English  |  正體中文  |  简体中文  |  Items with full text/Total items : 62805/95882 (66%)
Visitors : 3982125      Online Users : 639
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: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/35906


    Title: 粒子群最佳化3D角度搜尋之人臉辨識系統
    Other Titles: PSO accelerated 3D face angle searching system for face recognition
    Authors: 石孟憲;Shih, Meng-shian
    Contributors: 淡江大學電機工程學系碩士班
    謝景棠;Hsieh, Ching-tang
    Keywords: 粒子群最佳化;人臉辨識;3D模型輔助人臉辨識;particle swarm optimization;face recognition;3D model based face recognition
    Date: 2009
    Issue Date: 2010-01-11 07:18:28 (UTC+8)
    Abstract: 人臉辨識技術在以像處理的領域中已成為當今最熱門且最具挑戰性的主題之一。而傳統的2D人臉辨識系統對於任一角度的人臉辨識上來說是有一定的角度容忍範圍存在,所以以3D模型為輔助的人臉辨識系統在最近這幾年來被人提出來對這方面做改善。

    而傳統的3D模型為輔助人臉辨識系統在對任一角度的人臉做角度檢索搜尋時耗時相當的久,所以本篇論文提出搭配粒子群最佳化的演算法來加速人臉角度檢索的步驟。
    Face recognition has been one of the most popular topic of image processing. But there always exist a problem in conventional 2D face recognition system. It is the limitation of tolerance from face poses. For solving this problem, 3D model based face recognition has been proposed in recent years.

    But it took a long time while matching the angles from an random head pose in conventional 3D model based face recognition system. So we accelerated the angle matching step by combining the Particle Swarm Optimization with 3D model based face recognition system.
    Appears in Collections:[Graduate Institute & Department of Electrical Engineering] Thesis

    Files in This Item:

    File SizeFormat
    0KbUnknown460View/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