solutionsIEEE Transactions on Systems, Man, and Cybernetics, 1989
- Segmentation through variable-order surface fittingIEEE Transactions on Pattern Analysis and Machine Intelligence, 1988
- Flexible Corner Detection Based On A Single-Parameter ControlPublished by SPIE-Intl Soc Optical Eng ,1988
- On the stability of the Travelling Salesman Problem algorithm of Hopfield and TankBiological Cybernetics, 1988
- 3-D multiview object representations for model-based object recognitionPattern Recognition, 1986
- Computing with Neural Circuits: A ModelScience, 1986
- Model-based recognition in robot visionACM Computing Surveys, 1986
- Three-dimensional object recognitionACM Computing Surveys, 1985
- Matching three-dimensional objects using a relational paradigmPattern Recognition, 1984