English  |  正體中文  |  简体中文  |  Items with full text/Total items : 25248/25843 (98%)
Visitors : 5204109      Online Users : 61
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU 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://ir.lib.ksu.edu.tw/handle/987654321/14339


    Title: 基於影像辨識技術之家庭成員偵測系統
    Authors: 蔡哲民
    王建仁
    吳明昆
    Keywords: 數位家庭
    入侵偵測
    人員偵測
    Digital Home
    Intrusion Detection
    Human Detection
    Date: 2007-11-29
    Issue Date: 2008-01-027T04:45:03Z
    Abstract: 隨著資訊技術的進步與資訊產品價格的降低,將數位影像處理技術應用來改善日常家庭生活已經不再是遙不可及的事情。以往的偵測系統大多利用熱影像來偵測人員之外型、或透過近距離拍攝臉孔來進行辨別是否為入侵者或家庭成員。本文提出一個使用一般家庭防盜用之固定CCD 所取得之影像,依據家庭成員之衣著顏色、體型以及身高,來進行對家庭成員的辨識。由於影像判定難免會有誤差,因此本系統提供三種警戒模式,提供家庭成員依據需求來調整警報靈敏度,由實驗結果可得知,本系統擁有還不錯的人員偵測率。
    Successfully recognizing family members is important for home security. Image technique such as face recognition plays an important role in this task. Clear images are necessary to extract characteristics of the faces. However, image qualities are easily degraded due to low illumination, movements, face direction, etc., and results in poor recognition rates . On the other hand, shapes of human bodies are easier to be detected from images. In this paper, we proposed a family member recognition system based on the body shapes and colors of clothes. In field tests, this proposed system yields good recognition rates.
    Appears in Collections:[資訊科技學院 ] 2007年優質家庭生活科技(U-home)之關鍵技術研討會

    Files in This Item:

    File Description SizeFormat
    IE5.pdf226KbAdobe PDF2View/Open


    All items in KSUIR are protected by copyright, with all rights reserved.


    本網站之所有圖文內容授權為崑山科技大學圖書資訊館所有,請勿任意轉載或擷取使用。
    ©Kun Shan University Library and Information Center
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback