English  |  正體中文  |  简体中文  |  Items with full text/Total items : 28611/40652
Visitors : 765888      Online Users : 49
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search

Please use this identifier to cite or link to this item: http://ntour.ntou.edu.tw:8080/ir/handle/987654321/18678

Title: 利用基因演算法分割與主值成份分析於人臉辨識
Faces Recognition Based on Genetic Algorithms Segmentation and Principal Component Analysis
Authors: Peng-Hsuan Jen
Contributors: NTOU:Department of Electrical Engineering
Keywords: 人臉偵測;人臉辨識;主值成份分析;基因演算法
Face detection;Face recognition;Principal Component Analysis;Genetic Algorithms
Date: 2008
Issue Date: 2011-07-04
Abstract: 本論文利用基因演算法與主值成份分析( Principal Component Analysis , PCA)技術實現一套人臉辨識的自動化系統。此系統主要分為兩部份:人臉偵測與人臉辨識。在人臉偵測部份,本論文採用基因演算法(genetic algorithms) ,利用人臉輪廓及橢圓形狀來正確的偵測出人臉的位置,並準確的圈出人臉。在人臉辨識的部份,先將不同的長寬比例的人臉影像訓練組,利用次取樣與雙線性內插法技術轉換成70*70像素(pixel)大小的影像,然後以PCA方法建構出人臉資料庫,在以歐氏距離(Euclidean distance)的大小來判定人臉身份。
This paper utilize Genetic Algorithms and Principal Component Analyzation to realize an automatic system for face recognition. This system is divided into two sections: the faces detection and the face recognition. On the part of faces detection, we detect the facial areas with the genetic algorithms to find the best-fit ellipse in order to cover the face contour that can include the greater area of face outline.On the part of face recognition, the facial image training sets are set to the size of 70x70 pixels by subsampling and Bilinear Interpolation. Finally, we use PCA method to compare the facial images with data bank, minimum Euclidean distance is used as the criterion for facial recognition.
URI: http://ethesys.lib.ntou.edu.tw/cdrfb3/record/#G0M95530085
Appears in Collections:[電機工程學系] 博碩士論文

Files in This Item:

File Description SizeFormat

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


著作權政策宣告: 本網站之內容為國立臺灣海洋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,請合理使用本網站之內容,以尊重著作權人之權益。
網站維護: 海大圖資處 圖書系統組
DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback