Satellite Cloud Image De-Noising and Enhancement by Fuzzy Wavelet Neural Network and Genetic Algorithm in Curvelet Domain

摘要

A satellite cloud image is decomposed by discrete curvelet transform (DCT). In-complete Beta transform (IBT) is used to obtain non-linear gray transform curve so as to enhance the coefficients in the coarse scale in the DCT domain. GA determines optimal gray transform parameters. Information entropy is used as fitness function of GA. In order to calculate IBT in the coarse scale, fuzzy wavelet neural network (FWNN) is used to approximate the IBT. Hard-threshold method is used to reduce the noise in the high frequency sub-bands of each decomposition level respectively in the DCT domain. Inverse DCT is conducted to obtain final de-noising and enhanced image. Experimental results show that proposed algorithm can efficiently reduce the noise in the satellite cloud image while well enhancing the contrast. In performance index and visual quality, the proposed algorithm is better than traditional histogram equalization and unsharpened mask method.