利用新投影特徵於臉型辨識｜國立清華大學博碩士論文庫

簡易檢索 / 詳目顯示

回結果列表

研究生：	許洲豪
論文名稱：	利用新投影特徵於臉型辨識 New Projection-based Features for Face Recognition
指導教授：	陳朝欽 Chen Chaur-Chin
口試委員:
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 資訊系統與應用研究所 Institute of Information Systems and Applications
論文出版年：	2006
畢業學年度：	94
語文別：	英文
論文頁數：	38
中文關鍵詞：	人臉辨識
外文關鍵詞：	Face Recognition
相關次數：	點閱：2 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

近年來，利用生物特徵來辨認身份迅速成為影像處理技術的重要研究領域。目前像是臉型、指紋、掌紋和虹膜等生理上或者行為表現上的特徵都已經廣泛的利用在辨識人類身份的應用上。
臉型辨識系統是一個利用電腦強大的計算能力並且能利用擷取的影像或資料庫中的影像自動的辨認出目標者身份的系統。它可以被應用在門禁系統、保全系統以及數位家庭中等眾多的環境中。然而對臉型辨識系統最重要與最困難的部分即在於如果從人臉影像中擷取出最具辨別能力的特徵。
在本論文中，我們介紹四種著名的特徵擷取方法(Eigenfaces, Fisherfaces, 2DPCA and 2DLDA)並且提出了一個基於奇異值(SVD)與主成份分析(principal component analysis)的特徵擷取方式。在本文中把我們所提出的新方法與上述的四個著名的特徵擷取方法在辨識率和效能上互相比較。從實驗結果發現我們的方法在得到良好的辨識率同時也可以降低系統的記憶體需求。

Biometric identification has been rapidly becoming a critical research category of image processing techniques. Several kinds of features have been proposed for recognizing people which are based on physiological or behavioral characteristics such as face, fingerprint, handwriting, iris and etc. Face recognition system is a computer-based system that is able to automatically recognize people by face images. For face recognition systems, the most import and difficult task is to find out a method for extracting the most separable features.
In this thesis we propose a new feature extraction method based on singular value decomposition (SVD) and principal component analysis (PCA) for classifying facial images. Furthermore, it is compared with the other four famous feature extraction methods (Eigenfaces, Fisherfaces, 2DPCA and 2DLDA). From the experimental results, our approach obtains a good recognition rate and the memory cost is much smaller.

Chapter 1 Introduction............................................................................1
Chapter 2 Methodology...........................................................................4
    2.1 Eigenfaces........................................................................................................4
    2.2 Fisherfaces........................................................................................................9
    2.3 Two-Dimensional PCA (2D PCA).................................................................12
    2.4 Two-Dimensional LDA (2D LDA)................................................................16
    2.5 New projection-based features for face recognition.......................................20
Chapter 3 Face Databases for Experiments.........................................23
    3.1 The ORL Face Database.................................................................................23
    3.1 The YALE Face Database..............................................................................24
    3.1 The AR Face Database...................................................................................24
    3.1 The UMIST Face Database............................................................................26
Chapter 4 Experimental Results….......................................................27
    4.1 Experiments of the accuracy..........................................................................27
        4.1.1 Experiments on the ORL face database..............................................27
        4.1.2 Experiments on the YALE face database............................................28
        4.1.3 Experiments on the AR face database.................................................29
        4.1.4 Experiments on the UMIST face database..........................................30
4.2 Experiments of the performance and memory cost........................................31
    4.2.1 Performance analysis...........................................................................31
    4.2.2 Memory cost analysis..........................................................................34
Chapter 5 Conclusion.............................................................................35
References................................................................................................36

List of Tables

Table 3.1 : The configurations adopted in AR face database…………...25

Table 4.1: The memory cost (bytes) for the five feature extraction methods using 10 projection vectors to present a face image in four face databases………………………………………………………………...34

List of Figures

Figure 1.1: Training stages of a face recognition system……………………………..2

Figure 1.2: Test stages of a face recognition system………………………………..2

Figure 2.1:  Convert image matrix into image vector……………………………….5

Figure 2.2:  Reconstructed images with different number of principal components of the first individual in the ORL face database………………………………………….8

Figure 2.3:  PCA and LDA projection of elliptic data sets…………………………..9

Figure 2.4:     Fisherfaces and original faces ...…………………………………......11

Figure 2.5:  The reconstructed images of two individuals in the ORL face database with different principal components…………………………………………….........15

Figure 2.6:  The reconstructed images of two individuals in the ORL face database with different number of components………………………………………………..19

Figure 2.7:  The reconstructed images of two individuals in the ORL face database with different number of projection vectors………………………………………….22

Figure 3.1: The face images of the first individual in the ORL face database............23

Figure 3.2: The 11 face images of the Subject06 in the Yale face database…............24

Figure 3.3: The 26 images of one person in the AR face database………………….25

Figure 3.4: The 38 images of the first person in the UMIST face database…………26

Figure 4.1: The recognition rates of the five methods on ORL database…………...28

Figure 4.2: The recognition rates of the five methods on Yale database…………….29

Figure 4.3: The recognition rates of the five methods on AR face database..............30

Figure 4.4: The recognition rates of the five methods on UMIST database…….......31

Figure 4.5(a): The time cost of the five methods on ORL database……………..32

Figure 4.5(b): The time cost of the five methods on Yale database……………..32

Figure 4.5(c): The time cost of the five methods on AR database……….……...33

Figure 4.5(d): The time cost of the five methods on UMIST database……........33

[Ans05] A.N. Ansari and M. Abdel-Mottaleb, “Automatic facial feature extraction and 3D face modeling using two orthogonal views with application to 3D face recognition,” Pattern Recognition, Vol. 38, pp. 2549-2563, 2005.
[Bel96] P.N. Belhumeur, J.P. Hespanha and D.J. Kriegman, “Eigenfaces vs. Fisherfaces: Recognition using Class Specific Linear Projection,” Proc. of the 4th European Conference on Computer Vision, ECCV'96, pp. 45-58, 1996.
[Bel97] P.N. Belhumeur, J.P. Hespanha and D.J. Kriegman, “Eigenfaces vs. fisherfaces: Recognition using class specific linear projection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Special Issue on Face Recognition, 1997.
[Bia05] M. Bianchini, M. Maggini, L. Sarti and F. Scarselli, “Recursive neural networks learn to localize faces,” Pattern Recognition Letters, Vol. 26, pp. 1885-1895, 2005.
[Che05] P. Chen and D. Suter, “Subspace-based face recognition: Outlier detection and a new distance criterion,” International Journal of Pattern Recognition and Artificial Intelligence, Vol. 19, pp. 479-493, 2005.
[Dud00] R. Duda, P.E. Hart and D.G. Stork, “Pattern Classification (2nd Edition),” Wiley List, 2000.
[Gar04] C. Garcia and M. Delakis, “Convolutional face finder: a neural architecture for fast and robust face detection,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 26, pp. 1408-1423, 2004.
[Gun03] B.K. Gunturk, A.U. Batur, Y. Altunbasak, M.H. Hayes III and R.M. Mersereau, “Eigenface-domain super-resolution for face recognition,” IEEE Trans. on Image Processing, Vol. 12, pp. 597-606, 2003.
[Gra98] D.B. Graham and N.M. Allinson, “Characterizing Virtual Eigensignatures for General Purpose Face Recognition,” Face Recognition: From Theory to Applications, NATO ASI Series F, Computer and Systems Sciences, Vol. 163, pp. 446-456, 1998.
[Hei01] B. Heisele, P. Ho and T. Poggio, “Face recognition with support vector machines: global versus component-based approach,” International Conference on Computer Vision, Vol. 2, pp. 688-694, 2001.
[Hua05] L.L. Huang, A. Shimizu and H. Kobatake, “Robust face detection using Gabor filter features,” Pattern Recognition Letters, Vol. 26, pp. 1641-1649, 2005.
[Kim05] T.K. Kim and J. Kittler, “Locally linear discriminant analysis for multimodally distributed classes for face recognition with a single model image,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 27, pp. 318-327, 2005.
[Kir90] M. Kirby and L. Sirovich, “Application of the Karhunen-Loeve procedure for the characterization of human faces,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 12, 1990.
[Kwa05] K.C. Kwak and W. Pedrycz, “Face recognition using a fuzzy fisherface classifier,” Pattern Recognition, Vol. 38, pp. 1717-1732, 2005.
[Lay94] D.C. Lay, “Linear algebra and its applications,” Addison-Wesley, 1994
[Lia05] Y. Liang, W. Gong, Y. Pan and W. Li, “Generalizing relevance weighted LDA,” Pattern Recognition, Vol. 38, pp. 2217-2219, 2005.
[Liu04] C. Liu, “Gabor-based kernel PCA with fractional power polynomial models for face recognition,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 26, pp. 572-581, 2004.
[Mar98] A.M. Martinez and R. Benavente, “The AR Face Database,” CVC Technical Report #24, June 1998.
[Pri05] J.R. Price and T.F. Gee, “Face recognition using direct, weighted linear discriminant analysis and modular subspaces,” Pattern Recognition Vol. 38, pp. 209-219, 2005.
[Ros03] A. Rosenfeld, P.J. Phillips, R. Challappa and W. Zhao, “Face Recognition: A Literature Survey,” ACM Computing Surveys, Vol. 35, pp. 399-458, 2003.
[Sam94] F. Samaria and A. Harter, “Parameterisation of a Stochastic Model for Human Face Identification,” Proceedings of 2nd IEEE Workshop on Applications of Computer Vision, Sarasota FL, 1994.
[Tur91] M.A. Turk and A. Pentland, “Eigenfaces for Recognition,” Journal of Cognitive Neurosicence, Vol. 3, pp. 71-86, 1991.
[Wan05] L. Wang, X. Wang, X. Zhang and J. Feng, “The equivalence of two-dimensional PCA to line-based PCA,” Pattern Recognition Letters, Vol. 26, pp. 57-60, 2005.
[Yan04] J. Yang, D. Zhang, A.F. Frangi and J.Y. Yang, “Two-dimensional PCA: a new approach to appearance-based face representation and recognition,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 26, pp. 131-137, 2004.
[Yan05] J. Yang, D. Zhang, X. Yong and J.Y. Yang, “Two-dimensional discriminant transform for face recognition,” Pattern Recognition, Vol. 38, pp. 1125-1129, 2005.

全文公開日期本全文未授權公開 (校內網路)
全文公開日期本全文未授權公開 (校外網路)

簡易檢索 / 詳目顯示

相關論文