Abstract
Shape alignment or estimation under occlusion is one of the most challenging tasks in computer vision field. Most previous works treat occlusion as noises or part models, which usually lead to low accuracy or inefficiencies. This paper proposes an efficient and accurate regression-based algorithm for face alignment. In this framework, local and global regressions are iteratively used to train a series of random forests in a cascaded manner. In training and testing process, each step consists of two layers. In the first layer, a set of highly discriminative local features are extracted from local regions according to locality principle. The regression forests are trained for each facial landmark independently using those local features. Then the leaf node of the regression tree is encoded by histogram statistic method and the final shape is estimated by a linear regression matrix. In the second layer, our proposed global features are generated. Then we use those features to train a random fern to keep the global shape constraints. Experiments show that our method has a high speed, but same or slightly lower accuracy than state of the art methods under occlusion condition. In order to gain a higher accuracy we use multi-random shape for initialization, which may slightly reduce the calculation efficiency as a trade-off.
Similar content being viewed by others
References
Belhumeur PN, Jacobs DW, Kriegman DJ, Kumar N (2013) Localizing parts of faces using a consensus of exemplars. IEEE Int Conf Comput Vis 35(12):545–552
Breiman L (2001) Random forests. Mach Learn 45:5–32
Burgos-Atrizzu XP, Perona P, Dollar P (2013) Robust face landmark estimation under occlusion. IEEE Int Conf Comput Vis:1–6
Cao X, Wei Y, Wen F, Sun J (2012) Face alignment by explicit shape regression. Int J Comput Vis 107(2):2887–2894
Cao C, Weng Y, Lin S, Zhou K (2013) 3d shape regression for real-time facial animation. ACM Trans Graph 32(4):96–96
Cootes TF, Edwards GJ, Taylor CJ (1998) Active appearance models. Springer Berlin Heidelberg 1407(6):484–498
Cootes T, Taylor C (1995) Active shape models. Br Mach Vis Conf (BMVC):266–275
Cristinacce D, Cootes T (2007) Boosted regression active shape models. Br Mach Vis Conf (BMVC). doi:10.5244/C.21.79
Cui Y, Zhang J, Guo D, Jin Z (2015) Robust facial landmark localization using classified random ferns and pose-based initialization. Signal Process 110:46–53
Dantone M, Gall J, Fanelli G, Van Gool L (2012) Real-time facial feature detection using conditional regression forests. IEEE Conf Comput Vis Pattern Recog 157(10):2578–2585
Ding L, Martinez A (2010) Features vs. context: an approach for precise and detailed det. and delineation of faces and facial features. IEEE Trans Pattern Anal Mach Intell (PAMI) 32(11):2022–2038
Dollar P, Welinder P, Perona P (2010) Cascaded pose regression. IEEE Conf Comput Vis Pattern Recog 238(6):1078–1085
Ghiasi G, Fowlkes CC (2014) Occlusion coherence: localizing occluded faces with a hierarchical deformable part model. IEEE Conf Comput Vis Pattern Recog:1899–1906
Gonzalez RC, Woods RE (2007) Digital image processing [M], 3rd edn. [S.1.], Prentice Hall
Kass M, Witkin A, Terzopoulos D (1988) Snakes: active contour models. Int J Comput Vis (IJCV) 1(4):321–331
Kazemi V, Sullivan J (2014) One millisecond face alignment with an ensemble of regression trees. IEEE Conf Comput Vis Pattern Recog:1867–1874
Le V, Brandt J, Lin Z, Bourdev L, Huang TS (2012) Interactive facial feature localization. Springer Berlin Heidelberg 7574(1):679–692
Matthews I, Baker S (2004) Active appearance models revisited. Int J Comput Vis (IJCV) 60(2):135–164
Milborrow S, Nicolls F (2008) Locating facial features with an extended active shape model. Eur Conf Comput Vis: Part IV 5305:504–513
Ren S, Cao X, Wei Y, Sun J (2014) Face Alignment at 3000 FPS via regressing local binary features. IEEE Conf Comput Vis Pattern Recog:1685–1692
Sauer CP, Cootes T (2011) Accurate regression procedures for active appearance models. Br Mach Vis Conf (BMVC) 1(6):681–685
Tzimiropoulos G, Pantic M (2013) Optimization problem for fast AAM fitting in the wild. IEEE Int Conf Comput Vis 120(10):593–600
Acknowledgments
This paper is supported by “National Natural Science Foundations of China (No.11201136)” and “the Science and Technology Planning Project of Hunan Province (2014WK3002)”.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Guo, S., Tan, G., Pan, H. et al. Face alignment under occlusion based on local and global feature regression. Multimed Tools Appl 76, 8677–8694 (2017). https://doi.org/10.1007/s11042-016-3470-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-016-3470-7