Please use this identifier to cite or link to this item:
標題: 以基於支持向量學習之TS型式自我組織模糊網路做人臉偵測與追蹤
Face Detection and Tracking in Color Images Using Self-Organizing TS-Type Fuzzy Network with Support Vector Learning
作者: 許昇傑
Shiu, Sheng-Jie
關鍵字: face detection;人臉偵測;face tracking;skin color segmentation;kalman filter;real-time tracking;fuzzy neural network;人臉追蹤;膚色分割;卡爾門濾波器;即時追蹤;類神經模糊網路
出版社: 電機工程學系所
引用: [1] C. F. Juang, S. J. Shiu, and S. H. Chiu, “Face detection and tracking by support vector machine trained fuzzy system for robot vision system,” Proc. Of CACS Automatic Control Conference, Tainan, Taiwan, Nov. 2005. [2] M. Hunke and A. Waibel, “Face locating and tracking for human-computer interaction,” Proc. IEEE Cnf. Signal, System and Computers, vol. 2, pp. 1277-1281, Oct., 1994. [3] D. Comaniciu and V. Ramesh, “Robust detection and tracking of human faces with an active camera,” Proc. IEEE Cnf. Visual Survelliance, pp. 11-18, July., 2000. [4] M. Kawade, “Vision-based face understanding technologies and applications,” Proc. IEEE Cnf. Micromechatronics and Human Science, pp. 27-32, Oct., 2002. [5] M.Yang, D. Kriegman, and N. Ahuja, “Detecting Faces in Images: A Survey,” Proc. IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 1, pp. 34-58, Jan. 2002. [6] Y. B. Sun and J. T. Kim, and W. H. lee, “Extraction of face objects using skin color information,” Proc. IEEE Int. Conf. Communications, Circuits and Systems and West Sino Expositions, vol. 2, pp. 1136-1140, 2002. [7] C. Kotropoulos and I. Pitas, “Rule-Based Face Detection in Frontal Views,” Proc.IEEE Int'l Conf. Acoustics, Speech and Signal Processing, vol. 4, pp. 2537-2540, 1997. [8] K.C. Yow and R. Cipolla, “Feature-Based Human Face Detection,” Proc. IEEE Cnf. Image and Vision Computing, vol. 15, no. 9, pp. 713-735, 1997. [9] D. Chetverikov and A. Lerch, “Multiresolution Face Detection,” Threoretical Foundations of Computer Vision, vol. 69, pp. 131-140, 1993. [10] K.-K. Sung and T. Poggio, “Example-Based Learning for View-Based Human Face Detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 1, pp. 39-51, Jan. 1998. [11] C. Garica and M. Delakis, “Convolutional face finder: a neural architecture of fast and robust face detection,” IEEE Jnl. Pattern Analysis and Machine Intelligence, pp. 1408-1423, Nov., 2004. [12] H. Rowley, S. Baluja, and T. Kanade, “Neural Network-Based Face Detection,” IEEE Trans. Pattern Analysis and Machine intelligence, vol. 20, no. 1, pp. 23-38, Jan. 1998. [13] V. Vapnik, The Nature of Statistical Learning Theory, New York : Springer - Verlag, 1995. [14] C. Garcia and M. Delakis, “Convolutional face finder: a neural architecture for fast and robust face detection,” IEEE Trans. Pattern Analysis And Machine Intelligence, vol. 26, no. 11, pp. 1408-1423, Nov., 2004. [15] D. Chai and K. N. Mgan, “Locating facial region of a head-and-shoulders color images,” Proc. 3rd Int. Conf. Automatic Face and Gesture recognition, pp. 124-129, 1998. [16] M. J. Jones and J. M. Rehg, “Statistical color models with application to skin detection,” Int. Journal of Computer Vision, vol. 46, no. 1, pp. 81-96, Jan. 2002. [17] S. Mckenna, S. Gong, and Y Raja, “Modeling facial colour and identity with Gaussian mixtures,” Pattern Recognition, vol. 31, no. 12, pp. 1883-1892, 1998. [18] E. Littmann, and H. Ritter, “Adaptive color segmentation - a comparison of neural and statistical methods,” IEEE Trans. Neural Networks, pp. 175-185, January 1997. [19] G. Hager and K. Toyama. “X vision: A portable substrate for real time vision applications,” Computer Vision and Image Understanding, 69(1):23-27, 1998. [20] D. Decarlo and D. Metaxas. “Deformable model based face shape and motion estimation,” Proc. Int'l Conf. Auto. Face and Gesture Recognition, 1996. [21] C. Edwards, C. Taylor, and T. Cootes. “Learning to identify and track faces in an image sequence,” Proc. Int'l Conf. Auto. Face and Gesture Recognition, pages 260-265, 1998. [22] E. Hjelmas and B.K. Low, “Face Detection: A Survey,” Computer Vision and Images Understanding, vol. 83, pp. 236-274, 2001. [23] R.E. Kalman: Trans. ASME, J. Basic Eng. 82, 35 (1960). [24] S. Kewei and F. Xitian, C. Anni and S. Jingao, “Automatic face Segmentation in YCrCb Images,” in Proc. Asia-Pacific Conf. on Communications and Optoelectronics and Communication Conf., vol. 2,, 1999, pp. [25] N.Habili, C.Lim et A.Moini. "Hand and face segmentation using motion and color cues in digital image sequences," Dans Proc. IEEE Int. Conf. on Multimedia and Expo, pp. 377--380, Tokyo, Japon, 2001. [26] C. T. Lin and C. S. G. Lee, Neural Fuzzy Systems: A Neural-Fuzzy Synergism to Intelligent Systems, Prentice Hall, May, 1996. [27] C.F. Juang, “A TSK-type recurrent fuzzy network for dynamic systems processing by neural network and genetic algorithms,” IEEE Trans. Fuzzy Systems, vol.10, no. 2, pp. 155-170, April, 2002. [28] C.F. Juang and C.T. Lin, “An on-line self-constructing neural fuzzy inference network and its applications,” IEEE Trans. Fuzzy Systems [29] L. Rutkowski and K. Cpalka, “Designing and learning of adjustable quasi- triangular norms with applications to neuro-fuzzy systems, “ IEEE Trans. Fuzzy Systems, vol. 13, no. 1, pp. 140- 151, Feb. 2005. [30] C. Cortes, and V. Vapnik, “Support vector networks,” International Journal on Machine Learning, vol. 20, pp. 1-25, 1995. [31] N. Cristianini and J. S.-Taylor, An Introduction to Support Vector Machines And Other Kernel-based Learning Methods, Cambridge University Press, 2000. [32] J. H. Chiang, and P. Y. Hao, “Support vector learning mechanism for fuzzy rule-based modeling: a new approach,” IEEE Trans. Fuzzy Systems, vol. 12, no. 1, pp. 1-12, Feb. 2004. [33] Y. Chen, and J. Z. Wang, “Support vector learning for fuzzy rule-based classification systems,” IEEE Trans. Fuzzy Systems, vol. 11, no. 6, pp. 716-728, Dec. 2003. [34] C. T. Lin, C. M. Yeh, and C. F. Hsu, “Fuzzy neural network classification using support vector machine,” Prof. IEEE Symp. Circuits and Systems, pp. 724-727, 2004. [35] C. T. Lin, C. M. Yeh, S. F. Liang, J. F. Chung, and N. Kumar, “Support-vector- based fuzzy neural network for pattern classification,” IEEE Trans. Fuzzy Systems, vol. 14, no. 1, pp. 31-41, Feb. 2006. [36] T. Joachims, N. Cristianini, and J. Shawe-Taylor, “Composite kernels for hypertext categorization,” Proc. Int. Conf. Machine Learning, 2001. [37] J. S. Roger Jang, and C. T. Sun, “Functional Equivalence Between Radial Basis Function Networks and Fuzzy Inference System, IEEE Trans. Neural Networks, vol. 4, no. 1, pp. 156-159, January 1993. [38] B. Sch lkopf, K. Sung, C. Burges, F. Girosi, P. Niyogi, T. Poggio, and V. Vapnik, “Comparing support vector machines with Gaussian kernels to radial basis function classifiers,” IEEE Trans. Signal Processing, vol. 45, pp. 2758-2765, 1997. [39] K. Sobottka and I. Pitas, “A novel method for automatic face segmentation, facial feature extraction and tracking,” Signal Processing: Image Communication, vol. 12, no. 3, pp. 263-281, June. 1998. [40] B. Menser and M. Brunig, “Face detection and tracking for video coding applications,” IEEE Cnf. Signal, System and Computers, vol. 1, pp. 49-53, Nov. 2000. [41] S. H. Chiu, Skin Color Image Segmentation by Support Vector Machine-aided Self Organizing Fuzzy Network, Master Thesis, Department of Electrical Engineering, National Chung Hsing University, Taiwan, July, 2005. [42] CIT face database [43] G. Bradski, A. Kaehler, and V. Pisarevsky, “Learning-based computer vision with Intel's open source computer vision library,” Intel Technology Journal, vol. 9, no. 2, pp. 119-130, 2005. [44] R. Lienhart and J. Maydt, “An extended set of Haar-like features for rapid object detection,” Prof. IEEE Int. Conf. Image Processing, pp. 900-903, 2002. [45] C. F. Juang and C. T. Lin, “An on-line self-constructing neural fuzzy inference network and its applications,” IEEE Trans, Fuzzy Systems, vol. 6, pp. 12-32, 1998.
本論文提出一個以基於支持向量學習之TS型式自我組織模糊網路(SOTFN-SV)的新方法做人臉偵測與追蹤。SOTFN-SV是一個結合模糊分群(Fuzzy Clustering)與支持向量機(SVM)的模糊系統,此模糊系統的前件部為對輸入資料作模糊分群(Fuzzy Clustering)而得,再使用支持向量機(SVM)來做後件部的調整,使得整個系統能夠得到較佳的性能。使用SOTFN-SV來做人臉偵測總共包含三個步驟,首先,SOTFN-SV被應用在膚色的分割中,我們使用了HSV色彩模型中色調(H)和濃度(S)二維彩色空間中的資訊。在膚色分割中,從不同的亮度情況和環境底下中選出來的樣本資訊所訓練的SOTFN-SV分類器可使我們的方法更為強健。為了剔除雜訊和產生人臉的候選區我們利用型態學“opening”運算元作選取的動作。而步驟二中,我們限制相關人臉的大小、比例和形狀用來排除人臉候選區域中錯誤偵測的個數。從形狀分析中可得知事實上人臉形狀可近似於橢圓形狀,所以我們找出每一個切刻膚色區域的最佳近似橢圓來做分析。最後,從剩下來的人臉候選區中,利用眼睛、嘴巴和臉部膚色的彩色結構資訊來當作偵測的特徵,然後把這些特徵資訊送入SOTFN-SV分類器來做最後的偵測判斷準則。我們所提出的人臉偵測方法可應用於即時的人臉追蹤上。在人臉追蹤時,用Kalman濾波器來平滑我們的追蹤曲線和預估我們偵測的區域以便降低所需要偵測的時間。實驗結果證明我們的方法可以很有效率的作人臉偵測和追蹤。

A new method for face detection and tacking by a Self-Organizing TS-type Fuzzy Network with Support Vector learning (SOTFN-SV) is proposed in this thesis. SOTFN-SV is a fuzzy system constructed by the hybridization of fuzzy clustering and SVM. The antecedent part of SOTFN-SV is generated via fuzzy clustering of the input data, and then SVM is used to tune the consequent part parameters to give the network better generalization performance. Face detection is based on SOTFN-SV and consists of three stages. In the first stage, SOTFN-SV is applied to skin color segmentation. Color information from the Hue and Saturation (HV) color space is used. For skin color segmentation, pattern information from images under different lighting conditions and environments is used to train a SOTFN-SV classifier to make the method as robust as possible. Morphological opening operation is employed on segmented pixels for eliminating noises and generating face candidates regions. In the second stage, constraints related to face size and shape are employed to exclude components from the face candidates to reduce the number of false alarms. Shape analysis in based on the fact that the oval face shape can be approximated by an elliptical shape, and a best fitting ellipse to each connected skin region is found for analysis. Finally, for the left face candidates, facial color texture information from the eyes, mouth, and skin regions are used as detection features. These features are fed as inputs to a SOTFN-SV classifier to make a final detection decision. The proposed face detection method is applied to real-time face tracking. For face tracking, a Kalman filter algorithm is employed for face trajectory smoothing and prediction. The trajectory prediction function helps to narrow down the face detection region so that the detection time can be reduced. Experimental results are performed to verify the effectiveness of the proposed face detection and tracking method.
其他識別: U0005-1507200622024000
Appears in Collections:電機工程學系所

Show full item record

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.