English  |  正體中文  |  简体中文  |  Items with full text/Total items : 28607/40644
Visitors : 5916230      Online Users : 233
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search

Please use this identifier to cite or link to this item: http://ntour.ntou.edu.tw:8080/ir/handle/987654321/35759

Title: 低品質影像之畫質改良
Improvement of Low Quality Image
Authors: Jia-Hui Chu
Contributors: NTOU:Department of Computer Science and Engineering
Keywords: 低品質影像;色彩校正;影像解析度
Color correction;Low-quality image;Resolution synthesis
Date: 2012
Issue Date: 2013-10-07T02:58:48Z
Abstract: 在現今資訊發達的時代,我們能隨時隨地使用數位產品以獲取影像,例如由照相型數位產品所攝取的影像,但其影像品質會因為低廉的硬體設備產生失真的現象。本文則探討如何增進低品質影像的色彩品質,以達到影像色彩校正之目的。 本文提出一個改良性架構,針對低品質影像的色彩修正演算法。本架構是使用最大期望演算法(Expectation Maximization Algorithm, EM)獲取色彩參數,將低品質影像分類成數項的色彩偏差類,然後個別處理每項色彩偏差類中的影像,處理步驟分成三個階段來進行。首先,低品質的全域性色彩屬性係使用高斯混和模型(Gaussian Mixture Mode, GMM)以執行全域性M項的分類。第二步,在每一項全域性分類是以非線性色彩校正演算法處理輸入後的影像,在本文中稱此色彩校正方法為綜合解析度色彩校正(Resolution Synthesis Color Correction, RSCC),其色彩校正方法取決於輸入影像之區域性的色彩屬性。最後,綜合解析度色彩校正的預測子(RSCC Predictor)與全域性分類的權重值加總後,即可輸出色彩校正後的影像。
Currently, many devices are available to capture images. The image color is usually distorted if a low cost device is adapted. This thesis explores an approach of improving the low-quality digital images such as cell phone cameras through correction of distorted color images. This thesis proposes a color correction algorithm for the low-quality digital images. The proposed method uses the expectation maximization algorithm (EM algorithm) to obtain the parameters, which assign input images into many defects classes. There are three processing steps for the proposed method. First, global color attributes of the low quality input image are used in a Gaussian mixture model (GMM) framework to classify the input images into M predefined global classes. In the second step, the input image is processed with a non-linear color correction algorithm for each of the M global classes. This color correction algorithm, referred to as RSCC (resolution synthesis color correction), applies a spatially varying color correction, which is determined by the local color attributes of the input image. Last, the outputs of the RSCC predictors are combined using the global classification weights to generate the corrected color image.
URI: http://ethesys.lib.ntou.edu.tw/cdrfb3/record/#G0019957042
Appears in Collections:[資訊工程學系] 博碩士論文

Files in This Item:

File Description SizeFormat

All items in NTOUR are protected by copyright, with all rights reserved.


著作權政策宣告: 本網站之內容為國立臺灣海洋大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,請合理使用本網站之內容,以尊重著作權人之權益。
網站維護: 海大圖資處 圖書系統組
DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback