ASIA unversity:Item 310904400/5850
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 94286/110023 (86%)
Visitors : 21691842      Online Users : 565
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU 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
    Home ‧ Login ‧ Upload ‧ Help ‧ About ‧ Administer Goto mobile version
    ASIAIR > College of Computer Science > Proceedings >  Item 310904400/5850


    Please use this identifier to cite or link to this item: http://asiair.asia.edu.tw/ir/handle/310904400/5850


    Title: Automation of Image Contrast Enhancement Based on Intensity-pair Distribution
    Other Titles: 以強度對分佈為基礎的自動化影像對比增強
    Authors: 戴顯權;張蓺英;王乃慶
    Contributors: 國立成功大學電機工程所;國立成功大學電通所
    Keywords: 強度對分佈;對比增強;自動化對比增強 intensity-pair;contrast enhancement;automation of contrast enhancement
    Date: 2007-12-20
    Issue Date: 2009-12-15
    Publisher: 亞洲大學資訊學院;中華電腦學會
    Abstract: 強度對分佈(intensity-pair distribution)是近年來針對影像對比增強的新研究方法。它除了能有效地增強對比之外，亦能使得對比增強後雜訊不至於被放大。在此演算法中留有相當多可提供使用者自行調整的參數。而在適當的參數設定下，強度對分佈演算法確實有著令人激賞的表現。但是目前此種演算法中，並無有效選擇參數的方法。本文提出了一有效的準則來選擇參數，使得此演算法的效果能夠有效地發揮，並且透過疊代的方式，使得參數選擇具有自動化的能力。Intensity-pair distribution was recently proposed to enhance the contrast of an image without noise amplification. There are several parameters left in that algorithm. With proper parameter combinations, the algorithm performs very well, but there is no effective method of parameter selection mentioned. In this paper, we proposed an effective criterion to decide proper parameters to maximize its performance. Automation of parameter selection can easily be done by iteratively using proposed algorithm.
    Relation: 2007NCS全國計算機會議 12-20~21
    Appears in Collections:[College of Computer Science] Proceedings

    Files in This Item:

    File SizeFormat
    4076.pdf4334KbAdobe PDF8176View/Open


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

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