English  |  正體中文  |  简体中文  |  Items with full text/Total items : 70588/70588 (100%)
Visitors : 23145506      Online Users : 523
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.ncu.edu.tw/handle/987654321/8814

    Title: 不同場景的膚色偵測與臉部定位;Skin Color Detection and Face Location in Different sceneries
    Authors: 林文章;Wen-Chang Lin
    Contributors: 資訊工程學系碩士在職專班
    Keywords: 膚色偵測;臉部定位;skin color detection;face location
    Date: 2009-01-07
    Issue Date: 2009-09-22 11:35:16 (UTC+8)
    Publisher: 國立中央大學圖書館
    Abstract: 我們常需要用電腦來自動擷取影像中關於”人”的資訊。就本論文的膚色偵測與臉部定位主題,人類解決這個問題其實相當簡單,但交給電腦來做就變得複雜許多。若要再能適用於不同場景及天候,更是困難。過去有許多方法被提出來解決這類的問題;大部份的方法都是定義一組膚色的像素顏色範圍,再逐點偵測影像中的所有像素;若該像素經計算後是介於事先定義好的範圍內即判定為膚色。找到膚色後再透過後續的步驟進一步確認那些區域是人臉,那些區域不是,以此來尋找影像中的人臉。 我們發現,在不同場景下所拍得的影像中,膚色會有偏移,光線照射的角度對於膚色偵測的影響尤大。因此以上述的固定膚色範圍於是不可能能適用於不同場景的膚色偵測,因此我們選了三種場景,歸納出這三個場景所各自需要的膚色範圍及後續的人臉定位方法。 本論文有三個研究議題: (i) 膚色偵測, (ii) 人臉定位,及 (iii) 解決不同場景所造成的問題。在第一主題中,我們定義膚色範圍來初步找到膚色候選點,我們不但比較了歷年來膚色範圍準則,也提出我們自已的膚色範圍。在偵測膚色像素前,我們先將膚色的表示式做幾種轉換,以降低光線對於膚色判定的影響。在第二個主題中,我們針對可能的臉部矩形區塊找眼睛及嘴巴特徵,並提出我們針對嘴巴特徵點的改良公式。在第三個主題中,我們在三個場景中實驗我們的系統,並微調這三個場景適用的準則。 The objective of this study is to detect human faces in images. Many methods have been proposed to detect skin color and then extract the face regions based on the face features. Actually, the face detection is easy for most human beings, but is difficult for computerized autonomous systems. The hardness comes from the variant of skin color and influence of the weather conditions. In this study, we indifidually consider three different sceneries to detect the human face such that the detection is less influenced by the weather conditions. The three sceneries are cloudy outdoor, sunny outdoor, and indoor environments. In each scenery, we define the skin color ranges based on several color methods. Thenextract all skin pixels, and refine the skin-color regions. Thirdly, we use several region features to delete the non-face regions. At last, we extract the eye and mouth from each candidate skin-color regions to verify the faces. The contribution of this study includes: (i) new color transform concept for extract more accurate skin color. (ii) New formula for eye detection in YCbCr color space. (iii) New formula for mouth detection in YCbCr color space.
    Appears in Collections:[資訊工程學系碩士在職專班 ] 博碩士論文

    Files in This Item:

    File SizeFormat

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

    社群 sharing

    ::: Copyright National Central University. | 國立中央大學圖書館版權所有 | 收藏本站 | 設為首頁 | 最佳瀏覽畫面: 1024*768 | 建站日期:8-24-2009 :::
    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback  - 隱私權政策聲明