DocumentCode :
2050025
Title :
A Novel Algorithm of Image Fusion Based on Adaptive ULPCNN Time Matrix
Author :
Liu, Qing ; Xu, Lu-ping ; Wang, Yong ; MA, Yi-de ; Xie, Qiang
Author_Institution :
Sch. of Phys. & Inf. Sci., Tianshui Normal Univ., Tianshui, China
Volume :
1
fYear :
2010
fDate :
14-15 Aug. 2010
Firstpage :
198
Lastpage :
202
Abstract :
A novel image fusion algorithm using adaptive Unit-Linking Pulse Coupled Neural Networks (ULPCNN) is put forward. Firstly, ULPCNN threshold function is improved, and then the null interconnection and the adaptive interconnection ULPCNN are formed. Secondly, the nonlinear mapped ULPCNN time matrix can be obtained, which can represent the characteristic of the single pixel, but can reflect the pixel information of the neighbourhood region in an image. Finally, through adaptive characteristic statistical judgment of each pixel and the neighbour local character in time matrix, corresponding fusion processing to source image can be established. Theoretical analysis and experimental simulations show that the proposed algorithm enhances image fusion performance with PCNN automatically. The abundant characteristic information are better than PCA, Laplacian pyramid and wavelet transform, it presents higher detail average gradient, better visual effect and good fusion qualities.
Keywords :
image fusion; image segmentation; matrix algebra; neural nets; ULPCNN threshold function; adaptive characteristic statistical judgment; adaptive unit linking pulse coupled neural network; image fusion; neighbour local character; nonlinear mapped ULPCNN time matrix; null interconnection; Algorithm design and analysis; Artificial neural networks; Image fusion; Neurons; Pixel; Principal component analysis; Transforms; AULPCNN; Discrete coefficient; Image fusion; Interconnection strength; Time matrix;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Information Engineering (ICIE), 2010 WASE International Conference on
Conference_Location :
Beidaihe, Hebei
Print_ISBN :
978-1-4244-7506-3
Electronic_ISBN :
978-1-4244-7507-0
Type :
conf
DOI :
10.1109/ICIE.2010.54
Filename :
5571056
Link To Document :
بازگشت