臺灣博碩士論文加值系統

本論文利用結合PCA與灰色理論來建立一套人臉辨識系統. 我們利用加入一些影像前處理,如用兩眼的間距來做正規化,用兩眼中心來做正臉位置的校準及利用統計正臉的平均灰度值來做平均灰度值的補償,來增加PCA理論的辨識率.另一方面,在第二階段辨識的方法是利用幾何特徵值來補償抽象特徵值PCA理論的不足.而幾何特徵值是利用影像處理常用的統計法,色調特性及邊緣偵測等技術將幾何特徵有效率及準確地求得. 利用計算第一階段用PCA理論所得結果的準確率將兩階段式不同辨識方法及特徵值結合.經過實驗過後可以很清楚的得到約93%的辨識率,而所花的時間在Pentium 700M Hz的電腦上平均不到1秒鐘.

This thesis proposes a human face recognition system combining PCA theory with Gray theory. Recognition rate of PCA theory can be improved by several image pre-processing, such as using distance between two eyes for normalization, using center of two eyes for adjustment and using gray balance. On the other hand, recognition of geometric features can be used to compensate recognition of abstract features using PCA. Several general image processings are used in the proposed system, such as histogram, color character and edge detection, to extract geometric features accurately and efficiently. Two recognition methods using distinct features are combined by calculating accuracy index of the result obtained from PCA. The proposed system obviously obtains about 93% recognition rate in several experiments. It spends less than one second in recognition on the Pentium 700M Hz computer.

Contents
Abstract (in Chinese)…………………………………………………………………i
Abstract (in English) ………………………………………………………………...ii
Acknowledgments…………………………………………………………..iii
Contents………………………………………………………………………….iv
List of Tables……………………………………………………………………v
List of Figures…………………………………………………………………vi
1 Introduction……………………………………………………………………..1
1.1 Motivation…………………………………………………………………..1
1.2 Review of related work…………………………………………………..…2
1.3 The proposed system…………………………………………………..……3
1.4 Organization of thesis……………………………………………….………3
2 Relative Image Processing……………………………………………………...4
2.1 The HSI color model………………………………………………………..4
2.2 Conversion from RGB to HSI………………………………………………5
2.3 Histogram processing……………………………………………………….6
2.4 Edge processing..…………………………………………………………...8
2.5 Principal Component Analysis (PCA).……………………………………..9
3 Introduction to the Human Face Recognition System………………………12
3.1 Flow chart of the proposed system………………………………………..13
3.2 Introduction to each work of whole system……………………………….14
4 Pre-process of Human Face Recognition System……………………………17
4.1 Locating the human face…………………………………………………..17
4.2 Locating eyes and eyebrows………………………………………………20
4.3 Locating mouth……………………………………………………………22
4.4 Locating nose……………………………………………………………...23
4.5 Face model………………………………………………………………...24
4.6 Extracting the geometric features of eye…………………………………..26
4.7 Extracting the geometric features of mouth……………………………….31
4.8 Extracting the geometric feature of nose………………………………….36
5 Human Face Recognition System…………………………………………….37
5.1 Database…………………………………………………………………...37
5.2 Recognition using PCA……………………………………………………39
5.3 Recognition using Gray Theory…………………………………………...41
6 Experiment Result…………………………………………………………….42
6.1 Extraction result…………………………………………………………...43
6.2 Result of recognition of geometric features……………………………….43
6.2.1 Experiment 1……………………………………………………44
6.2.2 Experiment 2……………………………………………………44
6.3 Result of recognition of abstract features…………………….……………45
6.3.1 Experiment 3……………………………………………………45
6.3.2 Experiment 4……………………………………………………46
6.4 Effect of different number of eigenface…………………………………...47
6.4.1 Experiment 5……………………………………………………47
6.5 Result of the proposed system……………………………………………..48
7 Conclusion……………………………………………………………………...51
7.1 Conclusion…………………………………………………………………51
7.2 Future work………………………………………………………………..51
Bibliography………………………………………………………………………...52

Bibliography
[1] M. Turk and A. Pentland, “Face recognition using eigenfaces”, Proc. CVPR’91, pp.586—591, 1991.
[2] T. Yokoyama, H. Wu, and M. Yachida, “Automatic detection of facial feature points and contours”, Robot and Human Communication, pp.335-340, 1996.
[3] Yanjiang Wang and Baozong Yuan, “Human eyes location using wavelet and neural network”, Proc. ICSP’2000, vol.2, pp.1233-1236, 2000.
[4] Hsin-Chia Fu, P.S. Lai, R.S. Lou, and H.T. Pao, “Face detection and eye localization by neural network based color segmentation”, Neural Networks for Signal Processing X, vol.2, pp.507-516, 2000.
[5] Y. Shiga, H. Ebine, M. Ikeda, and O. Nakamura, “Human face extraction based on color and moving information and the recognition of expressions”, Electrical and Computer Engineering, vol.2, pp.1100-1108, 2000.
[6] Kin-Man Lam and Hong Yan, “An improved method for locating and extracting the eye in human face images”, Proc. ICPR’96, pp.411—415, 1996.
[7] Bertrand Leroy, Isabelle L. Herlin and Laurent D. Cohen, “Face identification by deformation measure”, Proc. ICPR’96, pp.633-637, 1996.
[8] Li-an Tang and Thomas S. Huang, “Characterizing smiles in the context of video phone data compression”, Proc. ICPR’91, pp.659—663, 1991.
[9] JianHuang Lai, Pong C Yuen, WenSheng Chen, Shihong. Lao and Masato Kawade, “Robust facial feature point detection under nonlinear illuminations”, Proc. ICPR’2001, pp.168-174, 2001.
[10] C. Garcia and G. Tziritas, “Face detection using quantized skin color regions merging and wavelet packet analysis”, IEEE Transactions on Multimedia, vol.1, no.3, pp. 264-277, September, 1999.
[11] Haiyuan Wu, Qian Chen and M. Yachida, “Face detection from color images using a fuzzy pattern matching method”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.21, no.6, pp.557-563, June, 1999.
[12] K. Sobottka and I. Pitas, “Extraction of facial regions and features using color and shape information”, Proc. ICPR’96 Pattern Recognition, vol.3, pp.421-425, 1996.
[13] Jeonghee Park, Jungwon Seo, Dongun An and Seongjong Chung, “Detection of human faces using skin color and eyes”, Proc. IEEE, vol.1, pp.133-136, 2000.
[14] Y. Mitsukura, E. Fukumi, and N. Akamatsu, “A design of face detection system by using lip detection neural network and skin distinction neural network”, Proc. IEEE, vol.4, pp.2789-2793, 2000.
[15] Hirayama, Y. and Nakamura, O., “Personal identification system through facial images based on the modified HSV color system and isodensity maps”, Proc. IEEE Electrical and Computer Engineering, vol.2, pp.823-826, 1997.
[16] Chengjun Liu and H. Wechsler, “A shape- and texture-based enhanced Fisher classifier for face recognition”, IEEE Transactions on Image Processing, vol.10, no.4, pp.598-608, April, 2001.
[17] G. C. Feng and P. C. Yuen, “Recognition of head-and-shoulder face image using virtual frontal-view image”, IEEE Transactions on Systems, Man and Cybernetics-Part A, , vol.30, no.6, pp.871-882, Nov. 2000.
[18] Kin-Man Lam and Hong Yan, “An analytic-to-holistic approach for face recognition based on a single frontal view”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.20, no.7, pp.673—686, July, 1998.
[19] A. Z. Kouzani, F. He and K. Sammut, “Multiresolution eigenface-components”, Proc. IEEE Speech and Image Technologies for Computing and Telecommunications, vol.1, pp.353-356, 1997.
[20] Rafael G. Gonzalez and Richard E. Woods, “Digital image processing”, Addison-Wesley, 1992.