Title :
Contour Extraction by a Neural Network Approximation
Author :
Zhiheng Zhou ; Delu Zeng
Author_Institution :
South China Univ. of Technol., Guangzhou
Abstract :
A contour extraction algorithm based on a neural network is proposed in this paper. A series of searching circles are used in obtained feature pixels with discrimination analysis for the final curve function approximation by neural network. Robust back propagation algorithm has been used to control the final curve shape. The simulations also show that the proposed algorithm has a great performance for different kinds of images.
Keywords :
approximation theory; backpropagation; edge detection; feature extraction; neural nets; contour extraction; final curve shape; neural network approximation; robust back propagation algorithm; searching circles; Active contours; Approximation algorithms; Function approximation; Image processing; Level set; Neural networks; Pixel; Robust control; Shape control; Statistical learning;
Conference_Titel :
Innovative Computing Information and Control, 2008. ICICIC '08. 3rd International Conference on
Conference_Location :
Dalian, Liaoning
Print_ISBN :
978-0-7695-3161-8
Electronic_ISBN :
978-0-7695-3161-8
DOI :
10.1109/ICICIC.2008.639
