The smoothing of images is a very important step in the stitching process of images. An improved seamless image stitching algorithm based on the wavelet direction contrast is presented by the analysis of some available smoothing algorithms. The improved algorithm makes the luminance of the two images same first, then the multiresolution decomposition of the two images is implemented by using wavelet transformation and the images are smoothed by an improved wavelet direction contrast algorithm. The simulation results were assessed with some objective evaluation standards. The results show that this algorithm can make two images smoothly in despite of a great gray difference between the two images. Therefore, it is independent of the ambient light and can make the details of images clear.
Key words
image smoothing /
seamless stitching /
statistical parameter /
wavelet direction contrast
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
References
[1]BURT P J. The pyramid as a structure for efficient computation[C]∥ROSENFELD A. Multiresolution image processing and analysis.Berlin:[s.n.], 1984.
[2]LEMESHEWSKY G P. Multispectral multisensor image fusion using wavelet transforms[J]. SPIE,1999,3716:214-222.
[3]EL-KHAMY S E, HADHOUD M M, DESSOUKY M L, et al. Reqularized supper-rusolution recon-struction of images using wavelet fusio[J]. Optical Engineering,2005,44(9):097001-1-9.
[4]MALLAT S G. A wavelet tour of signal processing[M]. San Diego, California:Academic Press, 1998.
[5]晁锐, 张科,李言俊.一种基于小波变换的图像融合算法[J]. 电子学报, 2004,32(5):750-753.
CHAO Rui, ZHANG Ke, LI Yan-jun. A wavelet transform-based image fusion method[J]. Acta Electronica Sinica, 2004,32(5):750-753. (in Chinese with an English abstract)
[6]TOET A, RUYNEN L V, VELATON J. Merging thermal and visual images by a contrast pyramid[J]. Optical Engineering
{{custom_fnGroup.title_en}}
Footnotes
{{custom_fn.content}}
