What is Filtering

Current image coding with image fusion schemes make it hard to utilize external images for transform even if highly correlated images can be found in the cloud. To solve this problem, we explain an approach of cloud-based image transform coding with image fusion methodwhich is distinguish from exists image fusion method. A fast and efficient image fusion technique is proposed for creating a highly generated fused image through merging multiple corresponding images. The proposed technique is based on a two-scale decomposition of an image into a low layer containing large scale variations, and a detail layer acquiring small scale details. A novel approach of guided filtering-based weighted average method is proposed to make full use of spatial consistency for merge of the base and detail layers. Analytical results represent that the proposed technique can obtain state-of-the-art performance for image fusion of multispectral, multifocus, multimodal, and multiexposure images.