利用區塊人臉特徵為基礎之混合式人臉辨識系統; A Hybrid Method for Face Recognition based on Block-Based Facial Features

NCU Institutional Repository > 資訊電機學院 > 資訊工程研究所 > 博碩士論文 > Item 987654321/9325

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: http://ir.lib.ncu.edu.tw/handle/987654321/9325

题名:	利用區塊人臉特徵為基礎之混合式人臉辨識系統;A Hybrid Method for Face Recognition based on Block-Based Facial Features
作者:	梁皓雲;Hau-Yun Liang
贡献者:	資訊工程研究所
关键词:	人臉辨識;Face Recognition
日期:	2006-06-29
上传时间:	2009-09-22 11:45:27 (UTC+8)
出版者:	國立中央大學圖書館
摘要:	在人臉辨識的相關研究中，所要加強和克服的不外乎辨識的準確率，而輸入影像的前處理步驟及輸入影像的內容也將明顯影響辨識的準確性。所謂影像的內容指的是拍攝環境和人臉上的光線變化，這個因素影響辨識率很深。之前許多的研究都是拿整張人臉去做辨識。在本論文中是將人臉分成不同的區域，然後分別將這些區域去做辨識。因為整張人臉包含了許多膚色區域，而這些膚色區域對於表示人的特徵上並沒有太大的幫助，反而會因為光線或環境的變化去影響這些膚色區域，所以為了能減少這些膚色區域對辨識的影響，所以才提出了在人臉上框取幾個不同的區域，這些區域要以膚色愈少愈好。人臉辨識的演算法則是LDA + PCA ，而在辨識前我們必須對辨識影像先做小波轉換，原因是小波轉換能將影像保留最不變性的部份，也就是會去除掉一些不必要的部分，另外影像也會縮小，在辨識的時間上也就減少。在做完辨識後因為框取了數個辨識區域所以會有數個辨識結果，因此在整合這些辨識結果方面一般來說通常是採用投票法，但是在本論文中除了採用投票法還加上權重。所謂的權重是依據特徵做分群後的結果而定。當投票法無法判定時便採用以權重來辨識。最後經由自行拍攝的影像測試結果顯示，我們所提出的方法在辨識率上的確比使用整張人臉來的要好。 The relevant research of face recognition has have to be strengthen and overcome rate of accuracy of recognition. The previous treatment steps and content of input image obviously affect accuracy of recognition. The so-called content of image means that the environment and the changes of lighting on face, and this factor affects the rate of recognition very deeply. Most previous research focus on taking whole face image for recognition. This thesis focuses on dividing the face image into different areas, then takes these different areas to recognize. The face image is often full of skin areas, which have less help to recognition but damage. Furthermore, the color of skin areas is easily influenced by the lighting condition or changes of the environment. In order to prevent the above drawbacks which may decrease the accuracy of face recognition, the paper propose a method which fetches different areas of the face as features and these areas have little skin color areas . The algorithm of face recognition consists of LDA + PCA and before recognition we must first do wavelet transform on the image. The reason doing wavelet transform is to keep the changeless parts of image, in other words it can remove some unnecessary parts of image. In addition, the size of image will dwindle too, so the time to recognize will be reduced. After finishing of recognition, due to several areas to recognize, several results of recognition will be produced. So generally speaking in combining these result of recognition, people usually adopts the vote method, but in addition to voting method, we also adopted weighting approach in this thesis. The weight value was based on the results of features which were clustered. We adopt weighting method when the vote method is unable to decide. The experimental results showed that our proposed approach which is based on certain blocks in the face is better than other methods which using the entire face image in accuracy rate.
显示于类别:	[資訊工程研究所] 博碩士論文

文件中的档案:

档案	大小	格式	浏览次数

在NCUIR中所有的数据项都受到原著作权保护.

社群 sharing

数据加载中.....