iccv iccv2013 iccv2013-355 iccv2013-355-reference knowledge-graph by maker-knowledge-mining

355 iccv-2013-Robust Face Landmark Estimation under Occlusion


Source: pdf

Author: Xavier P. Burgos-Artizzu, Pietro Perona, Piotr Dollár

Abstract: Human faces captured in real-world conditions present large variations in shape and occlusions due to differences in pose, expression, use of accessories such as sunglasses and hats and interactions with objects (e.g. food). Current face landmark estimation approaches struggle under such conditions since theyfail toprovide aprincipled way ofhandling outliers. We propose a novel method, called Robust Cascaded Pose Regression (RCPR) which reduces exposure to outliers by detecting occlusions explicitly and using robust shape-indexed features. We show that RCPR improves on previous landmark estimation methods on three popular face datasets (LFPW, LFW and HELEN). We further explore RCPR ’s performance by introducing a novel face dataset focused on occlusion, composed of 1,007 faces presenting a wide range of occlusion patterns. RCPR reduces failure cases by half on all four datasets, at the same time as it detects face occlusions with a 80/40% precision/recall.


reference text

[1] P. Belhumeur, D. Jacobs, D. Kriegman, and N. Kumar. Localizing parts of faces using a concensus of exemplars. In CVPR, 2011.

[2] L. Bourdev and J. Malik. Poselets:body part detectors trained using 3D human pose annotations. In ICCV, 2009.

[3] S. Branson, C. Wah, F. Babenko, B. Schroff, P. Welinder, P. Perona, and S. Belongie. Visual recognition with humans in the loop. In ECCV, 2010.

[4] X. Burgos-Artizzu, P. Doll a´r, D. Lin, D. Anderson, and P. Perona. Social behavior recognition in continuous videos. In CVPR, 2012.

[5] M. Burl, M. Weber, and P. Perona. A probabilistic approach to object recognition using local photometry and global geometry. In ECCV, 1998.

[6] C. Cao, Y. Weng, S. Lin, and K. Zhou. 3D shape regression

[7]

[8]

[9]

[10]

[11]

[12]

[13]

[14]

[15]

[16]

[17]

[18]

[19]

[20] for real-time facial animation. In SIGGRAPH, 2013. X. Cao, Y. Wei, F. Wen, and J. Sun. Face alignment by explicit shape regression. In CVPR, 2012. H. Cevikalp, B. Triggs, and V. Franc. Face and landmark detection by using cascade of classifiers. In FG, 2013. T. Cootes, G. Edwards, and C. Taylor. Active appearance models. PAMI, 23(6):681–685, 2001. T. Cootes and C. Taylor. Active shape models. In BMVC, 1992. D. Cristinacce and T. Cootes. Boosted regression active shape models. In BMVC, 2007. M. Dantone, J. Gall, G. Fanelli, and L. VanGool. Real-time facial feature detection using conditional regression forests. In CVPR, 2012. L. Ding and A. Martinez. Features vs. context: An approach for precise and detailed det. and delineation of faces and facial features. PAMI, 32(1 1):2022–2038, 2010. P. Doll a´r, P. Welinder, and P. Perona. Cascaded pose regression. In CVPR, 2010. N. Duffy and D. P. Helmbold. Boosting methods for regression. Machine Learning, 47(2-3): 153–200, 2002. B. Efraty, C. Huang, S. Shah, and I. Kakadiaris. Facial landmark det. in uncontrolled conditions. In IJCB, 2011. P. Ekman and W. Friesen. Facial action coding system. 1977. N. K. et al. Leafsnap: A computer vision system for automatic plant species identification. In ECCV, 2012. M. Everingham, J. Sivic, and A. Zisserman. Hello! My name is... Buffy - automatic naming of characters in tv video. In BMVC, 2006. P. Felzenszwalb, R. Girshick, D. McAllester, and D. Ramanan. Object detection with discriminatively trained part

[21]

[22]

[23]

[24]

[25]

[26]

[27]

[28]

[29]

[30] [3 1]

[32]

[33]

[34] based models. PAMI, 32(9): 1627–1645, 2010. F. Fleuret and D. Geman. Fast face detection with precise pose estimation. In ICPR, 2002. F. Fleuret and D. Geman. Stationary feat. and cat detection. J. of Machine Learning Research, 9:2549–2578, 2008. J. H. Friedman. Greedy function approximation:a gradient boosting machine. The Annals of Statistics, 29(5): 1189– 1232, 2001. R. Gross, I. Matthews, J. Cohn, T. Kanade, and S. Baker. Multi-pie. In FG, 2008. I. P. H. Yang. Privileged information-based conditional regression forest for facial feature detection. In FG, 2013. G. Huang, M. Ramesh, T. Berg, and E. Learned-Miller. Labeled faces in the wild: A database for studying face rec. in unconstr. environments. Technical report, Amherst, 2007. O. Jesorsky, K. J. Kirchberg, and R. W. Frischholz. Robust face detection using the Hausdorff dist. In AVBPA, 2001 . M. Kass, A. Witkin, and D. Terzopoulos. Snakes: Active contour models. IJCV, 1(4):321–33 1, 1988. V. Le, J. Brandt, Z. Lin, L. Bourdev, and T. S. Huang. Interactive facial feature localization. In ECCV, 2012. A. Martinez and S. Du. A model of the perception of facial expressions of emotion by humans: Research overview and perspectives. JMLR, 13: 1589–1608, 2012. I. Matthews and S. Baker. Active appearance models revisited. IJCV, 60: 135–164, 2004. S. Milborrow and F. Nicolls. Locating facial features with an extended active shape model. In ECCV, 2008. E. Murphy-Chutorian and M. Trivedi. Head pose estimation in computer vision:a survey. PAMI, 3 1(4):607–626, 2009. M.-E. Nilsback and A. Zisserman. Automated flower classi-

[35]

[36]

[37]

[38]

[39]

[40]

[41]

[42]

[43]

[44]

[45]

[46] fication over a large num. of classes. In ICVGIP, 2008. M. Ozuysal, M. Calonder, V. Lepetit, and P. Fua. Fast keypoint recognition using random ferns. PAMI, 32(3):448–461, 2010. J. Saragih, S. Lucey, and J. F. Cohn. Deformable model fitting by regularized landmark mean-shift. IJCV, 2(91):200– 215, 2011. C. P. Sauer and T. Cootes. Accurate regression procedures for active appearance models. In BMVC, 2011. J. Sivic, M. Everingham, and A. Zisserman. Who are you? Learning person specific classifiers from video. In CVPR, 2009. M. Valstar, B. Martinez, X. Binefa, and M. Pantic. Facial point detection using boosted regression and graph models. In CVPR, 2010. C. Wah, S. Branson, P. Perona, and B. S. Multiclass recog. and part localiz. with humans in the loop. In ICCV, 2011. M. Weber, W. Einhauser, M. Welling, and P. Perona. Viewpoint-invariant learning and detection of human heads. In FG, 2000. H. Yang and I. Patras. Face parts localization using structured-output regression forests. In ACCV, 2012. M.-H. Yang, D. Kriegman, and N. Ahuja. Detecting faces in images: a survey. PAMI, 24(1):34–58, 2002. Y. Yang, S. Baker, A. Kannan, and D. Ramanan. Recognizing proxemics in personal photos. In CVPR, 2012. A. L. Yuille, P. Hallinan, and D. S. Cohen. Feature extraction from faces using deformable templates. IJCV, 8(2):99–1 11, 1992. W. Zhao, R. Chellappa, P. Phillips, and A. Rosenfeld. Face recognition: A literature survey. ACM Computing Surveys, 35(4):399–458, 2003.

[47] X. Zhu and D. Ramanan. Face detection, pose estimation, and landmark localiz. in the wild. In CVPR, 2012. 11552200