English  |  正體中文  |  简体中文  |  Items with full text/Total items : 49287/83828 (59%)
Visitors : 7153340      Online Users : 48
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/987654321/74406


    Title: 一個根據空間關係進行影片尋取之基因演算法
    Other Titles: A genetic algorithm for video retrieval based on spatial relations
    Authors: 張貴棠;Chang, Kuei-Tang
    Contributors: 淡江大學資訊管理學系碩士班
    梁恩輝
    Keywords: 影片尋取;相似尋取;基因演算法;影像相似度;Video Retrieval;Similarity Retrieval;Genetic Algorithm;Image Similarity
    Date: 2011
    Issue Date: 2011-12-28 18:33:21 (UTC+8)
    Abstract: 如何對龐大的多媒體資料進行尋取是一重要的研究議題。本研究是以影像相似度為基礎,將影像相似度延伸應用至影片相似尋取,利用影像在空間關係上的相似度,進行影片相似度之計算。本研究之目的是針對一參考影片,查詢參考影片中與查詢影片最為相似之片段。我們從參考影片中,隨機挑選多張影像組成一段影片,並計算此段影片與查詢影片的相似度,但隨機組合之結果數量龐大,對其一一計算相似度不是有效率之方法,所以,本研究加入基因演算法,利用其尋求近似最佳解之能力進行影片相似尋取。
    How to retrieve multimedia information is an important issue. Based on image similarity, our research extends to similarity retrieval for video. We measure video similarity according to spatial relation in images. Given a reference video, our objective is to retrieve the video segment in the reference video the most similar to query video. We select frames randomly from the reference video to compose them as a video segment and measure the similarity between it and the query video. But, the amount of random selection is very huge. It is not efficient to measure video similarity for each selection. Therefore, we propose the genetic algorithm to retrieve the video segment which is the most similar to query video in this paper.
    Appears in Collections:[資訊管理學系暨研究所] 學位論文

    Files in This Item:

    File SizeFormat
    index.html0KbHTML161View/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