National Chung Cheng University Institutional Repository:Item A095B0000Q/299
English  |  正體中文  |  简体中文  |  Items with full text/Total items : 889/889 (100%)
Visitors : 14796012      Online Users : 52
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:

    Title: 模糊RLDA與類神經網路於臉部辨識之應用
    Authors: 沈威宇;Chen, Wei-Yu
    Contributors: 數學系應用數學研究所
    Keywords: 人臉辨識;類神經網路;同態濾波;RLDA;neural networks;face recognition
    Date: 2017
    Issue Date: 2019-07-17
    Publisher: 數學系應用數學研究所
    Abstract: 人臉辨識的應用替許多領域的作業流程帶來不少便利,自1960年以來不斷地被研究,直到如今已受到越來越多的重視。資料量龐大和光源、角度、配件等干擾是做人臉辨識的研究時主要要克服的問題。本研究使用直方圖截斷與拉伸和同態濾波作為影像前置處理,改善照度變化的問題;在特徵萃取階段使用RLDA解決資料量龐大的問題,另外再加入模糊化減輕角度、配件等干擾造成識別的影響;最後,我們使用倒傳遞類神經網路、機率類神經網路和最近鄰居法作為分類器來訓練和測試資料。實驗階段本研究採用ORL人臉資料庫、Yale人臉資料庫、MIT-CBCL人臉資料庫、MultiPIE人臉資料庫和自製人臉資料庫作為樣本,展現前面所提方法對辨識率的提升和比較不同分類器於此研究的優劣。
    The application of face recognition has brought a great deal of convenience to many fields. Since 1960, it has been researched and paid more and more attention. High-dimension data and variation of illumination, angle, accessories and other interference are the main problems to be overcome in face recognition. In this study, histogram truncation and stretching and homomorphic filtering are used as image preprocessing to improve the problem of the varying illuminance. In the feature extraction phase, RLDA is used to solve the problem of high-dimension data. In addition, the use of fuzzification reduces the influence in recognition caused by angle, accessories and other interference. Finally, we use back-propagation neural networks, probabilistic neural networks, and nearest neighbor methods as classifiers to train and test the data. In the present study, ORL face database, Yale face database, MIT-CBCL face database, MultiPIE face database and self-made face database were used as samples to demonstrate the improvement of the recognition rate by the methods mentioned before, and compare the advantages and disadvantages of different classifiers used in this study.
    Appears in Collections:[Institute of Applied Mathematics] thesis

    Files in This Item:

    File Description SizeFormat

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

    版權聲明 © 國立中正大學圖書館網頁內容著作權屬國立中正大學圖書館


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