淡江大學機構典藏:Item 987654321/102549
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 62830/95882 (66%)
Visitors : 4038286      Online Users : 568
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
Scope Tips:
  • please add "double quotation mark" for query phrases to get precise results
  • please goto advance search for comprehansive author search
  • Adv. Search
    HomeLoginUploadHelpAboutAdminister Goto mobile version
    Please use this identifier to cite or link to this item: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/102549


    Title: 數位化文件雜訊清除方法探討與實作
    Other Titles: A method for eliminating noise generated by digital archiving
    Authors: 李杰;Lee, Chieh
    Contributors: 淡江大學資訊工程學系碩士在職專班
    汪柏;Wang, Bal
    Keywords: 型態學;雜訊消除;影像處理;Morphology;Noise Reduction;Image Processing
    Date: 2014
    Issue Date: 2015-05-04 09:58:36 (UTC+8)
    Abstract: 由於資訊科技與產品快速且多樣的發展與進步,除了早期的科學數據型資料外,近年來幾乎所有的資料如文字、聲音、圖(影)像等皆以數位方式呈現儲存,舉凡MP3、MP4、PDF、JPG等常見檔案皆為儲存數位化資料檔案,簡單的說存在於電腦儲存設備內並使用電腦周邊設備呈現的資料即為數位資料。數位方式所呈現與儲存的資料有著穩定、不會質變和搬運與複製方便等等優點,資料數位化已逐漸變成不可避免的一種趨勢了。然而較早期的一些舊資料(包含可能的有聲音、影像、文字或者圖像)為了長久保存以及方便管理目的而產生了數位化需求。而數位化資料品質與資料原始來源本身的保存好壞,以及數位化轉換方法與設備規格有者絕對的相關性。舊資料在數位轉換過程中往往可能發生失真、雜訊等不良現象,且長期累積的龐大數量傳統資料如以人工方式進行轉換及消除雜訊需耗費大量人力及時間,且可能因為處理人員主觀意識不同而產生出來的結果有所差異。在本論文中我們將針對紙本文件本身,及其轉換後所產生的文件做雜訊優化處理。目的希望取代人工方式並且能夠達到一定程度的雜訊辨識、與消除率。
    此篇論文主要研究關鍵在於如何識別及定位雜訊,利用地理模型概念統計影像密度、範圍與分佈位置等方式作為雜訊判斷及識別指標(Threshold),並藉由此值找出雜訊可能位置及區域與字體區分,再將目標文件進行分割消除、合併還原等處理。
    In this paper, we introduce a method for noise reduction in digitized document. We proposed a method that uses a successive procedure based on Mathematical Morphology concept to remove noise. We not only remove pepper and salt noise, but the noise generated by digitization process or the dirty file itself. This approach applies geographical model to image and then utilize segmentation, statistic and average method to elect proper threshold to remove noise area for sub image. Finally, we judge and restore the excessive reduction area. The goal of this paper is we hope to find a method to substitute for artificial noise reduction.
    Appears in Collections:[Graduate Institute & Department of Computer Science and Information Engineering] Thesis

    Files in This Item:

    File SizeFormat
    index.html0KbHTML156View/Open

    All items in 機構典藏 are protected by copyright, with all rights reserved.


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - Feedback