Novel PCA Based Pixel-Level Multi-Focus Image Fusion Algorithm

Close range optical images are considered as useful inputs to current object detection systems. By using image fusion techniques, the object detection system can reduce the redundant information from the input image and improve its understanding about the close range environment. Recently multi-focus image fusion has been applied to adaptive landmine detection systems. This paper proposes a new PCA based adaptive image fusion algorithm to fuse multi-focus images with the same visual angle but different focus. The core of the algorithm is a new technique for comparing each pixel's covariance matrix with the average covariance matrix. The test results show that the proposed algorithm outperforms state-of-the-art multi-focus image fusion algorithms. In addition, the proposed algorithm features lower implementation costs, which is suitable for the embedded systems.