研究生: |
張嘉宏 Chang, Chia-Hung |
---|---|
論文名稱: |
基於遠距離人臉辨識體型與身高估測之人員識別 Human Identification Based on Distant Face Recognition Body Shape and Height Estimation |
指導教授: |
王駿發
Wang, Jhing-Fa |
學位類別: |
碩士 Master |
系所名稱: |
電機資訊學院 - 電機工程學系 Department of Electrical Engineering |
論文出版年: | 2010 |
畢業學年度: | 98 |
語文別: | 英文 |
論文頁數: | 52 |
中文關鍵詞: | 遠距離人員識別 、身高估測 、體型估測 、人臉辨識 |
外文關鍵詞: | Distant Identification, Height Estimation, Face Recognition, Body Shape Analysis, Linear Discriminant Analysis |
相關次數: | 點閱:114 下載:7 |
分享至: |
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 |
隨著科技日新月異,電影情節利用指紋、聲紋、虹膜或者人臉來辨識身分,在現在已經很容易可以達到,尤其指紋與虹膜在正確率上,相當出色,許多國家如:巴西、韓國、智利、馬來西亞、義大利等身分證上結合指紋,讓犯罪無所遁逃,然而,在人臉辨識上,距離是一大考量,如何在監視範圍內辨認身分一直是挑戰,因為隨著辨識距離越遠,辨識率也隨之下降,本篇論文使用身高與體型配合人臉辨識,提高受限於環境因素的辨識率,來實現遠距離身分辨識,論文實驗了近距離人臉辨識,改良式線性鑑別分析(Linear Discriminant Analysis) 辨識人臉,線性鑑別分析可降低維度,運算量低的優點,鑑別分析可以降低少部份光線、表情等對辨識率的影響,進而提高近距離的辨識度。遠距離取高度與體型估測結合,高度估測部分採用單視點量測(Single-View Metrology),已知攝影機高度可推估待測人物高度,體型部分使用上半身二值化圖形(Binary Image),在重複利用改良式線性鑑別分析,減少系統運算量,本系統交互使用遠近演算法,達到在限制監視範圍皆可辨別身分,辨識率約80%。
human identity by biometric information such as fingerprint, voice, iris, or face image. Since the accuracy of fingerprint and iris are excellent, many countries such as Brazil, South Korea, Chile, Malaysia and Italy …etc, combine fingerprint with ID cards for reducing the crime rate. However, the distance variance problem is a major error factor for face recognition. Especially in the situation of far distance which causes the low camera resolution, leads the human face recognition to be a challenge for a high performance.
In this thesis, we integrate face recognition with height estimation and body shape analysis to improve the far-field human identification accuracy for constrained environment. The proposed face recognition system adopts the fusion of single-view height estimation and body shape analysis. A subject height is estimated by the camera height information and the body shape is analyzed by binary image of upper body. Based on the improved linear discriminant analysis (LDA) algorithm, our system is able to reduce the illumination and the facial expressions effects on the recognition rate. Experimental results indicate that the proposed system can reach around 80% recognition rate in the both of near and far constrained surveillance fields.
[1] Ping-Han Lee, Gee-Sern Hsu, Yi-Ping Hung, “Face Verification And Identification Using Facial Trait Code”, Accepted by the IEEE Computer Society Conference on Computer Vision and Pattern Recognition to be held on June 20-25, 2009, Miami beach, Florida
[2] R.J. Baron, “Mechanisms of human facial recognition”, Int. J. Man-Machine Studies, 1981.
[3] D. Xu, S. Yan Lin,S. Huang, and T.S., “Convergent 2-D Subspace Learning With Null Space Analysis,” Circuits and Systems for Video Technology, IEEE Transactions, Volume 18, Dec. 2008, p.1753-1759
[4] P.N Belhumeur, J.P. Hespanha, and D.J. Kriegman,, "Eigenfaces vs. Fisherfaces: recognition using class specific linear projection," IEEE Transactions, Pattern Analysis and Machine Intelligence, 1997
[5] P.N. Belhumeur and D.J. Kriegman, “What is the set of images of an object under all possible lighting conditions?” In Proceedings, IEEE Conference on Computer Vision and Pattern Recognition. 52–58, 1997.
[6] C. Tian, G. Fan, and X. Gao, “Multi-view face recognition by nonlinear tensor decomposition ,” Pattern Recognition, 2008, p.1-4
[7] V. Blanz and T. Vetter, “Face recognition based on fitting a 3D morphable model”, IEEE Trans. PAMI, 2003, vol. 25, no. 9, pp. 1063-1074.
[8] C.P. Chen and C.S. Chen, “Lighting Normalization with Generic Intrinsic Illumination Subspace for Face Recognition,” accepted by IEEE International Conference on Computer Vision, ICCV 2005, Beijing, China, October 2005
[9] G. Guo, S.Z. Li and K. Chan, “Face Recognition by Support Vector Machines”, Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000 pp. 196
[10] V.V. Kohir and U.B. Desai, “Face recognition using a DCT-HMM approach,” in Proc. IEEE Workshop on Applications of Computer Vision (WACV’98), Princeton, NJ, 1998, pp.226–231.
[11] K.C. Lee, J. Ho, M.H. Yang and D. Kriegman , “Visual tracking and recognition using probabilistic appearance manifolds”, Computer Vision and Image Understanding 99, 2005, pp.303–331
[12] A. Criminisi, I. Reid and A. Zisserman, ”Single View Metrology,” Proceedings of the 7th International Conference on Computer Vision(ICCC’09), Sep. 1999, Kerkyra, Greece, pp. 434-41
[13] A. Criminisi, “Single-View Metrology: Algorithms and Applications,” Proceedings of the 24th DAGM Symposium on Pattern Recognition, 2002, Pages: 224 - 239
[14] Z. Pan, R. Adams, and H. Bolouri, “Dimensionality reduction of face images using discrete cosine transforms for recognition,” IEEE Conference on Computer Vision and Pattern Recognition, 2000.
[15] Ojala, T., Pietikainen, M., Harwood, D.: A Comparative Study of texture Measures with Classification based on Featured Distributions. J. Pattern Recognition 29(1), 51–59 (1996)
[16] H. A. 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.
[17] T.R. Raviv and A. Shashua, “The quotient image: Class based re-rendering and recognition with varying illuminations”. In Proceedings, IEEE Conference on Computer Vision and Pattern Recognition. 566–571, 1999.
[18] 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.
[19] M.A. Turk and A.P. Pentland, "Face recognition using eigenfaces," presented at Computer Vision and Pattern Recognition, 1991.
[20] M. Kirby and L. Sirovich, ”Application of the Karhunen-Loeve procedure for the characterization of human faces”. IEEE Trans.Patt. Anal. Mach. Intell. 12, 1990.
[21] Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution Gray Scale and Rotation Invariant Texture Classification with Local Binary Pattern. J. Pattern Analysis and Machine Intelligence, IEEE Transaction 24(7), 971–987 (2002)
[22] P. Viola and M.J. Jones, "Rapid Object Detection using a Boosted Cascade of Simple Features," in Proceedings of the IEEE Computer Society International Conference on Computer Vision and Pattern Recognition, vol. 1, pp. 511-518, Dec. 2001.
[23] Ahonen, T., Hadid, A., Pietikäinen, M.: Face Recognition with Local Binary Patterns. In:Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3021, pp. 469–481. Springer, Heidelberg (2004)
[24] H.T. Wang, S.Z. Li, Y.S. Wang, “Face Recognition under Varying Lighting Conditions Using Self Quotient Image”, Automatic Face and Gesture Recognition. Proceedings. Sixth IEEE International Conference on Publication, 17-19 May 2004
[25] K.C. Lee and J. Ho and D. Kriegman, "Acquiring Linear Subspaces for Face Recognition under Variable Lighting ", IEEE Trans. Pattern Anal. Mach. Intelligence, volume 27, no. 5, p.684-698, 2005
[26] J. Ye. , “Characterization of a family of algorithms for generalized discriminant analysis on under-sampled problems.” Journal of Machine Learning Research, 6:483–502, 2005.
[27] Verma B., Selvaraj H., de Carvalho A. and Yao X “Human shape recognition from snakes using neural networks,” pp. 292-296, in Proc. 3rd International Conference on Computational Intelligence and Multimedia Applications (ICCIMA), Delhi, India, 1999.
[28] Kass M., Witkin A. & Terzopoulos D. Snakes: active contour models. In International Journal of Computer Vision, 1988, pp.321-331
[29] Liang Wang and David Suter, “Learning and Matching of Dynamic Shape Manifolds for Human Action Recognition”, IP(16), No. 6, June 2007, pp. 1646-1661. IEEE
[30] Chikahito Nakajima, Massimiliano Pontil , Bernd Heiselec and, Tomaso Poggioc “Full-body person recognition system”, Journal of Pattern Recognition ,2003
[31] Kazuki Hoshiai , Shinya Fujie , and Tetsunori Kobayashi, “Upper-body Contour Extraction and Tracking Using Face and Body Shape Variance Information”, IEEE-RAS International Conference on Humanoid Robots , 2008
[32] István Kispál and Ern Jeges, “Human height estimation using a calibrated camera”, In Proc. CVPR, 2008
[33] C. Ben Abdelkader and Y. Yacoob, (2008) Statistical body height estimation from a single image, Proceedings of 8th IEEE International Conference on Automatic Face and Gesture Recognition, 1-7.
[34] Morita Shinzi, Kazumasa Yamazawa, Akihiko Terasawa Tadashi, Naokazu Yokoya: "network-friendly remote monitoring system for omnidirectional image sensors," Journal of IEICE (D-II), Vol. J88-D- II, No. 5, pp. 864-875, (2005.5).
[35] M. Alex O. Vasilescu and Demetri Terzopoulos, “Multilinear Image Analysis for Facial Recognition,” Proc. of the International Conference on Pattern Recognition (ICPR’02), Quebec City, Canada, August, 2002, Vol 3: 511–514.
[36] Fukunaga, “Introduction To Statistical Pattern Recognition,” 2nd, 1990
[37] 森田真司,山澤一誠,寺沢征彦,横矢直和:”全方位画像センサを用いたネットワーク対応型遠隔監視システム,” 電子情報通信学会論文誌(D-II), Vol. J88-D-II, No. 5, pp. 864-875, (2005.5).
[38] http://www.cl.cam.ac.uk/research/dtg/attarchive/facedatabase.html
[39] ftp://ftp.wisdom.weizmann.ac.il/pub/FaceBase/
[40] 林咸仁,“改良線式鑑別式分析在少量訓練樣本下之人臉辨識研究,”資訊工程碩士論文, July, 2002