Image Contrast Enhancement based on Non-linear Processing

Contrast enhancement is one of the major image processing for cameras, smartphones and printers. This study proposes a novel adaptive image enhancement algorithm based on the Total Variation regularization decomposition. In our proposed method, an image is decomposed into a structure component and a texture component and the structure and texture components are processed by utilizing the Gamma correction to correct its contrast and a detail enhancement, respectively. The experimental results show that the performance of our proposed method is very similar to that of the Retinex method, whereas the computational time required is much lower than that with the Retinex method.