English  |  正體中文  |  简体中文  |  Items with full text/Total items : 55178/89446 (62%)
Visitors : 10661739      Online Users : 18
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/987654321/104258

    Title: An UM-based silhouette-crease edge enhancement for noisy images
    Authors: Shwu-Huey Yen;Tai-Kuang Li;Chun-Hui Wang
    Keywords: unsharp masking;UM;silhouette edges;crease edges;detail variance;background variance;UM-based edge enhancement;noisy images;image processing;noise suppression;noise smoothing;night images
    Date: 2015
    Issue Date: 2016-01-06 10:53:14 (UTC+8)
    Abstract: This paper presents an improved unsharp masking (UM) technique that enhances the quality and suppresses noises for the images acquired from a noisy environment such as taken during night time. Our approach employs noise smoothing and the idea that important edges should be enhanced more than minor edges. Edges are classified as silhouette and crease edges (major and minor edges) according to their lengths. An adaptive weighting method is used to enhance the edges. In this way, the major edges (silhouette) are sharpened more than minor edges (crease). The proposed method is examined on night images as well as noisy images. It is also compared to existing UM-based methods with satisfying results.
    Relation: International Journal of Computational Science and Engineering 10(4), pp.327-335
    DOI: 10.1504/IJCSE.2015.070989
    Appears in Collections:[Graduate Institute & Department of Computer Science and Information Engineering] Journal Article

    Files in This Item:

    File Description SizeFormat
    顏淑惠(An UM-based).pdf638KbAdobe PDF27View/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