DocumentCode :
2066284
Title :
A fast algorithm for image restoration using a recurrent neural network with bound-constrained quadratic optimization
Author :
Gendy, S. ; Kothapalli, G. ; Bouzerdoum, A.
Author_Institution :
Sch. of Eng. & Math., Edith Cowan Univ., Joondalup, WA, Australia
fYear :
2001
fDate :
18-21 Nov. 2001
Firstpage :
111
Lastpage :
115
Abstract :
This paper presents a fast algorithm for a recurrent neural network that can restore a degraded image with fewer iterations and shorter processing time by using bound-constrained quadratic optimization (BCQO) and a weighted mask. The BCQO technique has already been used in signal restoration, however implementation of this method in image restoration requires considerable memory and it is computationally expensive. The proposed algorithm replaces the weight matrix of the network with a much smaller mask, thus reducing the processing time and requiring much less memory space. This algorithm produces better results than those obtained by Wiener filter, and achieves image restoration with less iterations compared to a modified Hopfield neural network.
Keywords :
Hopfield neural nets; image restoration; mean square error methods; quadratic programming; recurrent neural nets; bound-constrained quadratic optimization; degraded image; image restoration; modified Hopfield neural network; recurrent neural network; weight matrix; weighted mask; Additive noise; Degradation; Frequency; Hopfield neural networks; Image restoration; Least squares methods; Low-frequency noise; Recurrent neural networks; Signal restoration; Wiener filter;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Information Systems Conference, The Seventh Australian and New Zealand 2001
Print_ISBN :
1-74052-061-0
Type :
conf
DOI :
10.1109/ANZIIS.2001.974060
Filename :
974060
Link To Document :
بازگشت