政大機構典藏-National Chengchi University Institutional Repository(NCCUR):Item 140.119/55471
English  |  正體中文  |  简体中文  |  Post-Print筆數 : 27 |  全文筆數/總筆數 : 113303/144284 (79%)
造訪人次 : 50809505      線上人數 : 790
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTU 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://nccur.lib.nccu.edu.tw/handle/140.119/55471


    題名: 基於延展式區域三元化樣式的物件描述方法
    其他題名: Object Description Using Exntended Local Ternary Patterns
    作者: 廖文宏
    貢獻者: 國立政治大學資訊科學系
    行政院國家科學委員會
    關鍵詞: 延展式區域三元化樣式;物件描述
    日期: 2010
    上傳時間: 2012-11-12 11:05:06 (UTC+8)
    摘要: 開發強健且具效率的物件辨識演算法，是電腦視覺領域中十分重要，但也極具挑戰性的議題，除了外在環境變因的不可控制性，影響影像分析與特徵擷取的穩定度，進而增加辨識的困難度外，使用視覺資訊，還有一項最大問題，就是如何從龐大的資料中，進行有效率的運算，找出所需追蹤或辨識的特徵，進而獲得辨識或理解週遭事物的能力。穩定且具代表性的特徵描述方法是發展一個有效的物件辨識核心的重要關鍵。區域二元樣式(local binary pattern, LBP)是目前研究中經常被使用的特徵，LBP有著易於計算、適用時機廣的特性，但也存在若干缺點，包含抗噪性與直方圖維度問題，本研究嘗試改善區域二元樣式，提出新的延展式區域三元樣式(Extended Local Ternary Pattern, ELTP)，並就抗噪性、描述力與計算複雜度等面向與原始的LBP 進行分析與比較。在定義ELTP的過程中，除了理論面的推導，許多效能必須透過實驗來驗證，因此我們計畫進行一連串的測試，包含材質分析、背景建模、人臉辨識、表情識別等物件辨識的實務應用，藉此評估LBP與ELTP的優缺點。
    Robust and efficient object recognition is an important, yet challenging problem in computer vision. It is known that image acquisition and feature extraction process are easily interfered by the variability of the operating environments. The situation is worsened by the huge amount of data needed to be processed such that scene analysis and image understanding can be accomplished. Identifying a stable and effective feature descriptor is a key step in establishing a functional object recognition system. The local binary pattern (LBP) operator has been proved to be a computationally efficient local texture descriptor and has found many useful applications. However, its sensitivity to noise and the high dimensionality of histogram associated with a medium size neighborhood has raised some concerns. In this research, we attempt to improve the original LBP and propose a novel extension named extended local ternary pattern (ELTP). We will investigate the characteristics of ELTP in terms noise immunity, discriminability and computational efficiency. There exist different ways to define an ELTP. A proper definition requires strong theoretical foundations as well as validation through experiments. We plan to examine the efficacy of the proposed ELTP in several object recognition tasks, including texture analysis, background modeling, face and facial expression recognition.
    關聯: 商品化
    學術補助
    研究期間:9908~ 10007
    研究經費:604仟元
    資料類型: report
    顯示於類別:[資訊科學系] 國科會研究計畫

    文件中的檔案:

    檔案 大小格式瀏覽次數
    992221E004012.pdf3231KbAdobe PDF21888檢視/開啟


    在政大典藏中所有的資料項目都受到原著作權保護.


    社群 sharing

    著作權政策宣告 Copyright Announcement
    1.本網站之數位內容為國立政治大學所收錄之機構典藏，無償提供學術研究與公眾教育等公益性使用，惟仍請適度，合理使用本網站之內容，以尊重著作權人之權益。商業上之利用，則請先取得著作權人之授權。
    The digital content of this website is part of National Chengchi University Institutional Repository. It provides free access to academic research and public education for non-commercial use. Please utilize it in a proper and reasonable manner and respect the rights of copyright owners. For commercial use, please obtain authorization from the copyright owner in advance.

    2.本網站之製作，已盡力防止侵害著作權人之權益，如仍發現本網站之數位內容有侵害著作權人權益情事者，請權利人通知本網站維護人員(nccur@nccu.edu.tw)，維護人員將立即採取移除該數位著作等補救措施。
    NCCU Institutional Repository is made to protect the interests of copyright owners. If you believe that any material on the website infringes copyright, please contact our staff(nccur@nccu.edu.tw). We will remove the work from the repository and investigate your claim.
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - 回饋