Salt‐and‐pepper denoising method for colour images based on tensor low‐rank prior and implicit regularization

• Published in: IET image processing 2023-02, Vol.17 (3), p.886-900
• Main Authors: Zhang, Jun, Li, Zhao‐yang, Wang, Ling‐zhi, Chen, Ying‐pin
• Format: Article
• Language: English
• Subjects: data‐driven; FFDNet; model‐driven; parallel matrix factorization; salt and pepper denoising
• ISSN: 1751-9659; 1751-9667
• DOI: 10.1049/ipr2.12680

Most of the information obtained by humans comes from colour images. However, salt‐and‐pepper noise (SPN) during signal acquisition, encoding, transmission, and decoding easily interferes with the quality of colour images. Most existing SPN denoising methods decompose a colour image into three independent matrices according to the colour channel and then recover each channel signal independently, ignoring the strong data correlation between channels. In addition, most existing SPN denoising methods apply only a single model‐driven or data‐driven approach and fail to take the advantages of their combination fully. Therefore, we first regard a colour image contaminated by SPN as the sum of an SPN tensor and a tensor with missing data. In this manner, we transform the denoising problem into a low‐rank tensor reconstruction problem. We then introduce a model‐driven‐based parallel matrix factorization low‐rank tensor reconstruction algorithm and a data‐driven‐based FFDNet denoising network to restore the colour image better. The proposed method not only enhances the similarity of the colour image channels but also explores the deep prior of the colour image to capture the image details. Finally, the proposed method is compared with some advanced denoising methods. The results show that the proposed method achieves a competitive denoising performance. 1) In our article, color images are no longer three independent matrixes, but a tensor with a low‐rank structure. Under this assumption, the noise‐contaminated color image is regarded as the sum of a tensor with missing data and a salt and pepper noise tensor. In this way, the color image denoising is subtly transformed into a low‐rank tensor recovery problem. 2) The model‐driven method (TMac) is effectively combined with the data‐driven method (DP3). Thus, the proposed model only mines the information similarity between channels but also explores the data's deep prior knowledge within the channel.