DocumentCode :
540086
Title :
A fast training approach to artificial neural networks designed for image segmentation
Author :
Malki, Heidar A. ; Moghaddamjoo, Alireza
fYear :
1990
fDate :
9-11 Aug. 1990
Firstpage :
355
Lastpage :
358
Abstract :
A novel training approach based on the backpropagation algorithm for image segmentation is presented. A set of training vectors is obtained by applying Karhunen-Loeve transformations on the training patterns. Training is started in the direction of the major components and then continues by including other components, in the order of their significance. With this approach, not only will the number of computations during training decrease, but also the problem of trapping in a local minimum will be minimized. This method is applied to image segmentation and compared to the general backpropagation algorithm
Keywords :
learning systems; minimisation; neural nets; picture processing; Karhunen-Loeve transformations; backpropagation; image segmentation; local minimum; neural networks; picture processing; training approach;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Systems Engineering, 1990., IEEE International Conference on
Conference_Location :
Pittsburgh, PA, USA
Print_ISBN :
0-7803-0173-0
Type :
conf
DOI :
10.1109/ICSYSE.1990.203170
Filename :
5725702
Link To Document :
بازگشت