Deep Convolutional Neural Network Based on Multi-Scale Feature Extraction for Image Denoising

被引：6

作者：

Zhang, Jing ^{[1
]}

Sang, Liu ^{[1
]}

Wan, Zekang ^{[1
]}

Wang, Yuchen ^{[1
]}

Li, Yunsong ^{[1
]}

机构：

[1] Xidian Univ, State Key Lab Integrated Serv Networks, Xian, Peoples R China

来源：

2020 IEEE INTERNATIONAL CONFERENCE ON VISUAL COMMUNICATIONS AND IMAGE PROCESSING (VCIP) | 2020年

关键词：

image denoising; multi-scale; convolutional network; diamond;

D O I：

10.1109/vcip49819.2020.9301843

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

With the development of deep learning, many methods on image denoising have been proposed processing images on a fixed scale or multi-scale which is usually implemented by convolution or deconvolution. However, excessive scaling may lose image detail information, and the deeper the convolutional network the easier to lose network gradient. Diamond Denoising Network (DmDN) is proposed in this paper, which mainly based on a fixed scale and meanwhile considering the multi-scale feature information by using the Diamond-Shaped (DS) module to deal with the problems above. Experimental results show that DmDN is effective in image denoising.

引用

页码：213 / 216

页数：4

共 50 条

[41] Image fusion algorithm based on multi-scale detail siamese convolutional neural network
Liu Bo
Han Guang-liang
Luo Hui-yuan
[J]. CHINESE JOURNAL OF LIQUID CRYSTALS AND DISPLAYS, 2021, 36 (09) : 1283 - 1293
[42] Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring
Nah, Seungjun
Kim, Tae Hyun
Lee, Kyoung Mu
[J]. 30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 257 - 265
[43] Multi-Scale Dilated Convolutional Neural Network for Hyperspectral Image Classification
Shanshan Zheng
Wen Liu
Rui Shan
Jingyi Zhao
Guoqian Jiang
Zhi Zhang
[J]. Journal of Harbin Institute of Technology(New series), 2021, 28 (04) : 25 - 32
[44] Multi-scale Convolutional Neural Network for SAR Image Semantic Segmentation
Duan, Yiping
Tao, Xiaoming
Han, Chaoyi
Qin, Xiaowei
Lu, Jianhua
[J]. 2018 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM), 2018,
[45] Multi-Scale Deep Neural Network Microscopic Image Segmentation
Wu, Xundong
Wu, Yong
Stefani, Enrico
[J]. BIOPHYSICAL JOURNAL, 2015, 108 (02) : 473A - 473A
[46] FCNet: a deep neural network based on multi-channel feature cascading for image denoising
Feng, Siling
Qi, Zhisheng
Zhang, Guirong
Lin, Cong
Huang, Mengxing
[J]. JOURNAL OF SUPERCOMPUTING, 2024, 80 (12): : 17042 - 17067
[47] Dynamic Texture Feature Extraction Based on multi-scale Convolutional Autoencoder
Yi, Huimin
Zhu, Ziqi
Gu, Yangwei
[J]. 2021 4TH INTERNATIONAL CONFERENCE ON INTELLIGENT AUTONOMOUS SYSTEMS (ICOIAS 2021), 2021, : 108 - 112
[48] Synthetic aperture radar images denoising based on multi-scale attention cascade convolutional neural network
Shan, Huilin
Fu, Xiangwei
Lv, Zongkui
Xu, Xingchen
Wang, Xingtao
Zhang, Yinsheng
[J]. MEASUREMENT SCIENCE AND TECHNOLOGY, 2023, 34 (08)
[49] Transfer Learning-Based Multi-Scale Denoising Convolutional Neural Network for Prostate Cancer Detection
Chui, Kwok Tai
Gupta, Brij B.
Chi, Hao Ran
Arya, Varsha
Alhalabi, Wadee
Ruiz, Miguel Torres
Shen, Chien-Wen
[J]. CANCERS, 2022, 14 (15)
[50] Fault diagnosis of rolling bearing based on feature fusion of multi-scale deep convolutional network
Wang, Nini
Ma, Ping
Zhang, Hongli
Wang, Cong
[J]. Taiyangneng Xuebao/Acta Energiae Solaris Sinica, 2022, 43 (04): : 351 - 358

← 1 2 3 4 5 →