Less-Visible Contrast Enhancement Based on Non-Linear Scaling Function and Singular Value Decomposition

Abstract

Typically, the conventional image enhancement methods have a problem concerning the over- enhancement in an image which contains both less-visible and nicely-visible areas in common. To solve such a problem, we propose a novel contrast enhancement method based on a non-linear scaling function and the singular value decomposition (SVD). The SVD is used to decompose the image into several layers. Some layers are associated with the less-visible areas. Then, such layers are strengthened by using a proposed logarithmic-scaling function. To reduce the effect of over-enhancement that might occur due to our function, the pyramid-based blending scheme is deployed. The evaluation results show that our proposed method can successfully improve the local content without amplifying noise. It also preserves the tone, the key-lighting, and the texture of the original image.