English  |  正體中文  |  简体中文  |  Items with full text/Total items : 54371/62179 (87%)
Visitors : 9058358      Online Users : 85
RC Version 6.0 © Powered By DSPACE, MIT. Enhanced by NTHU 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://nthur.lib.nthu.edu.tw/dspace/handle/987654321/86623

    Title: 人臉辨識基於局部二元模式的方向
    Authors: 沈怡康
    Shen, Yi-Kang
    Description: GH02101062610
    Date: 2014
    Keywords: 人臉辨識;流明不變;尺度不變特徵轉換;局部二元圖
    face recognition;illumination invariance;Scale-invariant feature transform;local binary patterns
    Abstract: 流明改變和臉部表情在一般的環境中常常會造成人臉辨識的效率降低.傳統的尺度不變特徵轉換對於旋轉及大小有著良好的效果,但是在光影變化中辨識率則降低而且也需要較多的運算時間.因此,我們提出了一種較快的描述還有比對方法用在尺度不變特徵轉換上,利用局部二元圖方向還有直方圖均衡化移除光影的影響.而此方法有下列的優點(1)有效的移除光影影響 (2)提取不同的臉部細節 (3)降低了計算的花費.另外,我們也提出使用感興趣區域(ROI)來移除無用的特徵點,藉此降低我們的運算時間並且維持一定的辨識率.實驗結果顯示我們的方法在extended YaleB database辨識率比原本的方法好了0.8%並且降低了28.3%的運算時間,在FERET fc database中達到辨識率比原本的方法好了1.2%,並且比原本的SQI方法降低了28.6%的計算時間.而ROI的系統則在extended YaleB database中降低了61.9%的運算時間,還達到了75.7%的辨識率,在FERET fa database中降低了57.4%的運算時間,還達到了95.2%的辨識率
    Illumination variation and facial expression generally causes performance degradation of face recognition systems under real-life environments. In traditionally, Scale-invariant feature transform (SIFT) has good result for scale-variance and rotation, but the recognition is lower in illumination variation, and requires high computation complexity. Therefore, we propose a fast descriptor and matching method on SIFT, using the local binary patterns orientation and histogram equalization to remove the lighting effects. This method has the following advantages: (1) Remove the lighting influence effectively. (2) Extract different face details. (3) Reduce computational cost. We also propose using region of interest to remove the useless interest points for saving our computation time and maintaining the recognition rate. Experimental results demonstrate that our proposed has 0.8\% higher recognition rate than original and reduces 28.3\% computation time for FERET database has 1.2\% higher recognition rate than original and reduces 28.6\% computational time compared to original. In the ROI systems, experimental results demonstrate that our proposed reduces 61.9\% computation time and has 75.7\# recognition rates for FERET database has 95.2\% recognition rate original and reduces 57.4\% computational time.
    URI: http://nthur.lib.nthu.edu.tw/dspace/handle/987654321/86623
    Source: http://thesis.nthu.edu.tw/cgi-bin/gs/hugsweb.cgi?o=dnthucdr&i=sGH02101062610.id
    Appears in Collections:[資訊工程學系] 博碩士論文

    Files in This Item:

    File SizeFormat
    GH02101062610.pdf144KbAdobe PDF210View/Open


    SFX Query


    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback