computer animation virtual worlds LEARNING-BASED 3D FACE DETECTION detection of geometric facial features for applications 13.Mitra NJ,Guibas LJ,Pauly M.Partial and approximate in facial expression cloning and editing.In addition, symmetry detection for 3d geometry.ACM Transactions on as a rich,compact yet discriminative shape descriptor, Graphics2006;25(3):560-568. geometric context can be further investigated to patch 14.Freund Y,Schapire R.A decision-theoretic generalization of on-line learning and an application to boosting.Journal of registration of geometric data.In this way,the optimized Computer and System Sciences 1997:55:119-139. pairwise matching for different sets of geometric contexts 15.Colombo A,Cusano C,Schettini R.3d face detection using needs to be meticulously considered.We will investigate curvature analysis.Pattern Recognition 2006;39(3):444-455. it in future. 16. Belongie S,Malik J,Puzicha J.Shape matching and object recognition using shape contexts.IEEE Transactions on PAMI 2002:244上：509-522. ACKNOWLEDGMENTS 17.Huber D,Hebert M.Fully automatic registration of multiple 3d data sets.Image and Vision Computing 2003;21(7):637-650. 18.Gelfand N,Mitra NI,Guibas LJ,Pottmann H.Robust global The work is supported by CUHK Direct Research Grant(No. registration.In Symposium on Geometry Processing,2005; 2050349),National973 program (No.2002CB312101),and NSFC Pp.197-206. grant(No.60403038)in China.The authors thank Dr Feng Tang 19.Dong Z,Chen W,Bao HJ,Zhang HX,Peng QHS.Real- for his helpful discussion and the anonymous reviewers for their time voxelization for complex polygonal models.In Pacific thoughtful comments.Models are courtesy of the University of Graphics,2004;pp.73-78. South Florida,University of Washington Graphics and Imaging 20.Blanz V,Vetter T.Morphable model for the synthesis of 3d Laboratory,National Taiwan University,max-planck-institut faces.In Siggraph 99,pp.187-194,1999. informatik and the aim@shape database.2 All the models listed 21.Zhang L,Snavely N,Curless B,Seitz S.Spacetime faces: in this paper are used for academic research only. high-resolution capture for modeling and animation.ACM Transactions on Graphics 2004;23(3):548-558. 22.http://3d.csie.ntu.edu.tw/~dynamic/databa-se/index. References html 23.http://www.aimatshape.net 1.Rowley HA,Baluja S,Kanade T.Neural network-based Authors'biographies: human face detection.IEEE Transactions on PAMI1998;20(1): 23-38. 2.Viola P,Jones M.Rapid object detection using a boosted cascade of simple features.In IEEE Conference on Computer Vision and Pattern Recognition,2001;511-518. 3.Zhang Z,Li SZ,Zhang H.Real-time multi-view face detection.In Conference on Automatic Face and Gesture Recognition,2002;149-154. 4.Yang MH,Kriegman D,Ahuja N.Detecting faces in images: a survey.IEEE Transactions on PAMI 2002;24(1):34-58. 5.Phillips PJ,Moon H,Rizvi S,Rauss P.The feret Yanwen Guo born in 1980,is now an Assistant evaluation methodology for face-recognition algorithms Professor at the National Laboratory for Novel Software IEEE Transactions on PAMI 2000;22(10):1090-1104. Technology,Nanjing University,P.R.China.He received 6.Gordon GG.Face recognition based on depth and curvature his Ph.D.in State Key Lab of CAD&CG,Zhejiang feat1re.1992:108-110. University in 2006.His research interests include real- 7.Chang KI,Bowyer KW,Flynn PJ.An evaluation of multi- time computer graphics,image video processing,and model 2d+3d biometrics.IEEE Transactions on PAMI 2005; computer vision. 27(4):619-624. 8.Guo YW,Wang J,Sun HQ,Peng QHS.A novel constrained texture mapping method based on harmonic map.Computers Graphics 2005;29(6):972-979. 9.Funkhouser T,Min P,Kazhdan M,et al.A search engine for 3d models.ACM Transactions on Graphtics 2003;22(1):83-105. 10.Von Funck W,Theisel H,Seidel HP.Shape matching based on fully automatic face detection on triangular meshes.In Computer Graphics International,vol.4035.pp.242-253,2006. 11.Sun C,Sherrah J.3d symmetry detection using extended Gaussian image.IEEE Transactions on PAMI1997;19(2):164- Fuyan Zhang is now a Professor at the National Labora- 168 tory for Novel Software Technology,Nanjing University, 12.Podolak J,Shilane P,et al.A planar-reflective symmetry P.R.China.His research interests include computer transform for 3d shapes.ACM Transactions on Graphics 2006; graphics,digital library,multimedia computing,and 25(3:549-559 system. Copyright 2007 John Wiley Sons,Ltd. 491 Comp.Anim.Virtual Worlds 2007;18:483-492 DOL:10.1002/caVLEARNING-BASED 3D FACE DETECTION ........................................................................................... detection of geometric facial features for applications in facial expression cloning and editing. In addition, as a rich, compact yet discriminative shape descriptor, geometric context can be further investigated to patch registration of geometric data. In this way, the optimized pairwise matching for different sets of geometric contexts needs to be meticulously considered. We will investigate it in future. ACKNOWLEDGMENTS The work is supported by CUHK Direct Research Grant (No. 2050349), National 973 program (No. 2002CB312101), and NSFC grant (No. 60403038) in China. The authors thank Dr Feng Tang for his helpful discussion and the anonymous reviewers for their thoughtful comments. Models are courtesy of the University of South Florida, University of Washington Graphics and Imaging Laboratory, National Taiwan University, max-planck-institut informatik and the aim@shape database.23 All the models listed in this paper are used for academic research only. References 1. Rowley HA, Baluja S, Kanade T. Neural network-based human face detection. IEEE Transactions on PAMI 1998; 20(1): 23–38. 2. Viola P, Jones M. Rapid object detection using a boosted cascade of simple features. In IEEE Conference on Computer Vision and Pattern Recognition, 2001; 511–518. 3. Zhang Z, Li SZ, Zhang H. Real-time multi-view face detection. In Conference on Automatic Face and Gesture Recognition, 2002; 149–154. 4. Yang MH, Kriegman D, Ahuja N. Detecting faces in images: a survey. IEEE Transactions on PAMI 2002; 24(1): 34–58. 5. Phillips PJ, Moon H, Rizvi S, Rauss P. The feret evaluation methodology for face-recognition algorithms. IEEE Transactions on PAMI 2000; 22(10): 1090–1104. 6. Gordon GG. Face recognition based on depth and curvature feature. 1992; 108–110. 7. Chang KI, Bowyer KW, Flynn PJ. An evaluation of multi￾model 2d+3d biometrics. IEEE Transactions on PAMI 2005; 27(4): 619–624. 8. Guo YW, Wang J, Sun HQ, Peng QHS. A novel constrained texture mapping method based on harmonic map. Computers & Graphics 2005; 29(6): 972–979. 9. Funkhouser T, Min P, Kazhdan M, et al. A search engine for 3d models. ACM Transactions on Graphics 2003; 22(1): 83–105. 10. Von Funck W, Theisel H, Seidel HP. Shape matching based on fully automatic face detection on triangular meshes. In Computer Graphics International, vol. 4035. pp. 242–253, 2006. 11. Sun C, Sherrah J. 3d symmetry detection using extended Gaussian image. IEEE Transactions on PAMI 1997; 19(2): 164– 168. 12. Podolak J, Shilane P, et al. A planar-reflective symmetry transform for 3d shapes. ACM Transactions on Graphics 2006; 25(3): 549–559. 13. Mitra NJ, Guibas LJ, Pauly M. Partial and approximate symmetry detection for 3d geometry. ACM Transactions on Graphics 2006; 25(3): 560–568. 14. Freund Y, Schapire R. A decision-theoretic generalization of on-line learning and an application to boosting. Journal of Computer and System Sciences 1997; 55: 119–139. 15. Colombo A, Cusano C, Schettini R. 3d face detection using curvature analysis. Pattern Recognition 2006; 39(3): 444–455. 16. Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts. IEEE Transactions on PAMI 2002; 24(4): 509–522. 17. Huber D, Hebert M. Fully automatic registration of multiple 3d data sets. Image and Vision Computing 2003; 21(7): 637–650. 18. Gelfand N, Mitra NJ, Guibas LJ, Pottmann H. Robust global registration. In Symposium on Geometry Processing, 2005; pp. 197–206. 19. Dong Z, Chen W, Bao HJ, Zhang HX, Peng QHS. Real￾time voxelization for complex polygonal models. In Pacific Graphics, 2004; pp. 73–78. 20. Blanz V, Vetter T. Morphable model for the synthesis of 3d faces. In Siggraph 99, pp. 187–194, 1999. 21. Zhang L, Snavely N, Curless B, Seitz S. Spacetime faces: high-resolution capture for modeling and animation. ACM Transactions on Graphics 2004; 23(3): 548–558. 22. http://3d.csie.ntu.edu.tw/∼dynamic/databa-se/index. html 23. http://www.aimatshape.net Authors’ biographies: Yanwen Guo born in 1980, is now an Assistant Professor at the National Laboratory for Novel Software Technology, Nanjing University, P.R. China. He received his Ph.D. in State Key Lab of CAD&CG, Zhejiang University in 2006. His research interests include real￾time computer graphics, image video processing, and computer vision. Fuyan Zhang is now a Professor at the National Labora￾tory for Novel Software Technology, Nanjing University, P.R. China. His research interests include computer graphics, digital library, multimedia computing, and system. ............................................................................................ Copyright © 2007 John Wiley & Sons, Ltd. 491 Comp. Anim. Virtual Worlds 2007; 18: 483–492 DOI: 10.1002/cav