Abstract
In this work, we propose a novel extension of pseudo 2D image warping (P2DW) which allows for joint alignment and recognition of non-rectified face images. P2DW allows for optimal displacement inference in a simplified setting, but cannot cope with stronger deformations since it is restricted to column-to-column mapping. We propose to implement additional flexibility in P2DW by allowing deviations from column centers while preserving vertical structural dependencies between neighboring pixel coordinates. In order to speed up the recognition we employ hard spacial constraints on candidate alignment positions. Experiments on two well-known face datasets show that our algorithm significantly improves the recognition quality under difficult variability such as 3D rotation (poses), expressions and illuminations, and can reliably classify even automatically detected faces. We also show an improvement over state-of-the-art results while keeping computational complexity low.
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.
Similar content being viewed by others
References
Arashloo, S., Kittler, J.: Hierarchical image matching for pose-invariant face recognition. In: BMVC (2009)
Dreuw, P., Steingrube, P., Hanselmann, H., Ney, H.: Surf-face: Face recognition under viewpoint consistency constraints. In: BMVC (2009)
Ekenel, H.K., Stiefelhagen, R.: Analysis of local appearance-based face recognition: Effects of feature selection and feature normalization. In: CVPRW, Washington, DC, USA, p. 34 (2006)
Eickeler, S., Mller, S., Rigoll, G.: High performance face recognition using pseudo 2-d hidden markov models. In: ECCV (1999)
Gass, T., Dreuw, P., Ney, H.: Constrained energy minimisation for matching-based image recognition. In: ICPR, Istanbul, Turkey (2010) (in press)
Gross, R.: http://ralphgross.com/FaceLabels
Keysers, D., Unger, W.: Elastic image matching is np-complete. Pattern Recognition Letters 24, 445–453 (2003)
Ke, Y., Sukthankar, R.: Pca-sift: A more distinctive representation for local image descriptors. In: CVPR, vol. (2), pp. 506–513 (2004)
Kolmogorov, V.: Convergent tree-reweighted message passing for energy minimization. IEEE TPAMI 28, 1568–1583 (2006)
Kuo, S.S., Agazzi, O.E.: Keyword spotting in poorly printed documents using pseudo 2-d hidden markov models. IEEE TPAMI 16(8), 842–848 (1994)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91–110 (2004)
Martinez, A., Benavente, R.: The AR face database. Technical report, CVC Technical report (1998)
Mottl, V., Kopylov, A., Kostin, A., Yermakov, A., Kittler, J.: Elastic transformation of the image pixel grid for similarity based face identification. In: ICPR (2002)
Samaria, F.: Face Recognition Using Hidden Markov Models. PhD thesis, Cambridge University (1994)
Sarfraz, M.S., Hellwich, O.: Probabilistic learning for fully automatic face recognition across pose. Image and Vision Computing 28(5), 744–753 (2010)
Smith, S.J., Bourgoin, M.O., Sims, K., Voorhees, H.L.: Handwritten character classification using nearest neighbor in large databases. IEEE TPAMI 16(9), 915–919 (1994)
Sim, T., Baker, S., Bsat, M.: The CMU pose, illumination, and expression (PIE) database. In: AFGR (2002)
Tan, K., Chen, S.: Adaptively weighted sub-pattern pca for face recognition. Neurocomputing 64, 505–511 (2005)
Uchida, S., Sakoe, H.: A monotonic and continuous two-dimensional warping based on dynamic programming. In: ICPR, pp. 521–524 (1998)
Viola, P., Jones, M.: Robust real-time face detection. International Journal of Computer Vision 57(2), 137–154 (2004)
Wiskott, L., Fellous, J.M., Krg̈er, N., von der Malsburg, C.: Face recognition by elastic bunch graph matching. IEEE TPAMI 19, 775–779 (1997)
Wright, J., Hua, G.: Implicit elastic matching with random projections for pose-variant face recognition. In: CVPR, pp. 1502–1509 (2009)
Zhang, X., Gao, Y., Leung, M.K.H.: Recognizing rotated faces from frontal and side views: An approach toward effective use of mugshot databases. IEEE TIFS 3(4), 684–697 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pishchulin, L., Gass, T., Dreuw, P., Ney, H. (2011). The Fast and the Flexible: Extended Pseudo Two-Dimensional Warping for Face Recognition. In: Vitrià , J., Sanches, J.M., Hernández, M. (eds) Pattern Recognition and Image Analysis. IbPRIA 2011. Lecture Notes in Computer Science, vol 6669. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21257-4_7
Download citation
DOI: https://doi.org/10.1007/978-3-642-21257-4_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21256-7
Online ISBN: 978-3-642-21257-4
eBook Packages: Computer ScienceComputer Science (R0)