English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 55025/89277 (62%)
造访人次 : 10606907      在线人数 : 25
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: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/76036


    题名: Image stylisation
    作者: Yen, Shwu-huey;Yeh, Jih-pin;Lin, Hwei-jen;Lee, Tai-kuang;Pai, Yi-chun
    贡献者: 淡江大學資訊工程學系
    关键词: stained glass;image stylisation;segmentation;Voronoi diagram;seed;back-propagation neural network (BPNN)
    日期: 2012
    上传时间: 2012-04-30 18:00:09 (UTC+8)
    出版者: Leeds: Maney Publishing
    摘要: We propose a flexible image stylisation system for reforming a source image into a
    stained-glass style or some other style desired by users. It consists of three stages including image segmentation, colour or texture allocation and synthesis of calmes. Each stage provides some options for users to choose from. The system provides three options of image
    segmentation for the users to choose from, including automatic, semi-automatic and manual image segmentation. The automatic option randomly generates seeds in the image region, calculates the distance between each seed and each pixel and then assigns each pixel to the nearest seed region to accomplish image segmentation. The semi-automatic one segments the image according to the seeds provided by the user. The user then repeatedly adjusts the result by deleting or adding some seeds. The last version involves manual image segmentation performed by the users. The next step in segmentation is colour or texture allocation. Each segmented region is allocated with the colour or texture of reference images chosen from a pre-built database. The proposed system provides many options for this allocation, allowing the users to select from a variety of methods of texture or colour allocation. A unique feature of stained glass is that it is held together with lead, zinc, brass or copper strips called calmes. We use a back-propagation neural network to train a calme generator using an image of line drawing as the input together with an image of the corresponding calme of the line drawing as the output. The users can choose whether or not to put the synthesised calmes on the resulting images. The proposed system is easy to use and very flexible. It provides many options for users to stylise an image into a variety of stylised results. Our experiments show that the proposed system can generate a wide range of satisfactory results.
    關聯: Imaging Science Journal 60(5), pp.248-255
    DOI: 10.1179/1743131X11Y.0000000046
    显示于类别:[資訊工程學系暨研究所] 期刊論文

    文件中的档案:

    档案 描述 大小格式浏览次数
    1368-2199_60(5)p248-255.pdf1015KbAdobe PDF101检视/开启
    index.html0KbHTML175检视/开启

    在機構典藏中所有的数据项都受到原著作权保护.

    TAIR相关文章

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