The Research On Image Enhancement Algorithm Based On NSCT And Shearlet Transform

With the development of science and technology,image has become the most important carrier of information,and various imaging techniques are becoming more and more mature and perfect.Due to the influence of imaging equipment,image transmission and storage,the original images acquired will be affected by interference from various aspects.These interference will make the images appear on the low resolution,the details of the distortion,the sharp decline in contrast and other defects,seriously affecting people's access to information quickly and accurately.So the image enhancement that is one of the main steps of image preprocessing has become significant,it is mainly in suppressing or eliminating image noise and enhancing image texture details,as well as the contrast and definition of the background,so that the overall image quality is improved,the target information is more prominent,and more conductive to the analysis of subsequent applications.In this paper,the remote sensing images and medical images are taken as the research object,and the proposed algorithm is verified as follows:Firstly,a remote sensing image enhancement algorithm based on NSCT combing improved fuzzy contrast is proposed.First,the original image is decomposed into a low frequency subband and several high frequency subbands by NSCT;the linear transformation can be used to improve the overall contrast by modifying the low frequency subband;then,the improved threshold function is used to reduce the noise by amending the coefficient of high frequency subbands;finally,the improved fuzzy contrast is used to adjust the coefficients of NSCT inverse transformation,which can further improve the image edge contour information and the definition.It can be seen from the experimental results that the proposed algorithm in this paper is superior to the traditional enhancement methods in the objective index,and the subjective visual effect of the image has been greatly improved.Second,a new medical image enhancement method is proposed by applying the improved Gamma correction to the Shearlet domain.The improved gamma correction is used to deal with the low frequency part of the shearlet decomposition,then,the distortion of the image background information is corrected to adjust the overall contrast of the image.The improved adaptive threshold function that is proposed in preceding part of the text is utilized to denoise the high frequency part;finally,the reconstructed image of the shearlet inverse transformation is highlighted the details of the image by applying the improved fuzzy contrast enhancement.The experimental results show that the proposed algorithm is superior to other comparative algorithms in the objective evaluation of the peak signal-to –noise ratio(PSNR),the structure similarity of index measure(SSIM),and the mean absolute difference(MAE),especially the PSNR improvement is more obvious.These results show that the proposed algorithm can not only suppress the noise effectively,but also improve the image contrast.Compared with other comparative methods,the algorithm can get better visual effect.