Skip to Main Content
For most image fusion algorithms split relationship among pixels and treat them more or less independently, this paper proposes a region based multi-focus image fusion scheme using quality assessment of spatial domain and genetic algorithm, which combines aspects of feature and pixel-level fusion. The basic idea is to divide the source images into blocks, and then select the corresponding blocks with higher quality assessment value to construct the resultant fused image. GA is brought forward to determine the suitable sizes of the block. Experimental results demonstrate that the proposed scheme outperforms Haar wavelet approach and morphological wavelet approach, both in visual effect and objective evaluation criteria, which is more robust under mis-registration situation.