Multi-focus image fusion based on matching pursuit

Aiming at multi-focus image fusion, a new image fusion algorithm based on matching pursuit is proposed. Through matching pursuit signal decomposition algorithm, distinctive atoms with higher energy are selected from each input registered image to construct fused image. Some problems in traditional image fusion methods, such as ringing effect or blocking artifacts, can be avoided effectively. The last comparative experiments show that the proposed MP based image fusion algorithm outperforms the traditional wavelet image fusion.

[1]  Image Fusion Algorithm Based on Wavelet Transformation , 2006, 2006 International Conference on Mechatronics and Automation.

[2]  Edward H. Adelson,et al.  The Laplacian Pyramid as a Compact Image Code , 1983, IEEE Trans. Commun..

[3]  Alexander Toet,et al.  Hierarchical image fusion , 1990, Machine Vision and Applications.

[4]  Bhabatosh Chanda,et al.  A simple and efficient algorithm for multifocus image fusion using morphological wavelets , 2006, Signal Process..

[5]  Stéphane Mallat,et al.  Matching pursuits with time-frequency dictionaries , 1993, IEEE Trans. Signal Process..

[6]  B. S. Manjunath,et al.  Multisensor Image Fusion Using the Wavelet Transform , 1995, CVGIP Graph. Model. Image Process..

[7]  G. Clark,et al.  Reference , 2008 .