Skip to main content
Erschienen in: International Journal of Computer Vision 2-3/2015

01.09.2015

Sparse Illumination Learning and Transfer for Single-Sample Face Recognition with Image Corruption and Misalignment

verfasst von: Liansheng Zhuang, Tsung-Han Chan, Allen Y. Yang, S. Shankar Sastry, Yi Ma

Erschienen in: International Journal of Computer Vision | Ausgabe 2-3/2015

Einloggen

Aktivieren Sie unsere intelligente Suche um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Single-sample face recognition is one of the most challenging problems in face recognition. We propose a novel algorithm to address this problem based on a sparse representation based classification (SRC) framework. The new algorithm is robust to image misalignment and pixel corruption, and is able to reduce required gallery images to one sample per class. To compensate for the missing illumination information traditionally provided by multiple gallery images, a sparse illumination learning and transfer (SILT) technique is introduced. The illumination in SILT is learned by fitting illumination examples of auxiliary face images from one or more additional subjects with a sparsely-used illumination dictionary. By enforcing a sparse representation of the query image in the illumination dictionary, the SILT can effectively recover and transfer the illumination and pose information from the alignment stage to the recognition stage. Our extensive experiments have demonstrated that the new algorithms significantly outperform the state of the art in the single-sample regime and with less restrictions. In particular, the single-sample face alignment accuracy is comparable to that of the well-known Deformable SRC algorithm using multiple gallery images per class. Furthermore, the face recognition accuracy exceeds those of the SRC and Extended SRC algorithms using hand labeled alignment initialization.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Anhänge
Nur mit Berechtigung zugänglich
Fußnoten
1
In this paper, we use Viola-Jones face detector to initialize the face image location. As a result, we do not consider scenarios where the face may contain a large 3D transformation or large expression change. These more severe conditions can be addressed in the face detection stage using more sophisticated face models as we previously mentioned.
 
2
In our previous work (Zhuang et al. 2013), this simple extension was in fact used as the solution to transfer both the alignment and illumination information from the alignment stage to the recognition stage. However, the assumption was valid because the illumination dictionary used in Zhuang et al. (2013) was constructed by concatenating the auxiliary images themselves, namely, \(D\) in this paper. Therefore, the problem of warping a learned dictionary was mitigated.
 
3
The training are illuminations {0,1,7,13,14,16,18} in Multi-PIE Session 1.
 
4
The implementation of SVDL was provided by their authors at: http://​www4.​comp.​polyu.​edu.​hk/​~cslzhang/​code/​SVDL.​zip.
 
Literatur
Zurück zum Zitat Aharon, M., Elad, M., & Bruckstein, A. (2006). The K-SVD: An algorithm for designing of overcomplete dictionaries for sparse representation. IEEE Transactions on Signal Processing, 54(11), 4311–4322.CrossRef Aharon, M., Elad, M., & Bruckstein, A. (2006). The K-SVD: An algorithm for designing of overcomplete dictionaries for sparse representation. IEEE Transactions on Signal Processing, 54(11), 4311–4322.CrossRef
Zurück zum Zitat Basri, R., & Jacobs, D. (2003). Lambertian reflectance and linear subspaces. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(2), 218–233.CrossRef Basri, R., & Jacobs, D. (2003). Lambertian reflectance and linear subspaces. IEEE Transactions on Pattern Analysis and Machine Intelligence, 25(2), 218–233.CrossRef
Zurück zum Zitat Belhumeur, P., Hespanda, J., & Kriegman, D. (1997). Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(7), 711–720.CrossRef Belhumeur, P., Hespanda, J., & Kriegman, D. (1997). Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(7), 711–720.CrossRef
Zurück zum Zitat Boyd, S., Parikh, N., Chu, E., Peleato, B., & Eckstein, J. (2011). Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations and Trends in Machine Learning, 3(1), 1–122.CrossRef Boyd, S., Parikh, N., Chu, E., Peleato, B., & Eckstein, J. (2011). Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations and Trends in Machine Learning, 3(1), 1–122.CrossRef
Zurück zum Zitat Chen, X., Chen, M., Jin, X., & Zhao, Q. (2011). Face illumination transfer through edge-preserving filters. In Proceedings of the IEEE international conference on computer vision and pattern recognition. Chen, X., Chen, M., Jin, X., & Zhao, Q. (2011). Face illumination transfer through edge-preserving filters. In Proceedings of the IEEE international conference on computer vision and pattern recognition.
Zurück zum Zitat Cootes, T., Edwards, G., & Taylor, C. (1998). Active appearance models. In Proceedings of the European conference on computer vision. Cootes, T., Edwards, G., & Taylor, C. (1998). Active appearance models. In Proceedings of the European conference on computer vision.
Zurück zum Zitat Cootes, T., Taylor, C., & Graham, J. (1995). Active shape models—Their training and application. Computer Vision and Image Understanding, 61, 38–59.CrossRef Cootes, T., Taylor, C., & Graham, J. (1995). Active shape models—Their training and application. Computer Vision and Image Understanding, 61, 38–59.CrossRef
Zurück zum Zitat Deng, W., Hu, J., & Guo, J. (2012). Extended SRC: Undersampled face recognition via intraclass variant dictionary. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34, 1864–1870.CrossRef Deng, W., Hu, J., & Guo, J. (2012). Extended SRC: Undersampled face recognition via intraclass variant dictionary. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34, 1864–1870.CrossRef
Zurück zum Zitat Do, C., & Ng, A. (2005). Transfer learning for text classification. In Proceedings of NIPS. Do, C., & Ng, A. (2005). Transfer learning for text classification. In Proceedings of NIPS.
Zurück zum Zitat Elhamifar, E., & Vidal, R. (2012). Block-sparse recovery via convex optimization. IEEE Transactions on Signal Processing, 60, 4094–4107.CrossRefMathSciNet Elhamifar, E., & Vidal, R. (2012). Block-sparse recovery via convex optimization. IEEE Transactions on Signal Processing, 60, 4094–4107.CrossRefMathSciNet
Zurück zum Zitat Gabay, D., & Mercier, B. (1976). A dual algorithm for the solution of nonlinear variational problems via finite-element approximations. Computers and Mathematics with Applications, 2, 17–40.CrossRefMATH Gabay, D., & Mercier, B. (1976). A dual algorithm for the solution of nonlinear variational problems via finite-element approximations. Computers and Mathematics with Applications, 2, 17–40.CrossRefMATH
Zurück zum Zitat Ganesh, A., Wagner, A., Wright, J., Yang, A., Zhou, Z., & Ma, Y. (2011). Face recognition by sparse representation. In Compressed Sensing: Theory and Applications. Cambridge University Press. Ganesh, A., Wagner, A., Wright, J., Yang, A., Zhou, Z., & Ma, Y. (2011). Face recognition by sparse representation. In Compressed Sensing: Theory and Applications. Cambridge University Press.
Zurück zum Zitat Gross, R., Mathews, I., Cohn, J., Kanade, T., & Baker, S. (2008). Multi-PIE. In Proceedings of the eighth IEEE international conference on automatic face and gesture recognition. Gross, R., Mathews, I., Cohn, J., Kanade, T., & Baker, S. (2008). Multi-PIE. In Proceedings of the eighth IEEE international conference on automatic face and gesture recognition.
Zurück zum Zitat Gu, L., & Kanade, T. (2008). A generative shape regularization model for robust face alignment. In Proceedings of the European conference on computer vision. Gu, L., & Kanade, T. (2008). A generative shape regularization model for robust face alignment. In Proceedings of the European conference on computer vision.
Zurück zum Zitat Hager, G., & Belhumeur, P. (1998). Efficient region tracking with parametric models of geometry and illumination. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(10), 1025–1039.CrossRef Hager, G., & Belhumeur, P. (1998). Efficient region tracking with parametric models of geometry and illumination. IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(10), 1025–1039.CrossRef
Zurück zum Zitat Ho, J., Yang, M., Lim, J., Lee, K., & Kriegman, D. (2003). Clustering appearances of objects under varying illumination conditions. In Proceedings of the IEEE international conference on computer vision and pattern recognition. Ho, J., Yang, M., Lim, J., Lee, K., & Kriegman, D. (2003). Clustering appearances of objects under varying illumination conditions. In Proceedings of the IEEE international conference on computer vision and pattern recognition.
Zurück zum Zitat Horn, R. A., & Johnson, C. R. (1985). Matrix analysis. New York: Cambridge University Press.CrossRefMATH Horn, R. A., & Johnson, C. R. (1985). Matrix analysis. New York: Cambridge University Press.CrossRefMATH
Zurück zum Zitat Huang, J., Huang, X., & Metaxas, D. (2008). Simultaneous image transformation and sparse representation recovery. In Proceedings of the IEEE international conference on computer vision and pattern recognition. Huang, J., Huang, X., & Metaxas, D. (2008). Simultaneous image transformation and sparse representation recovery. In Proceedings of the IEEE international conference on computer vision and pattern recognition.
Zurück zum Zitat Lampert, C., Nickisch, H., & Harmeling, S. (2009). Learning to detect unseen object classes by between-class attribute transfer. In Proceedings of the IEEE international conference on computer vision and pattern recognition. Lampert, C., Nickisch, H., & Harmeling, S. (2009). Learning to detect unseen object classes by between-class attribute transfer. In Proceedings of the IEEE international conference on computer vision and pattern recognition.
Zurück zum Zitat Lee, K., Ho, J., & Kriegman, D. (2005). Acquiring linear subspaces for face recognition under variable lighting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(5), 684–698.CrossRef Lee, K., Ho, J., & Kriegman, D. (2005). Acquiring linear subspaces for face recognition under variable lighting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27(5), 684–698.CrossRef
Zurück zum Zitat Liang, L., Xiao, R., Wen, F., & Sun, J. (2008). Face alignment via component-based discriminative search. In Proceedings of the European conference on computer vision. Liang, L., Xiao, R., Wen, F., & Sun, J. (2008). Face alignment via component-based discriminative search. In Proceedings of the European conference on computer vision.
Zurück zum Zitat Lucas, B., & Kanade, T. (1981). An iterative image registration technique with an application to stereo vision. In Proceedings of international joint conference on artificial intelligence. Lucas, B., & Kanade, T. (1981). An iterative image registration technique with an application to stereo vision. In Proceedings of international joint conference on artificial intelligence.
Zurück zum Zitat Peers, P., Tamura, N., Matusik, W., Debevec, P. (2007). Post-production facial performance relighting using reflectance transfer. In Proceedings of ACM SIGGRAPH. Peers, P., Tamura, N., Matusik, W., Debevec, P. (2007). Post-production facial performance relighting using reflectance transfer. In Proceedings of ACM SIGGRAPH.
Zurück zum Zitat Quattoni, A., Collins, M., & Darrell, T. (2008). Transfer learning for image classification with sparse prototype representations. In Proceedings of the IEEE international conference on computer vision and pattern recognition. Quattoni, A., Collins, M., & Darrell, T. (2008). Transfer learning for image classification with sparse prototype representations. In Proceedings of the IEEE international conference on computer vision and pattern recognition.
Zurück zum Zitat Saragih, J., Lucey, S., & Cohn, J. (2009). Face alignment through subspace constrained mean-shifts. In Proceedings of the IEEE international conference on computer vision. Saragih, J., Lucey, S., & Cohn, J. (2009). Face alignment through subspace constrained mean-shifts. In Proceedings of the IEEE international conference on computer vision.
Zurück zum Zitat Shashua, A., & Riklin-Raviv, T. (2001). The quotient image: Class-based re-rendering and recognition with varying illuminations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(2), 129–139.CrossRef Shashua, A., & Riklin-Raviv, T. (2001). The quotient image: Class-based re-rendering and recognition with varying illuminations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(2), 129–139.CrossRef
Zurück zum Zitat Spielman, D. A., Wang, H., & Wright, J. (2012). Exact recovery of sparsely-used dictionaries. Journal of Machine Learning Research, 23(18), 1–37. Spielman, D. A., Wang, H., & Wright, J. (2012). Exact recovery of sparsely-used dictionaries. Journal of Machine Learning Research, 23(18), 1–37.
Zurück zum Zitat Tseng, P. (1991). Applications of a splitting algorithm to decomposition in convex programming and variational inequalities. SIAM Journal on Control and Optimization, 29, 119–138.CrossRefMathSciNetMATH Tseng, P. (1991). Applications of a splitting algorithm to decomposition in convex programming and variational inequalities. SIAM Journal on Control and Optimization, 29, 119–138.CrossRefMathSciNetMATH
Zurück zum Zitat Viola, P., & Jones, J. (2004). Robust real-time face detection. International Journal on Computer Vision, 57, 137–154.CrossRef Viola, P., & Jones, J. (2004). Robust real-time face detection. International Journal on Computer Vision, 57, 137–154.CrossRef
Zurück zum Zitat Wagner, A., Wright, J., Ganesh, A., Zhou, Z., Mobahi, H., & Ma, Y. (2012). Toward a practical face recognition: Robust pose and illumination via sparse representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(2), 372–386.CrossRef Wagner, A., Wright, J., Ganesh, A., Zhou, Z., Mobahi, H., & Ma, Y. (2012). Toward a practical face recognition: Robust pose and illumination via sparse representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(2), 372–386.CrossRef
Zurück zum Zitat Wright, J., & Ma, Y. (2010). Dense error correction via \(\ell ^1\)-minimization. IEEE Transactions on Information Theory, 56(7), 3540– 3560. Wright, J., & Ma, Y. (2010). Dense error correction via \(\ell ^1\)-minimization. IEEE Transactions on Information Theory, 56(7), 3540– 3560.
Zurück zum Zitat Wright, J., Yang, A., Ganesh, A., Sastry, S., & Ma, Y. (2009). Robust face recognition via sparse representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(2), 210–227.CrossRef Wright, J., Yang, A., Ganesh, A., Sastry, S., & Ma, Y. (2009). Robust face recognition via sparse representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(2), 210–227.CrossRef
Zurück zum Zitat Yan, S., Liu, C., Li, S., Zhang, H., Shum, H., & Cheng, Q. (2003). Face alignment using texture-constrained active shape models. Image and Vision Computing, 21, 69–75.CrossRef Yan, S., Liu, C., Li, S., Zhang, H., Shum, H., & Cheng, Q. (2003). Face alignment using texture-constrained active shape models. Image and Vision Computing, 21, 69–75.CrossRef
Zurück zum Zitat Yan, S., Wang, H., Liu, J., Tang, X., & Huang, T. (2010). Misalignment-robust face recognition. IEEE Transactions on Image Processing, 19, 1087–1096.CrossRefMathSciNet Yan, S., Wang, H., Liu, J., Tang, X., & Huang, T. (2010). Misalignment-robust face recognition. IEEE Transactions on Image Processing, 19, 1087–1096.CrossRefMathSciNet
Zurück zum Zitat Yang, A., Zhou, Z., Ganesh, A., Sastry, S., & Ma, Y. (2013). Fast \(\ell _1\)-minimization algorithms for robust face recognition. IEEE Transactions on Image Processing, 22(8), 3234–3246. Yang, A., Zhou, Z., Ganesh, A., Sastry, S., & Ma, Y. (2013). Fast \(\ell _1\)-minimization algorithms for robust face recognition. IEEE Transactions on Image Processing, 22(8), 3234–3246.
Zurück zum Zitat Yang, M., Gool, L.V., & Zhang, L. (2013). Sparse variation dictionary learning for face recognition with a single training sample per person. In Proceedings of the IEEE international conference on computer vision. Yang, M., Gool, L.V., & Zhang, L. (2013). Sparse variation dictionary learning for face recognition with a single training sample per person. In Proceedings of the IEEE international conference on computer vision.
Zurück zum Zitat Yang, M., Zhang, L., & Zhang, D. (2012). Efficient misalignment-robust representation for real-time face recognition. In Proceedings of the European conference on computer vision. Yang, M., Zhang, L., & Zhang, D. (2012). Efficient misalignment-robust representation for real-time face recognition. In Proceedings of the European conference on computer vision.
Zurück zum Zitat Zhang, L., Feng, M. Y. X., Ma, Y., & Feng, X. (2012). Collaborative representation based classification for face recognition. Technical report, arXiv:1204.2358. Zhang, L., Feng, M. Y. X., Ma, Y., & Feng, X. (2012). Collaborative representation based classification for face recognition. Technical report, arXiv:​1204.​2358.
Zurück zum Zitat Zhao, W., Chellappa, R., Phillips, J., & Rosenfeld, A. (2003). Face recognition: A literature survey. ACM Computing Surveys, 35(4), 399–458. Zhao, W., Chellappa, R., Phillips, J., & Rosenfeld, A. (2003). Face recognition: A literature survey. ACM Computing Surveys, 35(4), 399–458.
Zurück zum Zitat Zhuang, L., Yang, A. Y., Zhang, Z., Sastry, S., & Ma, Y. (2013). Single-sample face recognition with image corruption and misalignment via sparse illumination transfer. In Proceedings of the IEEE international conference on computer vision and pattern recognition, Portland, Oregon. Zhuang, L., Yang, A. Y., Zhang, Z., Sastry, S., & Ma, Y. (2013). Single-sample face recognition with image corruption and misalignment via sparse illumination transfer. In Proceedings of the IEEE international conference on computer vision and pattern recognition, Portland, Oregon.
Metadaten
Titel
Sparse Illumination Learning and Transfer for Single-Sample Face Recognition with Image Corruption and Misalignment
verfasst von
Liansheng Zhuang
Tsung-Han Chan
Allen Y. Yang
S. Shankar Sastry
Yi Ma
Publikationsdatum
01.09.2015
Verlag
Springer US
Erschienen in
International Journal of Computer Vision / Ausgabe 2-3/2015
Print ISSN: 0920-5691
Elektronische ISSN: 1573-1405
DOI
https://doi.org/10.1007/s11263-014-0749-x

Weitere Artikel der Ausgabe 2-3/2015

International Journal of Computer Vision 2-3/2015 Zur Ausgabe