3 October 1995 Three-dimensional thinning by neural networks
Author Affiliations +
Abstract
3D thinning is widely used in 3D object representation in computer vision and in trajectory planning in robotics to find the topological structure of the free space. In the present paper, we propose a 3D image thinning method by neural networks. Each voxel in the 3D image corresponds to a set of neurons, called 3D Thinron, in the network. Taking the 3D Thinron as the elementary unit, the global structure of the network is a 3D array in which each Thinron is connected with the 26 neighbors in the neighborhood 3 X 3 X 3. As to the Thinron itself, the set of neurons are organized in multiple layers. In the first layer, we have neurons for boundary analysis, connectivity analysis and connectivity verification, taking as input the voxels in the 3 X 3 X 3 neighborhood and the intermediate outputs of neighboring Thinrons. In the second layer, we have the neurons for synthetical analysis to give the intermediate output of Thinron. In the third layer, we have the decision neurons whose state determines the final output. All neurons in the Thinron are the adaline neurons of Widrow, except the connectivity analysis and verification neurons which are nonlinear neurons. With the 3D Thinron neural network, the state transition of the network will take place automatically, and the network converges to the final steady state, which gives the result medial surface of 3D objects, preserving the connectivity in the initial image. The method presented is simulated and tested for 3D images, experimental results are reported.
© (1995) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jun Shen, Wei Shen, "Three-dimensional thinning by neural networks", Proc. SPIE 2588, Intelligent Robots and Computer Vision XIV: Algorithms, Techniques, Active Vision, and Materials Handling, (3 October 1995); doi: 10.1117/12.222716; https://doi.org/10.1117/12.222716
PROCEEDINGS
9 PAGES


SHARE
RELATED CONTENT

Contemporary deep recurrent learning for recognition
Proceedings of SPIE (May 01 2017)
Improved adaptive resonance theory
Proceedings of SPIE (February 01 1991)
Extract configuration of three-dimensional object
Proceedings of SPIE (September 21 1994)
Monocular pose estimation of quadrics of revolution
Proceedings of SPIE (March 01 1992)

Back to Top