Multi-Band Contourlet Transform For Adaptive Remote Sensing Image Denoising. (25th September 2019)

• Record Type: Journal Article
• Authors: Wang, Haijiang; Wang, Jingpu; Yao, Fuqi; Ma, Yongqiang; Li, Lihong; Yang, Qinke
• Is Part Of: Computer journal. Volume 63:Number 7(2020)
• Page Start: 1084
• Page End: 1098
• Publication Date: 2019-09-25
• Subjects: contourlet -- wavelet -- M-band -- remote sensing images -- denoising; Computers -- Periodicals; 005.1
• DOI: 10.1093/comjnl/bxz073
• Languages: English
• ISSNs: 0010-4620

Abstract

Abstract: The ability to remove noise from remote sensing images, while retaining the important features of the images, is becoming increasingly important. In this paper, we introduce the multi-band contourlet transform, a new method for adaptively denoising remote sensing images. We describe existing methods that use multi-resolution analysis transforms for denoising images and discuss their respective advantages and disadvantages. We then introduce our novel denoising method, which exploits the advantages of existing methods. We summarize the results of a comprehensive set of experiments designed to evaluate the performance of our method and compare it with the performance of existing methods. The results demonstrate that our method is superior to existing methods, both in terms of its ability to denoise images and to retain salient features of those images following denoising.