DocumentCode :
3191126
Title :
Voronoi pyramids and Hopfield networks
Author :
Bischof, Horst ; Bertin, Etienne ; Bertolino, Pascal
Author_Institution :
Dept. of Pattern Recognition & Image Process., Tech. Univ. Wien, Austria
fYear :
1994
fDate :
9-13 Oct 1994
Firstpage :
330
Abstract :
Presents an algorithm for image segmentation with irregular pyramids. Instead of starting with the original pixel grid, the authors first apply an adaptive Voronoi tessellation to the image. For irregular pyramid construction the authors present a Hopfield neural network which controls the decimation process. The validity of the authors´ approach is demonstrated by several examples in image segmentation
Keywords :
image segmentation; Hopfield networks; Voronoi pyramids; adaptive Voronoi tessellation; decimation process; image segmentation; irregular pyramids; Convergence; Hopfield neural networks; Image processing; Image segmentation; Joining processes; Laboratories; Pattern recognition; Pixel; Process control;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition, 1994. Vol. 3 - Conference C: Signal Processing, Proceedings of the 12th IAPR International Conference on
Conference_Location :
Jerusalem
Print_ISBN :
0-8186-6275-1
Type :
conf
DOI :
10.1109/ICPR.1994.577192
Filename :
577192
Link To Document :
بازگشت