Cloud Based Image Contrast Enhancement

We propose a cloud based image contrast enhancement framework, in which the context-sensitive and context-free contrast is improved via solving a multi-criteria optimization problem. Specifically, the context-sensitive contrast enhancement is based on the unsharp masking of the input and edge-preserving filtered images, while the context-free contrast enhancement is achieved by the sigmoid transfer mapping. The parameters in the optimization process are determined with the reference to the image that has a similar content and better enhancement quality in the cloud. The image complexity from the free energy based brain theory and the "surface" quality statistics is collaboratively optimized to infer the parameters. Experimental results demonstrate that the proposed technique can efficiently create visually-pleasing enhanced images with the guidance image from cloud.