未來展望

目前本系統仍有許多可改善的空間：

1. 在特徵擷取方面

在利用影像校正迭代法追蹤人臉時，若人臉光源變化較為劇烈時，則容

光源變化的關係，而讓系統誤以為特徵點已收斂，影響後端的辨識。可 以將影像做具有抗光源變化的Gabor Wavelet 轉換，再去做影像迭代的 動作。本系統在人臉左右偏轉角度的限制為 30 度以內，若人臉偏轉超 過 30 度時，則必須再重新找出角度偏轉過多的人臉的形狀模型與紋理 模型，且特徵點需重新定義，若是利用2D AAM 與 3D 的做結合，則系 統可以知道使用者目前的偏轉角度，並去做迭代校正。

2. 在人臉辨識方面

雖然利用 PCA 的方法能夠進行維度的縮減，但相對的也遺失了少許資 訊，造成在辨識上的誤差。可以試著找出不需進行化減亦可不會讓辨識 速度降低太多的方法。同理，在做人臉辨識的比對時，若資料庫成員變 多時，相對的比對的速度就會降低。是否能先從資料庫找出各個家庭成 員的關鍵性特徵部份，若能找出每個成員的關鍵性特徵，再對此關鍵性 特徵做維度化減，則當進行成員比對時，可以只做關鍵性特徵上的比對 即可，讓系統的速度能再加快；另外在辨識人臉時，當受測者為非資料 庫之成員時，如何準確的判別受測者為非家庭成員為我們未來的重要議 題。

參考文獻

[1] http://www.robotworld.org.tw/index.htm?pid=10&News_ID=342/

[2] http://www.nec.co.jp/robot/english/intro/intro_01.html

[3] http://www.stcsm.gov.cn/detail/detail.aspx?tbno=202&id=34537 [4] http://www.mhi.co.jp/kobe/wakamaru/english/live/index.html [5] http://www.pitotech.com.tw/c/6-product06-2.htm

[6] M. A. Turk and A. P. Pentland, “Face Recognition using Eigenfaces,” Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, USA, 1991, pp. 586-591.

[7] P. N. Belhumeur, J. P. Hespanha and D. J. Kriegman, “Eigenfaces vs. Fisherfaces:

Recognition using Class Specific Linear Projection,” Proc. of IEEE Transactions on Pattern Analysis and Machine Intelligence, USA, vol. 19, no. 7, 1997, pp.

711-720.

[8] W. Chen, M. J. Er and S. Wu, “Illumination Compensation and Normalization for Robust Face Recognition using Discrete Cosine Transform in Logarithm Domain,” Proc. of IEEE Transactions on Systems, Man, and Cybernetics, Singapore, vol. 36, no. 2, 2006, pp.458-466.

[9] L. Wiskott, J. M. Fellous, N. Kruger and V. D. Malsburg, “Face Recognition by Elastic Bunch Graph Matching,” Proc. of IEEE Transactions on Pattern Analysis and Machine Intelligence, Germany, 1997, pp. 775-779.

[10] H. Wang, S. Li and Y. Wang, “Face Recognition under Varying Lighting Conditions using Self Quotient Image,” Proc. of IEEE International Conference on Automatic Face and Gesture Recognition, China, 2004, pp.

819-824.

[11] D. V. Jadhav and R. S. Holambe, “Multiresolution based Kernel Fisher Discriminant Model for Face Recognition,” Proc. of IEEE International Conference on Information Technology, India, 2007, pp. 848-853.

[12] A. T. Gualberto, S. P. Gabriel, N. M. Mariko and P. M. Hector, “Face Recognition Algorithm using The Discrete Gabor Transform,” Proc. of IEEE International Conference on Electronics, Communications and Computers, Mexico, 2007, pp.

[13] P. Jia and H. Hu, “AAM Based HCI for an Intelligent Wheelchair,” Proceedings of the 1st International Symposium on Multispectral Image Processing and Pattern Recognition, China, 2007.

[14] J. Xiao, S. Baker, I. Matthews and T. Kanade, “Real-Time Combined 2D+3D Active Appearance Models,” Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, USA, 2004, pp 535-542.

[15] R. Gross, S. Baker and I. Matthews, “Constructing and Fitting Active Appearance Models with Occlusion,” Proc. of IEEE International Conference on Computer Vision and Pattern Recognition Workshop, USA, 2004, pp. 72-80.

[16] Y. H. Liu and Y. T. Chen, “Face Recognition Using Total Margin-Based Adaptive Fuzzy Support Vector Machines”, Proc. of IEEE Transactions on Neural Networks, Taiwan, vol. 18, no. 1, 2007, pp. 178-192.

[17] T. Ahonen, A. Hadid, M. Pietikainen, “Face Description with Local Binary Patterns: application to Face Recognition”, Proc. of IEEE Transactions on Pattern Analysis and Machine Intelligence, Finland, 2006, pp 2037-2041.

[18] 陳文俊, 人臉辨識及其在家用機器人與人互動之應用, 碩士論文, 國立交通 大學電機與控制工程學系, 2002.

[19] 汪慶祥, 利用三維資訊做人臉辨識, 碩士論文, 國立交通大學資訊科學系, 2000.

[20] 林晁立, 以臉部器官形狀,寬度,相對位置從事人臉影像辨識, 碩士論文, 私立 東海大學資訊科學系, 2000.

[21] 陳嘉雄, 多角度人臉之二階段辨識, 碩士論文, 國立東華大學資訊工程系, 2002.

[22] 梁皓雲, 利用區塊人臉特徵為基礎之混合式人臉辨識系統, 碩士論文, 國立 中央大學資訊工程系, 2006.

[23] 周崇民, 光源變化下之即時人臉追蹤, 碩士論文, 國立交通大學電機與控制 工程學系, 2005.

[24] P. Viola and M. Jones, “Rapid Object Dectetion Using a Boosted Cascade of Simple Features,” Proc. IEEE Conf. on Computer Vision and Pattern Recognition, 2001.

[25] T. F. Cootes and C. J. Taylor, Technical Report: Statistical Models of Appearance for Computer Vision, The University of Manchester School of Medicine, 2004.

[26] http://www2.imm.dtu.dk/~aam/

[27] T. F. Cootes, C. J. Taylor, D. H. Cooper and J. Graham, “Active Shape Models-Their Training and Application,” Computer Vision and Image Understanding, 1995, vol. 61, no.1, pp.38-59.

[28] J.R. Shewchuk, Triangle: engineering a 2D quality mesh generator and Delaunay triangulator, In Applied Computational Geometry, FCRC'96 Workshop, pp.

203-222. Springer-Verlag, 1996.

[29] T. F. Cootes, G. J. Edwards and C. J. Taylor, “Active Appearance Models,” Proc.

of IEEE Transactions on Pattern Analysis and Machine Intelligence, UK, 2001, pp. 681-685.

[30] I. Matthews and S. Baker, “Active Appearance Models Revisited,” International Journal of Computer Vision, vol. 60, no.2, 2004, pp.135-164.

[31] S. Baker, F. Dellaert, and I. Matthews, “Aligning Images Incrementally Backwards,” Technical Report CMU-RI-TR-01-03, Robotics Institute, Carnegie Mellon University, 2001.

[32] S. Baker and I. Matthews, “Lucas-Kanade 20 Years On: A Unifying Framework:

Part 1,” Technical Report CMU-RI-TR-02-16, Robotics Institute, Carnegie Mellon University, 2002.

[33] P. Jia, “Active Appearance Model,” Online technical report available from http://www.visionopen.com/members/jiapei/pei_aamreport2006.pdf.

[34] S. Baker, R. Gross, I. Matthews and T. Ishikawa, “Lucas-Kanade 20 Years On: A Unifying Framework: Part 2,” Technical Report CMU-RI-TR-03-01, Robotics Institute, Carnegie Mellon University, 2003.

[35] S. Baker, R. Gross and I. Matthews, “Lucas-Kanade 20 Years On: A Unifying Framework: Part 3,” Technical Report CMU-RI-TR-03-35, Robotics Institute, Carnegie Mellon University, 2003.

[36] S.J. Leon, Linear Algebra with Application, Prentice Hall, 2002.

[37] H. Gupta, A. K. Agrawal, T. Pruthi, C. Shekhar and R. Chellappa, “An Experimental Evaluation of Linear and Kernel-Based Methods for Face Recognition”, Proc. of IEEE Workshop on Applications and Computer Vision, USA, 2002, pp 13-18.

[38] A. Henrry and K. T. Song, “Embedded CMOS Imaging System for Real-Time Robotic Vision”, Proc. of IEEE International Conference on Intelligent Robots and Systems, Edmonton, Alberta, Canada, 2005, pp.3694-3699..

[39] images.ee.umist.ac.uk/danny/database.html.