Remote Sensing Image Enhancement Based on Nonsubsampled Shearlet Transform and Local Laplacian Filter

To improve contrast for remote sensing image without suffering from insufficient details, this paper proposes an enhancement method for different remote sensing images based on nonsubsampled shearlet transform (NSST) and local laplacian filter. The input image is first decomposed into low-frequency and high-frequency components. Then, the chosen local laplacian filter is used to process the low-frequency coefficient, and the adaptive threshold is used to suppress the noise included in the high-frequency coefficient. Finally, the NSST is inversed to obtain the enhanced image. Visual and quantitative analysis indicate the significance of the proposed image enhancement scheme, as compared to state of the art techniques.