Efficient Compressive Multi-Focus Image Fusion

Two key points of pixel-level multi-focus image fusion are the clarity measure and the pixel coefficients fusion rule. Along with different improvements on these two points, various fusion schemes have been proposed in literatures. However, the traditional clarity measures are not designed for compressive imaging measurements which are maps of source sense with random or likely random measurements matrix. This paper presents a novel efficient multi-focus image fusion framework for compressive imaging sensor network. Here the clarity measure of the raw compressive measurements is not obtained from the random sampling data itself but from the selected Hadamard coefficients which can also be acquired from compressive imaging system efficiently. Then, the compressive measurements with different images are fused by selecting fusion rule. Finally, the block-based CS which coupled with iterative projection-based reconstruction is used to recover the fused image. Experimental results on common used testing data demonstrate the effectiveness of the proposed method.