臺灣博碩士論文加值系統

人臉的表情、姿態、燈光等變化對強健性人臉辨識是極具挑戰的問題。為了克服這些問題，本論文提出一種基於區域特徵之線性迴歸演算法來進行人臉辨識。線性回歸演算法是非常有未來性的人臉辨識方法，但直接以人臉影像強度為特徵則會因人臉的表情、姿態、燈光等變化而產生問題。過去幾年，尺度不變性特徵轉換的區域特徵在影像辨識的應用上備受注目。因為尺度不變性特徵轉換對於影像的尺度變化、旋轉及燈光變化是一種強健的區域特徵，我們引進此種區域特徵加上線性迴歸將可以解決人臉辨識所面臨的問題。本論文我們使用主成份分析來進行降維，然後以線性回歸分類法來完成辨識。實驗結果顯示本文提出的方法相較於類似的方法有更好的表現。

Variations (expression, pose, illumination, and so on) in a face image are the challenging problems for a robust face recognition system. In order to overcome these problems, in this thesis, we proposed a local feature based linear regression classification algorithm for face recognition. Recently, the linear regression classification (LRC), which evolved as a promising method for face recognition, suffers from problems with the variations when we use intensity value directly in the LRC. Over the past few years, the local features such as scale invariant feature transform (SIFT) have been gained much attention for recognition and pattern matching. Since the SIFT is a robust method to defend the different situations with scale, rotation and illumination variations of an image, we expected that the local features instead of pixel information can be more robust to meet the above challenges. Before classifying the features, we reduce the feature dimension with a statistical method, called the principal component analysis (PCA). Finally, linear regression classification (LRC) has been performed on these features. Experimental results show that the proposed method performs better the related methods.

摘要 I
ABSTRACT II
ACKNOWLEDGEMENT IV
CONTENTS V
LIST OF TABLES VII
LIST OF FIGURES VIII
CHAPTER 1 INTRODUCTION 1
1.1 RESEARCH BACKGROUND 1
1.2 MOTIVATION 2
1.3 LITERATURE REVIEW 3
1.4 THESIS ORGANIZATION 4
CHAPTER 2 RELATED WORKS 5
2.1 PRINCIPAL COMPONENT ANALYSIS (PCA) 5
2.2 LINEAR DISCRIMINANT ANALYSIS (LDA) 7
2.3 SCALE INVARIANT FEATURE TRANSFORM (SIFT) 8
2.4 LINEAR REGRESSION CLASSIFICATION(LRC) 16
CHAPTER 3 THE PROPOSED METHOD 19
3.1 OVERVIEW OF THE PROPOSED APPROACH 20
3.2 DENSE SCALE INVARIANT FEATURE TRANSFORM 21
3.3 DIMENSION REDUCTION USING PCA 24
3.4 LOCAL FEATURE BASED LINEAR REGRESSION CLASSIFICATION 26
CHAPTER 4 EXPERIMENTAL RESULTS 28
4.1 AR FACE DATABASE 28
4.1.1 Analysis on Expression Variation 29
4.1.2 Analysis on Illumination Variation 31
4.1.3 Analysis on Occlusion Variation 32
4.2 FERET FACE DATABASE 33
4.2.1 Analysis on expression and illumination variation 33
CHAPTER 5 CONCLUSIONS 36
CHAPTER 6 FUTURE WORKS 37
REFERENCES 38

[1]W. Zhao, R. Chellappa, A. Rosenfeld, and P. J. Phillips, “Face Recognition: A Literature Survey, ACM Computing Surveys, vol. 35, no. 4, pp. 399-458, 2003.
[2]M. A. Turk and A. Pentland, “Eigenface for Recognition, Jour. of Cognitive Neuroscience, vol. 3, no. 1, pp. 71–86, 1991.
[3]P. N. Belhumeur, J. P. Hespanha, and D. J. Kriegman, “Eigenfaces vs. Fsherfaces: Recognition Using Class Specific Linear Projection, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 4, pp. 711–720, 1997.
[4]B. Moghaddam and A. Pentland, “Probabilistic Visual Learning for Object Representation, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 19, no. 7, pp. 696–710, 1997.
[5]I. Naseem, R. Togneri, and M. Bennamoun, “Linear Regression for Face Recognition, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 32, no. 11, pp. 2106–2112, 2010.
[6]I. Naseem, R. Togneri, and M. Bennamoun, “Robust Regression for Face Recognition, Pattern Recognition, vol. 45, no. 1, pp. 104-118, 2012.
[7]S.M. Huang and J.F. Yang, Improved Principal Component Regression for Face Recognition Under Illumination Variations, IEEE Trans. on Signal Processing Letters, vol. 19, no. 4, pp.179-182, 2012.
[8]J.-D. Mi, J.-X. Liu, and J. Wen, New Robust Face Recognition Methods based on Linear Regression, Jour. of PLoS ONE, vol. 7, no. 8, 2012.
[9]Lowe D.G, “Distinctive Image Features from Scale-Invariant Keypoints, Jour. of Computer Vision, vol. 60, no. 2, pp. 91–110, 2004.
[10]Mohamed Aly, “Face recognition using SIFT features,
http://www.vision.caltech.edu/maala/research.php
[11]K. Mikolajczyk and C. Schmid. “A Performance Evaluation of Local Descriptors, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 27, no. 10, pp.1615-1630, 2005
[12]Vedaldi and B. Fulkerson, “VLFeat: An Open and Portable Library of Computer Vision Algorithms, International Conf. on Multimedia, pp. 25–29, 2010.
[13]L. Ce, J. Yuen, and A. Torralba, SIFT Flow: Dense Correspondence across Scenes and Its Applications, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 33, no. 5, pp.978-994, 2011.
[14]T. Tuytelaars, “Dense Interest Points, IEEE Conf. on Computer Vision and Pattern Recognition, 2010.
[15]T. Hastie, R. Tibshirani, and J. Friedman, “The Elements of Statistical Learning; Data Mining, Inference and Prediction, Springer, 2001.
[16]G. A. F. Seber, Linear Regression Analysis, Wiley-Interscience, 2003.
[17]T. P. Ryan, Modern Regression Methods, Wiley-Interscience, 1997
[18]Martinez and R. Benavente, “The AR Face Database, CVC Technical Report 24, 1998.
[19]P. J. Phillips, H. Moon, S. A. Rizvi, and P. J. Rauss, “The FERET Evaluation Methodology for Face-recognition Algorithms, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 22, pp.1090–1104, 2000.
[20]Ma P, Yang D, Ge Y, Zhang X, and Qu Y; “Face Recognition Using Two-dimensional Nonnegative Principal Component Analysis, Jour. Electron. Imaging, vol. 21, no. 3, 2012.
[21]R.G. Staudte and S.J. Sheather, Robust Estimation and Testing. WileyInterscience, 1990.
[22]R. Barsi and D. Jacobs, “Lambertian Reflection and Linear Subspaces, IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 2, pp. 218-233, 2003.Janez
[23]Krizaj, Vitomir Struc, and Nikola PaveAdaptation of SIFT Features for Robust Face Recognition, International Conf. on Image Analysis and Recognition, 2010.