Abstract
In this paper, we propose a novel algorithm for general 2D image matching, which is known to be an NP-complete optimization problem. With our algorithm, the complexity is handled by sequentially optimizing the image columns from left to right in a two-level dynamic programming procedure. On a local level, a set of hypotheses is computed for each column, while on a global level the best sequence of these hypotheses is selected. The optimization on the local level is guided by a lookahead that gives an estimate about the not yet optimized part of the image. We evaluate the algorithm on the task of pose-invariant face recognition in an automatic setup and show that the suggested method is competitive and achieves very good recognition accuracies on the popular face recognition databases CMU-PIE and CMU-MultiPIE.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Zhao, W., Chellappa, R., Phillips, P., Rosenfeld, A.: Face recognition: A literature survey. ACM Computing Surveys (CSUR) 35(4), 399–458 (2003)
Bowyer, K.W., Chang, K., Flynn, P.: A survey of approaches and challenges in 3d and multi-modal 3d+ 2d face recognition. Computer Vision and Image Understanding 101(1), 1–15 (2006)
Zhang, X., Gao, Y.: Face recognition across pose: A review. Pattern Recognition 42(11), 2876–2896 (2009)
Keysers, D., Deselaers, T., Gollan, C., Ney, H.: Deformation models for image recognition. IEEE T-PAMI, 1422–1435 (2007)
Uchida, S., Sakoe, H.: A monotonic and continuous two-dimensional warping based on dynamic programming. In: ICPR, pp. 521–524 (1998)
Gass, T., Pishchulin, L., Dreuw, P., Ney, H.: Warp that smile on your face: optimal and smooth deformations for face recognition. In: FG, pp. 456–463 (2011)
Keysers, D., Unger, W.: Elastic image matching is NP-complete. Pattern Recognition Letters 24(1-3), 445–453 (2003)
Kuo, S., Agazzi, O.: Keyword spotting in poorly printed documents using pseudo 2-D hidden Markov models. IEEE T-PAMI 16(8), 842–848 (1994)
Mottl, V., Kopylov, A., Kostin, A., Yermakov, A., Kittler, J.: Elastic transformation of the image pixel grid for similarity based face identification. In: ICPR, pp. 549–552 (2002)
Uchida, S., Sakoe, H.: Piecewise linear two-dimensional warping. In: ICPR, pp. 534–537 (2000)
Kolmogorov, V.: Convergent tree-reweighted message passing for energy minimization. IEEE T-PAMI, 1568–1583 (2006)
Arashloo, S., Kittler, J., Christmas, W.: Pose-invariant face recognition by matching on multi-resolution mrfs linked by supercoupling transform. Computer Vision and Image Understanding 115(7), 1073–1083 (2011)
Gass, T., Dreuw, P., Ney, H.: Constrained energy minimization for matching-based image recognition. In: ICPR, pp. 3304–3307 (2010)
Sim, T., Baker, S., Bsat, M.: The cmu pose, illumination, and expression (pie) database. In: FG, pp. 46–51 (2002)
Gross, R., Matthews, I., Cohn, J., Kanade, T., Baker, S.: Multi-pie. Image and Vision Computing 28(5), 807–813 (2010)
Ortmanns, S., Ney, H.: Look-ahead techniques for fast beam search. Computer Speech & Language 14(1), 15–32 (2000)
Kalal, Z., Matas, J., Mikolajczyk, K.: Weighted sampling for large-scale boosting. In: BMVC (2008)
Li, A., Shan, S., Gao, W.: Coupled bias–variance tradeoff for cross-pose face recognition. IEEE Transactions on Image Processing 21(1), 305–315 (2012)
Tan, X., Triggs, B.: Enhanced local texture feature sets for face recognition under difficult lighting conditions. In: Zhou, S.K., Zhao, W., Tang, X., Gong, S. (eds.) AMFG 2007. LNCS, vol. 4778, pp. 168–182. Springer, Heidelberg (2007)
Ke, Y., Sukthankar, R.: Pca-sift: A more distinctive representation for local image descriptors. In: CVPR, pp. II-506–II-513 (2004)
Dreuw, P., Steingrube, P., Hanselmann, H., Ney, H.: Surf-face: Face recognition under viewpoint consistency constraints. In: BMVC (2009)
Asthana, A., Marks, T., Jones, M., Tieu, K., Rohith, M.: Fully automatic pose-invariant face recognition via 3d pose normalization. In: ICCV, pp. 937–944 (2011)
Ding, L., Ding, X., Fang, C.: Continuous pose normalization for pose-robust face recognition. IEEE Signal Process. Lett. 19(11), 721–724 (2012)
Prabhu, U., Heo, J., Savvides, M.: Unconstrained pose-invariant face recognition using 3d generic elastic models. IEEE T-PAMI 33(10), 1952–1961 (2011)
Sharma, A., Haj, M.A., Choi, J., Davis, L.S., Jacobs, D.W.: Robust pose invariant face recognition using coupled latent space discriminant analysis. Computer Vision and Image Understanding 116(11), 1095–1110 (2012)
Heo, J., Savvides, M.: Face recognition across pose using view based active appearance models (VBAAMs) on CMU multi-PIE dataset. In: Gasteratos, A., Vincze, M., Tsotsos, J.K. (eds.) ICVS 2008. LNCS, vol. 5008, pp. 527–535. Springer, Heidelberg (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hanselmann, H., Ney, H., Dreuw, P. (2013). Pose-Invariant Face Recognition with a Two-Level Dynamic Programming Algorithm. In: Sanches, J.M., Micó, L., Cardoso, J.S. (eds) Pattern Recognition and Image Analysis. IbPRIA 2013. Lecture Notes in Computer Science, vol 7887. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-38628-2_2
Download citation
DOI: https://doi.org/10.1007/978-3-642-38628-2_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-38627-5
Online ISBN: 978-3-642-38628-2
eBook Packages: Computer ScienceComputer Science (R0)