Fuzzy contrast enhancement for remote sensing image based on fuzzy set in nonsubsampled contourlet domain

In view of conventional contrast enhancement algorithms usually adopt a global approach to enhance all the brightness level of the images which lead to some detailed information being lost and enhancement of the noise in noisy environment, and the remote sensing image contains a lot of low contrast and poor resolution textual information, a fuzzy contrast enhancement algorithm using fuzzy theory in nonsubsampled contourlet transform (NSCT) domain is presented in this paper. NSCT is developed recently and can offer a trait of multidirection, flexible multiscale and shift-invariant, which can capture the intrinsic geometrical structures perfectly, and fuzzy set theory is a useful tool for handling the uncertainty in the images, and the proposed algorithm accepts advantages of NSCT and fuzzy set theory as a basis for image enhancement. Firstly, decompose the source remote sensing image in highpass subbands and lowpass subbands by NSCT. Secondly, map each highpass subband into corresponding fuzzy plane using membership function with different constraints and implement fuzzy contrast enhancement in fuzzy domain for each fuzzy plane. Finally, transform the fuzzy domain to NSCT domain and reconstruct the enhanced image from the modified NSCT coefficients. Compared with some methods, the simulation results and analysis show that the proposed algorithm obviously outperforms in both Signal-to-Noise Ratio(SNR) and visual quality, and effectively enhances the detail and texture information of remote sensing image.