3D Filtering by Block Matching and Convolutional Neural Network for Image Denoising

• Published in: Journal of computer science and technology Vol. 33; no. 4; pp. 838 - 848
• Main Authors: Zou, Bei-Ji, Guo, Yun-Di, He, Qi, Ouyang, Ping-Bo, Liu, Ke, Chen, Zai-Liang
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.07.2018; Springer; Springer Nature B.V; School of Information Science and Engineering, Central South University, Changsha 410083, China; Center for Ophthalmic Imaging Research, Central South University, Changsha 410083, China%Center for Information and Automation of China Nonferrous Metals Industry Association, Changsha 410011, China; Center for Information and Automation of China Nonferrous Metals Industry Association, Changsha 410011, China%School of Information Science and Engineering, Central South University, Changsha 410083, China
• Subjects: Analysis; Artificial Intelligence; Artificial neural networks; Collaboration; Computer Science; Data Structures and Information Theory; Filtration; Image quality; Information Systems Applications (incl.Internet); Matching; Neural networks; Noise; Noise intensity; Noise levels; Noise reduction; Regular Paper; Regularization methods; Science; Signal to noise ratio; Software Engineering; Sparsity; Theory of Computation; denoising; block matching; 3D filtering; convolutional neural network (CNN)
• ISSN: 1000-9000; 1860-4749
• DOI: 10.1007/s11390-018-1859-7

Block matching based 3D filtering methods have achieved great success in image denoising tasks. However, the manually set filtering operation could not well describe a good model to transform noisy images to clean images. In this paper, we introduce convolutional neural network (CNN) for the 3D filtering step to learn a well fitted model for denoising. With a trainable model, prior knowledge is utilized for better mapping from noisy images to clean images. This block matching and CNN joint model (BMCNN) could denoise images with different sizes and different noise intensity well, especially images with high noise levels. The experimental results demonstrate that among all competing methods, this method achieves the highest peak signal to noise ratio (PSNR) when denoising images with high noise levels ( σ > 40), and the best visual quality when denoising images with all the tested noise levels.