博碩士論文 109221006 完整後設資料紀錄

DC 欄位 語言
DC.contributor數學系zh_TW
DC.creator蔡承璋zh_TW
DC.creatorCheng-Chang Tsaien_US
dc.date.accessioned2022-7-15T07:39:07Z
dc.date.available2022-7-15T07:39:07Z
dc.date.issued2022
dc.identifier.urihttp://ir.lib.ncu.edu.tw:444/thesis/view_etd.asp?URN=109221006
dc.contributor.department數學系zh_TW
DC.description國立中央大學zh_TW
DC.descriptionNational Central Universityen_US
dc.description.abstract影像填補是一種影像處理的技術,主要的目的是利用得到的資訊去填補待填補的區域。影像填補的問題已經有許多不同的處理方法,主要分為三個類別:以擴散為基礎的方法、以補丁為基礎的方法、和深度學習法。本文採用稀疏表示與字典學習的架構,這樣的架構屬於以補丁為基礎的方法,主要的優勢是能較好地填補紋理的部分,相對於深度學習法利用許多不同的影像取得填補所需的資訊,本文所採用的方法則是利用同一張影像中待填補區以外的區域所得到的資訊進行填補,所以稱為單一影像填補方法。在整個方法中,字典扮演著最關鍵的角色,然而訓練一本字典通常需要相當長的時間,這是字典學習的最大缺點。為了改善這個問題,本文提出了一個基於分治法的演算法,主要的想法是經由解決許多較小問題,從而得到本來問題的解答,藉由這個演算法可以更有效率地訓練一本字典。最後,我們進行多個數值實驗以驗證該演算法的性能。zh_TW
dc.description.abstractImage inpainting is a technique that fills in the pixels in a missing data region. There are many different approaches in the literature for dealing with image inpainting problems. These approaches are categorized into three classes: diffusion-based methods, patch-based methods, and deep learning methods. In this thesis, we study image inpainting based on the dictionary learning and sparse representation framework, which is a patch-based method. Such an approach generally has better image texture results. Compared to deep learning methods, which acquire information from multiple images, our framework, called single-image inpainting, trains a dictionary with the information from the same image. However, training an efficient dictionary usually takes a lot of time. Therefore, we propose an algorithm based on the divide-and-conquer concept for learning a dictionary, which is computationally more efficient. We verify the algorithm’s performance with several test problems.en_US
DC.subject影像處理zh_TW
DC.subject影像填補zh_TW
DC.subject稀疏表示zh_TW
DC.subject字典學習zh_TW
DC.subjectADMMzh_TW
DC.subjectimage processingen_US
DC.subjectimage inpaintingen_US
DC.subjectsparse representationen_US
DC.subjectdictionary learningen_US
DC.subjectADMMen_US
DC.title一種基於稀疏字典學習的單一影像填補zh_TW
dc.language.isozh-TWzh-TW
DC.titleA Sparse Dictionary Learning-Based Method for Single Image Inpaintingen_US
DC.type博碩士論文zh_TW
DC.typethesisen_US
DC.publisherNational Central Universityen_US

若有論文相關問題,請聯絡國立中央大學圖書館推廣服務組 TEL:(03)422-7151轉57407,或E-mail聯絡  - 隱私權政策聲明