Focusing on the problems of non-adaption of filtering parameters and edge blur of Non-Local Means (NLM) algorithm, an improved NLM denoising algorithm based on image segmentation was proposed. The proposed algorithm is composed of two phases. In the first phase, the filtering parameter was determined according to the noise level and image structure, and traditional NLM algorithm was used to remove the noise and generate the rough clean image. In the second phase, the estimated clean image was divided into detailed region and background region based on pixel variance, and the image patches belonged to different regions were denoised separately. To effectively remove the noise, the back projection was utilized to make full use of the residual structure from the method noise of the first phase. The experimental results show that compared with traditional NLM and three NLM-improved algorithms, the proposed algorithm achieves higher Peak Signal-to-Noise Ratio (PSNR) and Structural SIMilarity (SSIM), while maintaining more structure details and edges, making the denoised image clear and retaining the complete real information.

In multi-label learning, since different labels may have their own characteristics, multi-label learning approach with label-specific features named LIFT has been proposed. However, the construction of label-specific features may increase the dimension of feature vector, which brings some redundant information in feature space. To solve this problem, a multi-label learning approach named FRS-LIFT was presented, which can implement label-specific feature reduction by fuzzy rough set. FRS-LIFT contains four steps: construction of label-specific features, reduction of feature dimensionality, training of classification models and prediction of unknown samples. The experimental results on 5 multi-label datasets show that, compared with LIFT, the proposed method can not only reduce the dimension of label-specific features, but also achieve satisfactory performances in 5 evaluation metrics.