以適應性的主動外形模式定位臉部特徵｜國立中央大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	呂正偉 Cheng-wei Lu
論文名稱：	以適應性的主動外形模式定位臉部特徵 Face Feature Locating using Adaptive Active Shape Model
指導教授：	曾定章 Din-chang Tseng
口試委員:
學位類別：	碩士 Master
系所名稱：	資訊電機學院 - 資訊工程學系 Department of Computer Science & Information Engineering
畢業學年度：	96
語文別：	英文
論文頁數：	76
中文關鍵詞：	臉部特徵、臉部偵測、主動外型模式、平均模型
外文關鍵詞：	face detection, face feature, active shape model, mean shape
相關次數：	點閱：17 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

在近代發表的許多臉部特徵定位方法中，主動外型模式 (active shape model, ASM) 被認為是一個有效的臉部特徵定位工具。在本論文中，我們提供了一個 “以適應性的主動外型模式定位臉部特徵” 的系統。
我們的系統包含兩個部份，第一部份是模式訓練，第二部份是定位應用。模式訓練最主要的目的是要從訓練的影像中求出平均模型 (mean shape) 及轉換矩陣 (transform matrix)。而在定位應用中則反覆的執行兩個步驟：(i) 檢查已經找到的特徵點附近的區塊尋找更好的特徵點位置；(ii) 更新模型參數 (shape parameter) 讓模型更符合新找的特徵點位置。我們在定位應用的過程中使用了十字形特徵輪廓 (crisscross profile) 來決定更好的特徵點位置。另外還使用適應性仿射變換函數 (adaptive affine transform) 來得到更好的模型參考位置。
在實驗中，我們測試了三種影響偵測效果及效能的因素來比較系統的效能：(i) 特徵輪廓 (profile)、(ii) 固有值的數量 (numbers of eigenvalues)、及(iii) 仿射變換函數 (affine transform)。從實驗結果中，我們可以看到我們所提的系統，在定位臉部特徵的表現上比傳統主動外型模式更出色

Recently, many face feature locating methods have been proposed. Active shape model has been shown to be a powerful tool to aid the interpretation of images, especially in face alignment. In this study, we propose a face facture location system using adaptive active shape model.
The proposed system consists of two parts: (1) training process and (2) testing process. In the training process, we train a mean shape and transform matrix from training images. Then the testing process works by alternating the following steps: (i) Examine a region of image around each point for a better position. (ii) Update the shape parameters to fit the new found positions. In order to locate a better position for each point, we utilize the information of crisscross profiles around each point to decide the best position. We also utilize an adaptive affine transform to get a better reference position during testing process.
In the experiments, the proposed approaches are evaluated by several different factors such as profiles, numbers of eigenvalues, and two kinds of affine transform. From the experiment results, we find that the proposed approaches can efficiently locate face feature and have better effect than the classical active shape models.

Abstract ....................................................................................................................... i
Contents .................................................................................................................... ii
List of Figures ............................................................................................................ v
List of Tables .......................................................................................................... vii
Chapter 1 Introduction ............................................................................................... 1
1 Motivation .................................................................................................... 1
2 System overview .......................................................................................... 1
3 Thesis organization ....................................................................................... 2
Chapter 2 Related Works ........................................................................................... 5
1 Face detection ............................................................................................... 5
1.1 Knowledge-based methods ................................................................. 7
1.2 Feature invariant ................................................................................. 7
1.3 Template matching ............................................................................ 11
1.4 Appearance-based methods .............................................................. 14
2 Active shape model ..................................................................................... 17
Chapter 3 Training process ...................................................................................... 18
1 Landmark points ......................................................................................... 19
2 Shapes ......................................................................................................... 20
3 Aligning shapes .......................................................................................... 25
4 Shape model and mean shape ..................................................................... 28
5 Active shape model .................................................................................... 29
Chapter 4 Testing process ........................................................................................ 31
1 Profile model .............................................................................................. 32
1.1 Forming a crisscross profile ............................................................. 32
1.2 Building the crisscross profile model during training ...................... 33
2 Searching for the best image shape ............................................................ 33
- iii -
3 Finding adaptive affine transformation ...................................................... 34
4 Calculating average error and maximum error .......................................... 34
Chapter 5 Experiments ............................................................................................ 37
1 Experimental platform ................................................................................ 37
2 Face databases ............................................................................................ 37
2.1 The IMM face database ..................................................................... 37
2.2 The MIT-CBCL face recognition database ....................................... 38
2.3 The Georgia Tech face database ....................................................... 39
2.4 The INDIAN face database ............................................................... 39
2.5 The GTAV face database ................................................................... 40
2.6 The IPVR face database .................................................................... 41
2.7 Driving images under various illuminations .................................... 42
3 Results of the proposed system .................................................................. 43
3.1 Results of the IMM face database ..................................................... 43
3.2 Results of the MIT-CBCL face recognition database ....................... 46
3.3 Results of the Georgia Tech face database ....................................... 49
3.4 Results of the INDIAN face database ............................................... 52
3.5 Results of the GTAV face database ................................................... 54
3.6 Results of the driving images under various illuminations .............. 57
4 Comparisons ............................................................................................... 59
4.1 Profile condition ............................................................................... 59
4.2 Affine transform ................................................................................ 66
4.3 Size of the eigenvalues ..................................................................... 69
Chapter 6 Conclusions ............................................................................................. 71
References ............................................................................................................... 72

                                

[1] Agui, T., Y. Kokubo, H. Nagashashi, and T. Nagao, “Extraction of face recognition from monochromatic photographs using neural networks,” in Proc. 2nd Int. Conf. Automation, Robotics, and Computer Vision, vol.1, Singapore, Sep.15-18, 1992, pp.1881-1885.
[2] Augusteijn, M. F. and T. L. Skujca, “Identification of human faces through texture-based feature recognition and neural network technology,” in Proc. IEEE Conf. Neural Networks, San Francisco, CA, Mar.28-Apr.1, 1993, pp.392-398.
[3] Carr, J. C., R. K. Beatson, J. B. Cherrie, T. J. Mitchell, W. R. Fright, B. C. McCallum, and T. R. Evans, “Reconstruction and representation of 3D objects with radial basis functions,” in Proc. ACM SIGGRAPH 2001, Los Angeles, CA, Aug.12-17, 2001, pp.67-76.
[4] Cipolla, R. and A. Blake, “The dynamic analysis of apparent contours,” in Proc. 3rd IEEE Int. Conf. Computer Vision, Osaka, Japan, Dec.4-7, 1990, pp.616-623.
[5] Cootes, T. F. and C. J. Taylor, “Active shape models,” in Proc. 3rd British Machine Vision Conf., London, Sep.22-24, 1992, pp.266-275.
[6] Cootes, T. F., C. J. Taylor, D. Cooper, and J. Graham, “Training models of shape from sets of examples,” in Proc. 3rd British Machine Vision Conf., London, Sep.22-24, 1992, pp.9-18.
[7] Cootes, T. F. and C. J. Taylor, “Active shape model search using local grey-level models,” in Proc. 4th British Machine Vision Conf., Guildford, England, Sep.21-23, 1993, pp.639-648.
[8] Cootes, T. F., C. J. Taylor, A. Lanitis, D. H. Cooper, and J. Graham, “Building and using flexible models incorporating grey-level information,” in Proc. 4th Int. Conf. on Computer Vision, Berlin, Germany, May 11-14, 1993,
- 72 -
pp.355-365.
[9] Cootes, T. F. and C. J. Taylor, "Using grey-level models to improve active shape model search," in Proc. 12th IAPR Int. Conf., Jerusalem, Israel, Oct.9-13, 1994, pp.63-67.
[10] Cootes, T. F., C. J. Taylor, D. H. Cooper, and J. Graham, "Active shape models-their training and application", Computer Vision and Image Understanding, vol.61, no.1, pp.38-59, 1995.
[11] Cootes, T. F. and C. J. Taylor, "Locating faces using statistical feature detectors," in Proc. 2nd Int. Conf. Automatic Face and Gesture Recognition, Killington, VT, Oct.14-16, 1996, pp.204-209.
[12] Cootes, T. F., and C. J. Taylor, Statistical Models of Appearance for Computer Vision, Technical report, Imaging Science and Biomedical Engineering, Univ. of Manchester, Manchester, UK, 2004.
[13] Cootes, T. F., D. H. Cooper, C. J. Taylor, and J. Graham, "A trainable method of parametric shape description," in Proc. 2nd British Machine Vison Conf., London, Sep.24-26, 1991, pp.54-61.
[14] Cootes, T. F., D. H. Cooper, C. J. Taylor, and J. Graham, "A trainable method of parametric shape description," Image and Vision Computing, vol.10, no.5, pp.289-294, 1992.
[15] Craw, I., H. Ellis, and J. Lishman, “Automatic extraction of face features,” Pattern Recognition Letters, vol.5, pp.183-187, 1987.
[16] Craw, I., D. Tock, and A. Bennett, “Finding face features,” in Proc. 2nd European Conf. Computer Vision, Genova, Italy, May 19-22,1992, pp.92-96.
[17] Crowley, J. L. and J. M. Bedrune, “Integration and control of reactive visual processes,” in Proc. 3rd European Conf. Computer Vision, vol.2, Stockholm, Sweden, May 2-6, 1994, pp.47-58.
[18] Dai, Y. and Y. Nakano, “Face-texture model based on SGLD and its
- 73 -
application in face detection in a color scene,” Pattern Recognition, vol.29, no.6, pp.1007-1017, 1996.
[19] Fahlman, S. E. and C. Lebiere, “The cascade-correlation learning architecture,” in Advances in Neural Information Processing Systems , vol.2, D. S. Touretsky, ed., Morgan Kaufmann, San Mateo, 1990, pp.524-532.
[20] Forsyth, D. A., “A novel approach to color constancy,” in Proc. Int. Conf. on Computer Vision, Los Alamitos, CA, Dec.5-8, pp.9-18, 1988.
[21] Graf, H. P., T. Chen, E. Petajan, and E. Cosatto, “Locating faces and facial parts,” in Proc. 1st Int. Workshop Automatic Face and Gesture Recognition, Zurich, Switzerland, Jun.26-28, 1995, pp.41-46.
[22] Graf, H. P., E. Cosatto, D. Gibbon, M. Kocheisen, and E. Petajan, “Multimodal system for locating heads and faces,” in Proc. 2nd Int. Conf. Automatic Face and Gesture Recognition, Killington, VT, Oct.14-16, 1996, pp.88-93.
[23] Haralick, R. M., K. Shanmugam, and I. Dinstein, “Texture features for image classification,” IEEE Trans. Systems, Man, and Cybernetics, vol.3, no.6, pp.610-621, 1973.
[24] Jebara, T. S. and A. Pentland, “Parameterized structure from motion for 3D adaptive feedback tracking of faces,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition, San Juan, Puerto Rico, Jun.17-19, 1997, pp.144-150.
[25] Jones, M. J. and J. M. Rehg, “Statistical color models with application to skin detection,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol.1, Fort Collins, Colorado, Jun.23-25, 1999, pp.274-280.
[26] Kass, M., A. Witkin, and D. Terzopoulos, “Snakes: active contour models,” in Proc. 1st IEEE Int. Conf. Computer Vision, London, England, Jun.8-11, 1987 pp.259-269.
[27] Kirby, M. and L. Sirovich, “Application of the karhunen-loe`ve procedure for
- 74 -
the characterization of human faces,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol.12, no.1, pp.103-108, Jan. 1990
[28] Kjeldsen, R. and J. Kender, “Finding skin in color images,” in Proc. 2nd Int’l Conf. Automatic Face and Gesture Recognition, Killington, VT, Oct.14-16, 1996, pp.312-317.
[29] Kohonen, T., Self-Organization and Associative Memory, Springer-Verlag, New York, 1989.
[30] Kwon, Y. H. and N. da Vitoria Lobo, “Face detection using templates,” in Proc. Int’l Conf. Pattern Recognition, Jerusalem, Israel, Oct.9-13, 1994, pp.764-767.
[31] Lam, K. and H. Yan, “Fast algorithm for locating head boundaries,” J. Electronic Imaging, vol.3, no.4, pp.351-359, 1994.
[32] Lanitis, A., C. J. Taylor, and T. F. Cootes, “An automatic face identification system using flexible appearance models,” Image and Vision Computing, vol.13, no.5, pp.393-401, 1995.
[33] Leung, T. K., M. C. Burl, and P. Perona, “Finding faces in cluttered scenes using random labeled graph matching,” in Proc. Fifth IEEE Int’l Conf. Computer Vision, Cambridge, Massachusetts, Jun.20-23, pp.637-644.
[34] Lu, H.-C., and W.-G. Shi, “Skin-active shape model for face alignment,” in Proc. Computer Graphics Imaging and Vision, Beijing, China, Jul.26-29, 2005, pp.187-190.
[35] Osuna, E., R. Freund, and F. Girosi, “Training support vector machines: an application to face detection,” in Proc. IEEE Conf. Computer Vision and Pattern Recognition, San Juan, Puerto Rico, Jun.17-19, 1997, pp.130-136.
[36] Rowley, H., S. Baluja, and T. Kanade, “Neural network-based face detection,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol.20, no.1, pp.23-38,
- 75 -
Jan. 1998.
[37] Sakai, T., M. Nagao, and S. Fujibayashi, “Line extraction and pattern detection in a photograph,” Pattern Recognition, vol.1, pp.233-248, 1969.
[38] Sung, K.-K., Learning and Example Selection for Object and Pattern Detection, Ph.D. dissertation, Department of Brain and Cognitive Sciences, Massachusetts Inst. of Technology, MA, 1996.
[39] Sung, K.-K. 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.
[40] Turk, M. and A. Pentland, “Eigenfaces for recognition,” J. Cognitive Neuroscience, vol.3, no.1, pp.71-86, 1991.
[41] Yang, G. and T. S. Huang, “Human face detection in complex background,” Pattern Recognition, vol.27, no.1, pp.53-63, 1994.
[42] Yang, J. and A. Waibel, “A real-time face tracker,” in Proc. Third Workshop Applications of Computer Vision, Sarasota, FL, Dec.2-4, 1996, pp.142-147.
[43] Yang, M.-H. and N. Ahuja, “Gaussian mixture model for human skin color and its application in image and video databases,” in Proc. SPIE Conf. on Storage and Retrieval for Image and Video Databases, San Jose, CA, Jan.24-29, 1999, pp.458-466.
[44] Yang, M.-H., D. Kriegman, N. Ahuja, “Detecting faces in images: a survey” IEEE Trans. on Pattern Analysis and Machine Intelligence, vo1.24, no.1, pp.34-58, Jan., 2002.
[45] Yow, K. C. and R. Cipolla, “Feature-based human face detection,” Image and Vision Computing, vol.15, no.9, pp.713-735, 1997.
[46] Yuille, A., P. Hallinan, and D. Cohen, “Feature extraction from faces using deformable templates,” Int’l J. Computer Vision, vol.8, no.2, pp.99-111, 1992.

簡易檢索 / 詳目顯示

相關論文