DocumentCode
2934659
Title
Image fusion using a NSDFB-based contourlet packet
Author
Yang, Shuyuan ; Wang, Min ; Liu, ZhanWen ; Jiao, Licheng
Author_Institution
Xidian Univ., Xi´´an
fYear
2007
fDate
Nov. 28 2007-Dec. 1 2007
Firstpage
690
Lastpage
693
Abstract
In this paper, a new contourlet packet (CP) is constructed based on a complete wavelet quadtree followed by a nonsubsampled directional filter bank (NSDFB). By combing the finer approximation characteristic of wavelet packet with the invertible characteristic of NSDFB, the proposed CP can give more accurate reconstruction of images than WP. After the proposed CP transform on the fusing images, the low-frequency subbands are compared to preserve the coefficients whose module are minimum, local inner-product rule is performed on the high-frequency subbands of the images. Then the fusion image can be obtained by taking an inverse CP transform. The experiment results show the superiority of the method to Contourlet, Wavelet packet, NSCT, stationary Wavelet, complex wavelet and WBCP based fusion methods, both in image clarity and standard deviation, information entropy, average gradient, average cross
Keywords
channel bank filters; image fusion; image reconstruction; quadtrees; wavelet transforms; NSDFB-based contourlet packet; finer approximation characteristic; image fusion; images reconstruction; inverse CP transform; low-frequency subbands; nonsubsampled directional filter bank; wavelet packet; wavelet quadtree; Computed tomography; Filter bank; Frequency conversion; Image fusion; Image reconstruction; Information processing; Laboratories; Radar signal processing; Wavelet packets; Wavelet transforms; Image fusion; NSDFB; contourlet; contourlet packet;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Signal Processing and Communication Systems, 2007. ISPACS 2007. International Symposium on
Conference_Location
Xiamen
Print_ISBN
978-1-4244-1447-5
Electronic_ISBN
978-1-4244-1447-5
Type
conf
DOI
10.1109/ISPACS.2007.4445981
Filename
4445981
Link To Document