DocumentCode :
314348
Title :
Blind deconvolution by self-organization
Author :
Tai, Wen-Pin ; Lin, Ruei-Sung ; Liou, Cheng-Yuan
Author_Institution :
Nat. Taiwan Univ., Taipei, Taiwan
Volume :
3
fYear :
1997
fDate :
9-12 Jun 1997
Firstpage :
1568
Abstract :
In this paper, we devise a self-organizing network to solve both the unknown system and unknown input in blind deconvolution of blurred images. We utilize a criterion function which has a similar form as the Kullback-Leibler cross information formula to adapt the network´s weights to approach the unknown system function. This adaptation gradually reduces the criterion value which is a distance measure between the system output and the output of the adapted system with a reconstructed input signal. The weight matrices of the neurons in the network are shifted versions of the system function and will be aligned in the network according to their shifts during convergence. This is because the convolution operation which copes with this network scheme and the hidden topology of the shifted system functions can be aligned similarly in a 2D plane
Keywords :
deconvolution; identification; image processing; information theory; optimisation; self-organising feature maps; topology; Kullback-Leibler information criterion; blind deconvolution; blurred images; convergence; image processing; optimisation; self-organizing network; system identification; topology; weight matrices; Computer science; Convergence; Convolution; Deconvolution; Electronic mail; Image reconstruction; Neurons; Pollution measurement; Self-organizing networks; Signal processing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks,1997., International Conference on
Conference_Location :
Houston, TX
Print_ISBN :
0-7803-4122-8
Type :
conf
DOI :
10.1109/ICNN.1997.614127
Filename :
614127
Link To Document :
بازگشت