A Novel Multi-focus Image Fusion Based on Lazy Random Walks
Most existing fusion methods usually suffer from blurred edges and introduce artifacts (such as blocking or ringing). To solve these problems, a novel multi-focus image fusion algorithm using lazy random walks (LRW) is proposed in this paper. Firstly, the sum of the modified Laplacian (SML) of each source image and a maximum operation rule are used to obtain the highly believable focused regions. Then, a lazy random walks based image fusion algorithm is presented to precisely locate the boundary of focused regions from the above highly believable focused regions in each source image. Experimental results demonstrate that the proposed algorithm can generate high quality all-in-focus images, avoid annoying artifacts and well preserve the sharpness on the focused objects. Our method is superior to the state-of-the-art methods in both subjective and objective assessments.
KeywordsMulti-focus image fusion Lazy random walks Sum of the modified Laplacian
- 1.Tian, J., Chen, L.: Multi-focus image fusion using wavelet-domain statistics. In: 17th IEEE International Conference on Image Processing, pp. 1205–1208. IEEE, Hong Kong (2010)Google Scholar
- 15.Zhao, J., Laganiere, R., Liu, Z.: Performance assessment of combinative pixel-level image fusion based on an absolute feature measurement. Int. J. Innov. Comput. Inf. Control 3(6), 1433–1447 (2007)Google Scholar