doi:10.1016/j.sigpro.2005.06.015
Copyright © 2005 Elsevier B.V. All rights reserved.
A simple and efficient algorithm for multifocus image fusion using morphological wavelets
Ishita Dea and Bhabatosh Chandab,
, 
aDepartment of Computer Science, Barrackpore Rastraguru Surendranath College, Kolkata 700120, India
bElectronics and Communication Sciences Unit, Indian Statistical Institute, Kolkata 700108, India
Received 11 October 2004;
revised 16 July 2005.
Available online 25 August 2005.
References and further reading may be available for this article. To view references and further reading you must
purchase this article.
Abstract
This paper presents a simple yet efficient algorithm for multifocus image fusion, using a multiresolution signal decomposition scheme. The decomposition scheme is based on a nonlinear wavelet constructed with morphological operations. The analysis operators are constructed by morphological dilation combined with quadratic downsampling and the synthesis operators are constructed by morphological erosion combined with quadratic upsampling. A performance measure based on image gradients is used to evaluate the results. The proposed scheme has some interesting computational advantages as well.
Keywords: Multifocus image fusion; Multiresolution signal decomposition; Morphological wavelets; Image gradient
Fig. 1. Wavelet transform on a 2×2 block of X.
Fig. 2. Example for proposed wavelet transform.
Fig. 3. (a) Original signal X, (b) scaled signal X1 and details
at level 1, (c) scaled signal X2 and details
at level 2.
Fig. 4. Original multifocus images and the fused images by different algorithms: (a) Near focused image; (b) middle focused image; (c) far focused image; (d) fused image with proposed algorithm; (e) fused image by Haar wavelet; (f) fused image by Heijmans and Goutsias’ method.
Fig. 5. Original multifocus images and the fused images by different algorithms: (a) Left focused image; (b) center focused image; (c) right focused image; (d) fused image with proposed algorithm; (e) fused image by Haar wavelet; (f) fused image by Heijmans and Goutsias’ method.
Fig. 6. Original multifocus images and the fused images by different algorithms: (a) Focus on background; (b) focus on foreground; (c) fused image with proposed algorithm; (d) fused image by Haar wavelet; (e) fused image by Heijmans and Goutsias’ method.
Fig. 7. Original multifocus images and the fused images by different algorithms: (a) Focus on background; (b) focus on foreground; (c) fused image with proposed algorithm; (d) fused image by Haar wavelet; (e) fused image by Heijmans and Goutsias’ method.
Table 1.
Similarity between maximum gradient and fused gradient images
