淡江大學機構典藏:Item 987654321/34157
English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 64191/96979 (66%)
造訪人次 : 8151544      線上人數 : 7940
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
搜尋範圍 查詢小技巧：
  • 您可在西文檢索詞彙前後加上"雙引號"，以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋，建議至進階搜尋限定作者欄位，可獲得較完整資料
    •  進階搜尋


    請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/34157


    題名: 利用時空資訊之影片相似尋取
    其他題名: Similarity retrieval of videos based on spatio-temporal information
    作者: 葉智昇;Yeah, Chih-sheng
    貢獻者: 淡江大學資訊管理學系碩士班
    梁恩輝;Liang, En-hui
    關鍵詞: 空間關係;關係序列;最大完全子圖;spatial relation;relation number sequence;maximal complete subgraph
    日期: 2006
    上傳時間: 2010-01-11 04:59:00 (UTC+8)
    摘要: 隨著多媒體資料庫技術的發展，多媒體資料的數量愈來愈多，其中包括影像資料、影片資料等等。在影片資料庫中，影片中的每一個畫面可視為是一張靜態影像，因此影片的相似尋取技術可由影像相似尋取技術延伸而來。影像內容大致可分為低階視覺特徵(low-level visual feature)和高階關係特徵(high-level relationship feature)。而高階關係特徵中的空間關係(spatial relationships)則是常用衡量兩張影像之間的相似度的標準之一。在過去的研究中，多是以字串表示的方式來描述影像中物件對之間的空間關係，並以這種字串做為相似尋取之根據。在本篇論文中，我們對空間關係做編碼，並提出一個以編碼後的結果表示影片中兩兩物件一連串的空間關係變化的表示法，稱為關係序列(Relation Number Sequence，RNS)，並利用關係序列的內容做為相似尋取的依據。此外為了更客觀地表示相似程度，本篇論文以從圖(graph)中找出最大完全子圖(maximal complete subgraph)的方式，提供相似度的值。
    According to the improvement of multimedia techniques there are more and more multimedia data such as image and video. There are also many multimedia database including image database systems and video database systems. In video data, each frame of the video is exactly a still image. The techniques of video data similarity retrieval can be extended from that in image data. Image content can be categorized into low-level visual features and high-level relationship features. In high-level relationship, spatial relationships are usually used in determining the similarity between two images. In the previous researches, spatial relations between two objects are recorded by using string. These strings are then used to determine the similarity between two images.
    In this paper, we encode spatial relations by giving each of them a number. We use these numbers to represent the sequential spatial relation changes between two objects in the video. The sequences of number changes are called Relation Number Sequence (RNS for short). The RNSs are the criteria for determinant the similarity between two videos. In order to provide an objective similarity degree, we use the nodes of a maximal complete subgraph to represent the similarity between two videos.
    顯示於類別:[資訊管理學系暨研究所] 學位論文

    文件中的檔案:

    檔案 大小格式瀏覽次數
    0KbUnknown311檢視/開啟

    在機構典藏中所有的資料項目都受到原著作權保護.

    TAIR相關文章

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