Multi-focus image fusion using clarity map

A novel method to compute the clarity map from single image based on the local maxima and minima information inside image is proposed in this paper. The well-focused region can be easily identified according to the significant pixels inside the clarity map of image. Our method utilizes the clarity map difference between two source images as the focus criteria to implement multi-focus image fusion. According to the difference between two clarity images, the proposed method decides how to fuse different parts from source images. CUDA technology is utilized to make the process of computing clarity map 450 times faster than traditional CPU implementation. Four groups of experiments are designed to testify the performance of the proposed method. Several fusion results generated from state-ofart methods with the best parameter configuration are compared with results from our method in this paper. Based on the results of the experiments, our method exceeds other methods known presently in both subject and object evaluation criteria.