Title :
Zernike moment-based image registration scheme utilizing feedforward neural networks
Author :
Wu, Jianzhen ; Xie, Jianying
Author_Institution :
Dept. of Autom., Shanghai Jiao Tong Univ., China
Abstract :
A novel image registration scheme is proposed. Low order Zernike moments are used as image global pattern features and feed into feedforward neural networks to provide translation, rotation and scaling parameters. Experimental results show that the proposed registration scheme is accurate and robust to noise.
Keywords :
feature extraction; feedforward neural nets; image registration; Zernike moment based image registration; feedforward neural networks; image global pattern features; low order Zernike moments; rotation parameters; scaling parameters; translation parameters; Automation; Feedforward neural networks; Feeds; Image registration; Neural networks; Noise robustness; Parameter estimation; Polynomials; Registers; Shape;
Conference_Titel :
Intelligent Control and Automation, 2004. WCICA 2004. Fifth World Congress on
Print_ISBN :
0-7803-8273-0
DOI :
10.1109/WCICA.2004.1342260
