Title :
Computing Gabor expansion coefficients by TH neural network
Author :
Meng, Hongyig ; Liu, Guizhong
Author_Institution :
Inst. for Inf. Eng., Xi´´an Jiaotong Univ., China
Abstract :
It is proposed that the Gabor (1946) expansion coefficients of a periodic (or finite) discrete signal in both the critical sampling case and the oversampling case can be computed by TH neural networks. Theoretical analysis and simulations show that this network will certainly provide approximate solutions arbitrarily close to the accurate one within the time of the order of time constants of this network without any programming complexity
Keywords :
neural nets; signal representation; signal sampling; Gabor expansion coefficients; TH neural network; approximate solutions; critical sampling; finite discrete signal; oversampling; periodic discrete signal; signal analysis; signal representation; simulations; time constants; Analytical models; Binary search trees; Computed tomography; Computer networks; Hopfield neural networks; Image analysis; Image coding; Image segmentation; Neural networks; Signal analysis;
Conference_Titel :
Signal Processing, 1996., 3rd International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-2912-0
DOI :
10.1109/ICSIGP.1996.566575
