人臉影像辨識演算法的探討

人臉辨識在生物辨識領域已經被廣泛的研究，相較於其他生物辨識系統擁有更不侵犯性，使得在不強迫的情形下進行監視變的可行，因此人臉辨識這項研究的相當的熱門。雖然近年已經有相當多的論文發表，但似乎沒有無所不包的得引導，好讓我們實際的去時做論文上提及人臉辨識的方法。這篇論文中我們解答在這些論文條件下所出現的問題我們研究了主成分分析, 、線性鑑別分析、獨立成份分析法，除此之外核心版本的主成分分析與線性鑑別分析。我們執行實驗使用了五個人臉辨識演算法在AT&T、YALE和NTHU PRIP人臉資料庫，辨識率在結果的章節展示。

關鍵字

人臉；辨識

並列摘要

Face Recognition has become one of the most widely researched areas in the Biometric Identification domain. Its popularity is due mostly to the fact that it is less intrusive than other biometric systems thus making it highly applicable to fields such as law enforcement and surveillance. Although there are a vast number of papers that are published yearly, there seems to be no comprehensive guide as to how to actually implement the most read about face recognition methods. In this thesis we try to answer this question by providing the steps that these face recognition algorithms follow to arrive at their output. We studied Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and Independent Component Analysis (ICA). In addition we also studied the Kernel version of PCA and LDA. We performed experiments using the five face recognition methods on the AT&T, YALE and NTHU PRIP face databases. The classification rates are reported in the experimental results section.

並列關鍵字

無資料

參考文獻

[Zha99] W. Zhao, R. Chellappa, and P.J. Phillips, “Subspace Linear Discriminant

[Zha03] W. Zhao, R. Chellappa, and P.J. Phillips, and J. Rosenfeld,“FaceRecognition:A

[Bac02] F.R. Bach and M.I. Jordan, “Kernel Independent Component Analysis”,

JMLR, 3(Jul):1-48, March 2002.

[Bar02] M. Bartlett and T. Sejnowski, “Face Recognition by Independent Component

國際替代計量

人臉影像辨識演算法的探討

全文下載

主題瀏覽