Multi-focus image fusion using multi-scale image decomposition and saliency detection

Citations of this article
Mendeley users who have this article in their library.


In this paper, we develop a new multi-focus image fusion method based on saliency detection and multi-scale image decomposition. Proposed method is very efficient, since the visual saliency explored in this algorithm is able to emphasize visually significant regions. Unlike most of the multi-scale fusion methods, an average filter is employed in our algorithm for multi-scale image decomposition. Hence it is computationally simple. A new weight map construction process based on visual saliency is developed. Weight maps of this algorithm are capable of detecting and identifying focused and defocused regions of the source images. We are able to integrate only focused and sharpened regions into the fused image. Performance of the proposed method is compared with that of the state-of-the-art multi-focus fusion methods. Proposed method outperforms them in terms of visual quality and fusion metrics. Our method requires considerably less computational time, thus making it preferable for real time implementation.




Bavirisetti, D. P., & Dhuli, R. (2018). Multi-focus image fusion using multi-scale image decomposition and saliency detection. Ain Shams Engineering Journal, 9(4), 1103–1117.

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free