English  |  正體中文  |  简体中文  |  Items with full text/Total items : 52084/87215 (60%)
Visitors : 8915526      Online Users : 65
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: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/35035

    Title: 灰階影像之最佳彩色化
    Other Titles: Optimal colorization for grayscale images
    Authors: 吳軍逸;Wu, Chun-yi
    Contributors: 淡江大學資訊工程學系碩士班
    林慧珍;Lin, Hwei-jen
    Keywords: 彩色化;YCbCr顏色空間;擴散;線性規劃;線性內插;互動式;Colorization;YCbCr color space;Expansion;Linear programming;Linear interpolation;Interactive
    Date: 2007
    Issue Date: 2010-01-11 05:56:08 (UTC+8)
    Abstract: 灰階影像彩色化是一門相當重要的領域。然而由於灰階影像只擁有一維的資訊,也就是只有亮度的資訊,因此若想要將灰階影像轉換成擁有三維資訊,如紅、綠、藍的彩色影像,必須藉由使用者或者是參考的圖形所提供的顏色資訊,配合灰階影像的亮度來進行彩色化的工作。然而直接以RGB顏色空間進行運算,會因為三個維度的關連性過高導致運算上的困難,所以在此我們是利用YCbCr的顏色空間作為彩色化的基礎。彩色化的領域中,最常被討論的議題就是邊緣判斷的問題。而本論文分兩階段來解決區域判定的問題,第一階段以擴散的方式,猶如水波漣漪一般,初步決定顏色的區域;第二階段針對未決定所屬顏色的部份,利用計算其與顏色區域的關係資訊,來完成顏色區域的判斷。接著以線性規劃求出每個顏色區域內,原灰階影像最亮與最暗的像素點之最佳顏色資訊,再利用線性內插法,將整個顏色區域完成彩色化的工作。本論文是使用者為導向的著色方法,屬於互動式的著色系統,藉由提供顏色、亮度、區域關係判定的選擇,讓使用者彈性調整彩色化的結果。
    This paper proposes a user friendly interactive colorization system that utilizes simple regional judgment and linear programming to accomplish the work of colorization. The system provides several colorization modes for users to select by themselves. User only needs to simply scribble on the given gray-level image and select a coloring mode they want. Experimental results show that our system gives natural and satisfactory coloring results.
    Appears in Collections:[資訊工程學系暨研究所] 學位論文

    Files in This Item:

    File SizeFormat

    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