1. NCCU Academic Hub
  2. 學術產出
  3. College of Informatics
  4. Periodical Articles
  5. Item

學術產出-Periodical Articles

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

題名 Image Denoising Using Adaptive and Overlapped Average Filtering and Mixed-Pooling Attention Refinement Networks
作者 彭彥璁
Peng, Yan-Tsung
Lin, Ming-Hao
Hou, Zhi-Xiang
Cheng, Kai-Han
Wu, Chin-Hsien
貢獻者 資科系
關鍵詞 image denoising ;  overlapped averaging ;  mixed-pooling attention
日期 2021-05
上傳時間 23-Dec-2021 15:41:09 (UTC+8)
摘要 Cameras are essential parts of portable devices, such as smartphones and tablets. Most people have a smartphone and can take pictures anywhere and anytime to record their lives. However, these pictures captured by cameras may suffer from noise contamination, causing issues for subsequent image analysis, such as image recognition, object tracking, and classification of an object in the image. This paper develops an effective combinational denoising framework based on the proposed Adaptive and Overlapped Average Filtering (AOAF) and Mixed-pooling Attention Refinement Networks (MARNs). First, we apply AOAF to the noisy input image to obtain a preliminarily denoised result, where noisy pixels are removed and recovered. Next, MARNs take the preliminary result as the input and output a refined image where details and edges are better reconstructed. The experimental results demonstrate that our method performs favorably against state-of-the-art denoising methods. 
關聯 Mathematics, pp.1130
資料類型 article
DOI https://doi.org/10.3390/math9101130
dc.contributor 資科系-
dc.creator (作者) 彭彥璁-
dc.creator (作者) Peng, Yan-Tsung-
dc.creator (作者) Lin, Ming-Hao-
dc.creator (作者) Hou, Zhi-Xiang-
dc.creator (作者) Cheng, Kai-Han-
dc.creator (作者) Wu, Chin-Hsien-
dc.date (日期) 2021-05-
dc.date.accessioned 23-Dec-2021 15:41:09 (UTC+8)-
dc.date.available 23-Dec-2021 15:41:09 (UTC+8)-
dc.date.issued (上傳時間) 23-Dec-2021 15:41:09 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/138324-
dc.description.abstract (摘要) Cameras are essential parts of portable devices, such as smartphones and tablets. Most people have a smartphone and can take pictures anywhere and anytime to record their lives. However, these pictures captured by cameras may suffer from noise contamination, causing issues for subsequent image analysis, such as image recognition, object tracking, and classification of an object in the image. This paper develops an effective combinational denoising framework based on the proposed Adaptive and Overlapped Average Filtering (AOAF) and Mixed-pooling Attention Refinement Networks (MARNs). First, we apply AOAF to the noisy input image to obtain a preliminarily denoised result, where noisy pixels are removed and recovered. Next, MARNs take the preliminary result as the input and output a refined image where details and edges are better reconstructed. The experimental results demonstrate that our method performs favorably against state-of-the-art denoising methods. -
dc.format.extent 5079504 bytes-
dc.format.mimetype application/pdf-
dc.relation (關聯) Mathematics, pp.1130-
dc.subject (關鍵詞) image denoising ;  overlapped averaging ;  mixed-pooling attention-
dc.title (題名) Image Denoising Using Adaptive and Overlapped Average Filtering and Mixed-Pooling Attention Refinement Networks-
dc.type (資料類型) article-
dc.identifier.doi (DOI) 10.3390/math9101130-
dc.doi.uri (DOI) https://doi.org/10.3390/math9101130-