English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 62805/95882 (66%)
造访人次 : 3862590      在线人数 : 642
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
搜寻范围 查询小技巧:
  • 您可在西文检索词汇前后加上"双引号",以获取较精准的检索结果
  • 若欲以作者姓名搜寻,建议至进阶搜寻限定作者字段,可获得较完整数据
  • 进阶搜寻

    jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/76702

    题名: Image Inpainting Based on Geometric Similarity
    作者: Hung, Kuo-ming;Chen, Yen-liang;Hsieh, Ching-tang
    贡献者: 淡江大學電機工程學系
    关键词: Image Inpainting;Wavelet Transform;Repair Order;Fractal Geometry;GII
    日期: 2012-12
    上传时间: 2012-05-16 15:07:33 (UTC+8)
    出版者: Calgary: ACTA Press
    摘要: This paper proposed a new image inpainting method for restoring a large damaged area in the images called the “Geometric Image Inpainting Method (GII)”. The method was developed in response to several common problems encountered in the image inpainting process and provided a high-quality result compared to human vision. In the field of image inpainting, there are three key issues: texture analysis, repairing order and reconstruction of lost image pixels. Though there have been a lot of researches published, few combined all three key issues in their studies. We propose a novel image inpainting method integrating all three key issues at the same time. Experiments showed that the proposed image inpainting method offered better results than other existed methods.
    關聯: International Journal of Computers and Applications 34(1), pp.11-18
    DOI: 10.2316/Journal.202.2012.1.202-3020
    显示于类别:[電機工程學系暨研究所] 期刊論文


    档案 描述 大小格式浏览次数
    1111.pdf486KbAdobe PDF605检视/开启



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