Blind deblurring and denoising via a learning deep CNN denoiser prior and an adaptive L0‐regularised gradient prior for passive millimetre‐wave images. Issue 17 (18th March 2021)

• Record Type: Journal Article
• Authors: Sun, Dianjun; Shi, Yu; Feng, Yayuan
• Is Part Of: IET image processing. Volume 14:Issue 17(2020)
• Page Start: 4774
• Page End: 4784
• Publication Date: 2021-03-18
• Subjects: image denoising -- deconvolution -- image restoration -- iterative methods -- learning (artificial intelligence) -- optical transfer function -- millimetre wave imaging -- convolutional neural nets; learning deep CNN denoiser -- L0‐regularised gradient -- passive millimetre‐wave images -- optical imaging -- infrared imaging -- blurring resolution -- observed images -- PMMW images -- traditional image deblurring methods -- image noise -- point spread function estimation -- traditional image denoising methods -- biased PSF estimation -- denoising method -- deep denoising convolutional neural networks denoiser -- blind deblurring restoration model -- DnCNN denoising prior constraint -- latent clear image -- gradient domain -- nonblind deconvolution method -- blurred noise image -- latent image -- denoising network -- alternate iterative denoising -- final PSF estimation -- final clear image -- estimated PSF -- noise map; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2020.1193
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Passive millimetre‐wave (PMMW) imaging frequently suffers from blurring and low resolution due to the long wavelengths. In addition, the observed images are inevitably disturbed by noise. Traditional image deblurring methods are sensitive to image noise, even a small amount of which will greatly reduce the quality of the point spread function (PSF) estimation. In this paper, we propose a blind deblurring and denoising method via a learning deep denoising convolutional neural networks (DnCNN) denoiser prior and an adaptive ‐regularized gradient prior for passive millimetre‐wave images. First, a blind deblurring restoration model based on the DnCNN denoising prior constraint is established. Second, an adaptive ‐regularized gradient prior is incorporated into the model to estimate the latent clear image, and the PSF is estimated in the gradient domain. In a multi‐scale framework, alternate iterative denoising and deblurring are used to obtain the final PSF estimation and noise estimation. Ultimately, the final clear image is restored by non‐blind deconvolution. The experimental results show that the algorithm used in this paper not only has good detail recovery ability but is also more stable to different noise levels. The proposed method is superior to state‐of‐the‐art methods in terms of both subjective measure and visual quality.