Open AccessA Hybrid CNN for Image Denoising
Author(s) -
Menghua Zheng,
Keyan Zhi,
Jiawen Zeng,
Chunwei Tian,
Lei You
Publication year - 2022
Publication title -
journal of artificial intelligence and technology
Language(s) - English
Resource type - Journals
ISSN - 2766-8649
DOI - 10.37965/jait.2022.0101
Subject(s) - convolution (computer science) , normalization (sociology) , convolutional neural network , computer science , block (permutation group theory) , artificial intelligence , noise reduction , pattern recognition (psychology) , residual , feature (linguistics) , context (archaeology) , deep learning , image (mathematics) , algorithm , artificial neural network , mathematics , paleontology , linguistics , philosophy , geometry , sociology , anthropology , biology
Deep convolutional neural networks (CNNs) with strong learning abilities have been used in the field of image super-resolution. However, some CNNs depends on a single deep network to training an image super-resolution model, which will have poor performance in complex screens. To address this problem, we propose a hybrid denoising CNN (HDCNN). HDCNN is composed of a dilated block (DB), RepVGG block (RVB) and feature refinement block (FB), a single convolution. DB combines a dilated convolution, batch normalization (BN), common convolutions, activation function of ReLU to obtain more context information. RVB uses parallel combination of convolution and BN, ReLU to extract complementary width features. FB is used to obtain more accurate information via refining obtained feature from the RVB. A single convolution collaborates a residual learning operation to construct a clean image. These key components make the HDCNN have good performance in image denoising. Experiment shows that the proposed HDCNN enjoys good denoising effect in public datasets.