DocumentCode
1704895
Title
Recognition of three dimensional objects using a directional coupled neural network
Author
Miyanaga, Yoshikazu ; Motoyoshi, Katsuhito ; Tochinai, Koji
Author_Institution
Fac. of Eng., Hokkaido Univ., Sapporo, Japan
fYear
1996
Firstpage
259
Lastpage
262
Abstract
This report introduces a new approach on a recognition system of three dimensional, i.e., 3-D, objects. The proposed system is based on a restricted multi-layered neural network. In order to greatly reduce the total calculation cost of preprocessing for the recognition, directional coupled nodes in a network are introduced. This report also shows that the system can recognize some 3-D objects correctly in experiments
Keywords
image recognition; multilayer perceptrons; object recognition; 3D recognition system; calculation cost reduction; directional coupled neural network; directional coupled nodes; experiments; image recognition; preprocessing; restricted multilayered neural network; three dimensional object recognition; Costs; Electronic mail; IEEE members; Image edge detection; Image recognition; Multi-layer neural network; Multimedia systems; Neural networks;
fLanguage
English
Publisher
ieee
Conference_Titel
Digital Signal Processing Workshop Proceedings, 1996., IEEE
Conference_Location
Loen
Print_ISBN
0-7803-3629-1
Type
conf
DOI
10.1109/DSPWS.1996.555510
Filename
555510
Link To Document