Robust face recognition with partial occlusion, illumination variation and limited training data by optimal feature selection

Access Full Text

Robust face recognition with partial occlusion, illumination variation and limited training data by optimal feature selection

For access to this article, please select a purchase option:

Buy article PDF
£12.50
(plus tax if applicable)
Add to cart
Buy Knowledge Pack
10 articles for £75.00
(plus taxes if applicable)
Add to cart

IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.

Learn more about IET membership 

Recommend Title Publication to library

You must fill out fields marked with: *

Librarian details
Name:*
Email:*
Your details
Name:*
Email:*
Department:*
Why are you recommending this title?
Select reason:
 
 
 
 
 
IET Computer Vision — Recommend this title to your library

Thank you

Your recommendation has been sent to your librarian.

© The Institution of Engineering and Technology
Published

This study investigates face recognition with partial occlusion, illumination variation and their combination, assuming no prior information about the mismatch, and limited training data for each person. The authors extend their previous posterior union model (PUM) to give a new method capable of dealing with all these problems. PUM is an approach for selecting the optimal local image features for recognition to improve robustness to partial occlusion. The extension is in two stages. First, authors extend PUM from a probability-based formulation to a similarity-based formulation, so that it operates with as little as one single training sample to offer robustness to partial occlusion. Second, they extend this new formulation to make it robust to illumination variation, and to combined illumination variation and partial occlusion, by a novel combination of multicondition relighting and optimal feature selection. To evaluate the new methods, a number of databases with various simulated and realistic occlusion/illumination mismatches have been used. The results have demonstrated the improved robustness of the new methods.

Inspec keywords: probability; face recognition

Other keywords: posterior union model; partial occlusion; optimal feature selection; illumination variation; limited training data; optimal local image features; probability-based formulation; robust face recognition; similarity-based formulation

Subjects: Other topics in statistics; Image recognition; Other topics in statistics; Computer vision and image processing techniques

References

    1. 1)
      • Choi, S.I., Choi, C.H.: `An effective face recognition under illumination and pose variations', Int. Joint Conf. on Neural Networks (IJCNN'2007), 2007, p. 914–919.
    2. 2)
      • Little, G., Krishna, S., Black, J., Panchanathan, S.: `A methodology for evaluating robustness of face recognition algorithms with respect to variations in pose angle and illumination angle', Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'2005), 2005, p. 89–92.
    3. 3)
      • Gao, W., Zhao, D.: `Vitual face image generation for illumination and pose insensitive face recognition', Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'2003), 2003, p. 776–779.
    4. 4)
    5. 5)
      • Martinez, A.M., Benavente, R.: `The AR face database', CVC Technical Report #24, June 1998.
    6. 6)
      • Lin, J., Ming, J., Crookes, D.: `A probabilistic union approach to robust face recognition with partial distortion and occlusion', Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'2008), 2008, p. 993–996.
    7. 7)
      • J. Lin , J. Ming , D. Crookes . Robust face recognition using posterior union model based neural networks. IET Comput. Vis. , 130 - 142
    8. 8)
      • K. Ohba , K. Ikeuchi . Detectability, uniqueness, and reliability of eigen windows for stable verification of partially occluded objects. IEEE Trans. Pattern Anal. Mach. Intell. , 1043 - 1048
    9. 9)
      • Shan, S., Gao, W., Cao, B., Zhap, D.: `Illumination normalization for robust face recognition against varying lighting conditions', IEEE Workshop on Analysis and Modeling of Faces and Gestures (AMFG'2003), 2003, p. 157–164.
    10. 10)
      • J. Zhao , Y. Su , D. Wang , S. Luo . Illumination ratio image: synthesizing and recognition with varying illuminations. Pattern Recog. Lett. , 2703 - 2710
    11. 11)
      • Gudur, N., Asari, V.: `Gabor wavelet based modular PCA approach for expression and illumination invariant face recognition', 35thApplied Imagery and Pattern Recognition Workshop (AIPR'2006), 2006, p. 13–18.
    12. 12)
    13. 13)
    14. 14)
    15. 15)
      • Wang, H.T., Li, S.Z., Wang, Y.S., Zhang, W.W.: `Illumination modeling and normalisation for face recognition', IEEE Int. Workshop on Analysis and Modeling of Faces and Gestures (AMFG'03), 2003, p. 104–111.
    16. 16)
      • W.L. Chen , M.J. Er , S.Q. Wu . Illumination compensation and normalization for robust face recogntiion using discrete cosine transform in logarithm domain. IEEE Trans. Syst. Man Cybern. Part B: Cybern. , 458 - 466
    17. 17)
      • A.S. Georghiades , P.N. Belhumeur , D.W. Jacobs . From few to many: illumination cone models for face recognition under variable lighting and pose. IEEE Trans. Pattern Anal. Mach. Intell. , 630 - 660
    18. 18)
      • The FacePix Project, Arizona State University, http://www.facepix.org/, accessed October 2009.
    19. 19)
      • A. Shashua , T. Riklin-Raviv . The quotient image: class-based rerendering and recognition with varing illumination. IEEE Trans. Pattern Anal. Mach. Intell. , 129 - 139
    20. 20)
      • H.J. Shim , J.B. Luo , T.H. Chen . A subspace model-based approach to face relighting under unknown lighting and poses. IEEE Trans. Image Process. , 1331 - 1341
    21. 21)
      • The Yale Face Database B, Yale University, http://cvc.yale.edu/projects/yalefacesB/yalefacesB.html, accessed October 2009.
    22. 22)
    23. 23)
      • S.I. Choi , C. Kim , C.I. Choi . Shadow compensation in 2d images for face recognition. Pattern Recognit. , 2118 - 2125
    24. 24)
      • L. Zhang , D. Samaras . Face recognition from a single training image under arbitrary unknown lighting using spherical harmonics. IEEE Trans. Pattern Anal. Mach. Intell. , 351 - 363
    25. 25)
      • D. Liu , K. Lam , L. Shen . Illumination invariant face recognition. Pattern Recognit. , 1705 - 1716
    26. 26)
      • J. Wright , A.Y. Yang , A. Ganesh , S.S. Sastry , Y. Ma . Robust face recognition via sparse representation. IEEE Trans. Pattern Anal. Mach. Intell. , 210 - 227
    27. 27)
      • Qing, L.Y., Shan, S.G., Chen, X.L., Gao, W.: `Face recognition under varying lighting based on the probabilistic model of Gabor phase', Int. Conf. on Pattern Recognition (ICPR'2006), 2006, 3, p. 1139–1142.
    28. 28)
      • K. Jongsun , C. Jongmoo , Y. Juneho , M. Turk . Effective representation using ICA for face recognition robust to local distortion and partial occlusion. IEEE Trans. Pattern Anal. Mach. Intell. , 1977 - 1981
    29. 29)
      • B. Zhang , S. Shan , X. Chen , W. Gao . Histogram of Gabor phase patterns (HGPP): a novel object representation approach for face recognition. IEEE Trans. Image Process. , 57 - 68
    30. 30)
      • S.W. Lee , S.H. Moom , S.W. Lee . Face recognition under arbitary illumination using illuminated examplars. Pattern Recognit. , 1605 - 1620
    31. 31)
    32. 32)
      • Lin, J., Ming, J., Crookes, D.: `Robust face recognition with partially occluded images based on a single or a small number of training samples', Int. Conf. on Acoustics, Speech, and Signal Processing (ICASSP'2009), 2009, p. 881–884.
    33. 33)
      • Messer, K., Matas, J., Kittler, J., Luettin, J., Maitre, G.: `XM2VTSDB: the extended M2VTS database', Int. Conf. on Audio- and Video-Based Biometric Person Authentication, 1999, Washington, DC, USA, p. 72–77.
    34. 34)
      • Huang, C.Y., Camps, O.I., Kanungo, T.: `Object recognition using appearance-based parts and relations', IEEE Conf. on Computer Vision and Pattern Recognition (CVPR'97), 1997, p. 878–884.
    35. 35)
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2009.0121
Loading

Related content

content/journals/10.1049/iet-cvi.2009.0121
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading