Regional Contrast Fuzzy Enhancement for Remote Sensing Image Based on the Generalized Fuzzy Set in Nonsubsampled Contourlet Domain

Abstract

Most conventional contrast enhancement algorithms usually adopt a global approach to enhance all the brightness level of the image, it is usually to enhance the noise in noisy environment and difficult to enhance the local details contrast, therefore some detailed information may be lost, however, a majority of remote sensing images contain many low contrast and poor resolution details and fine textures information, and are degraded by noise. Fuzzy set theory is a useful tool for handling the uncertainty in the images associated with vagueness, and the nonsubsampled contourlet transform (NSCT) is an overcomplete techniques to capture the intrinsic geometrical structures. In this paper, we proposed a regional contrast fuzzy enhancement algorithm for remote sensing image based on the generalized fuzzy set (GFS) in NSCT domain. The experimental results have demonstrated that the proposed algorithm is more effective and adaptive for remote sensing image contrast enhancement, and superior both in visual quality of enhancement and anti-noise performance.