Nothing Special   »   [go: up one dir, main page]

skip to main content
article

An efficient illumination invariant face recognition framework via illumination enhancement and DD-DTCWT filtering

Published: 01 January 2013 Publication History

Abstract

In this paper, it is shown that multiscale analysis of facial structure and features of face images leads to superior recognition rates for images under varying illumination. The proposed method, which is computationally cost effective, significantly suppresses illumination effects. The problem is defined as how better to extract the reflectance portion from a given image. This can be used directly as an input to a dimensionality reduction unit followed by a classifier for recognition purposes. We first assume that an image I(x,y) is a black box consisting of a combination of illumination and reflectance. A new approximation is proposed to enhance the illumination removal phase. As illumination resides in the low-frequency part of image, it is reasonable to consider the use of a high-performance multiresolution transformation to first accurately separate the frequency components of an image. The double-density dual-tree complex wavelet transform (DD-DTCWT), possesses three core advantages, i.e., the transformation is (i) shift-invariant, (ii) directionally selective with no checkerboard effect, (iii) enriched by extra wavelets interpreted as double-density. The output of the first phase is sent to a DD-DTCWT unit to be decomposed into frequency subbands. High-frequency subbands are thresholded and an inverse DD-DTCWT is then applied to subbands to construct a low-frequency raw image, which is followed by a fine-tuning process. Finally, after extracting a mask, feature vector is formed and the principal component analysis (PCA) is used for dimensionality reduction which is then proceeded by the extreme learning machine (ELM) as a classifier to evaluate the performance of the proposed algorithm for face recognition under varying illumination. Unlike similar works, the proposed method is free of any prior information about the face shape, it is systematic and easy to implement, and it can be applied separately on each image. Furthermore, the proposed method which is significantly faster than similar techniques presents a robust behavior against the reduction in the number of images required for the training cycle. Several experiments are performed employing the available well-known databases such as the Yale B, Extended-Yale B, CMU-PIE, FERET, AT&T, and the Labeled Faces in the Wild (LFW). Illustrative examples are given and the results compare favorably to the current results in the literature.

References

[1]
Adini, Y., Moses, Y. and Ullman, S., Face recognition: the problem of compensating for changes in illumination direction. IEEE Transactions on Pattern Analysis and Machine Intelligence. v19 i7. 721-732.
[2]
Baker, S., Sim, T. and Bsat, M., The CMU pose, illumination, and expression database. IEEE Transactions on Pattern Analysis and Machine Intelligence. v25 i12. 1615-1618.
[3]
Baradarani, A., Jonathan Wu, Q.M., Ahmadi, M. and Mendapara, P., Tunable halfband-pair wavelet filter banks and application to multifocus image fusion. Pattern Recognition. v45 i2. 657-671.
[4]
Basri, R. and Jacobs, D.W., Lambertian reflectance and linear subspaces. IEEE Transactions on Pattern Analysis and Machine Intelligence. v25 i2. 218-233.
[5]
Bresch, M., Optimizing filter banks for supervised texture recognition. Pattern Recognition. v35. 783-790.
[6]
Belhumeur, P.N., Hespanha, J.P. and Kriegman, D.J., Eigenfaces versus fisherfaces: recognition using class specific linear projection. IEEE Transactions on Pattern Analysis and Machine Intelligence. v19 i7. 711-720.
[7]
P.N. Belhumeur, D.J. Kriegman, What is the set of images of an object under all possible lighting conditions? in:Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (CVPR96), San Francisco, CA, 1996, pp. 270-277.
[8]
Chen, T., Zhou, X.S., Comaniciu, D. and Huang, T.S., Total variation models for variable lighting face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. v28 i9. 1519-1524.
[9]
Chen, W., Er, M.J. and Wu, S., Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithmic domain. IEEE Transaction on Systems, Man and Cybernetics B. v36 i2. 458-466.
[10]
Cheng, K.-O., Law, N.-F. and Siu, W.-C., Multiscale directional filter bank with applications to structured and random texture retrieval. Pattern Recognition. v40. 1182-1194.
[11]
Coifman, R.R. and Donoho, D.L., Translation-Invariant de-Noising, in Wavelets and Statistics. 1995. Springer-Verlag, New York.
[12]
El Aroussi, M., El Hassouni, M., Ghouzali, S., Rziza, M. and Aboutajdine, D., Local appearance based face recognition method using block based steerable pyramid transform. Signal Processing. v91 i1. 38-50.
[13]
Eleyan, A., Özkaramanlı, H. and Demirel, H., Complex wavelet transform-based face recognition. EURASIP Journal on Advanced Signal Processing. v2008 i1. 1-13.
[14]
Fisher, R.A., The statistical utilization of multiple measurements. Annals of Eugenics. v8. 376-386.
[15]
Fukunaga, K., Introduction to Statistical Pattern Recognition. 1990. 2nd ed. Academic Press.
[16]
Georghiades, A.S., Belhumeur, P.N. and Kriegman, D.J., From few to many: illumination cone models for face recognition under variable lighting and pose. IEEE Transactions on Pattern Analysis and Machine Intelligence. v23 i6. 643-660.
[17]
Papakostas, G.A., Boutalis, Y.S., Karras, D.A. and Mertzios, B.G., A new class of Zernike moments for computer vision applications. Information Sciences. v177 i13. 2802-2819.
[18]
Horn, B.K.P., Robot Vision. 1986. MIT Press.
[19]
Huang, G.-B., Zhu, Q.-Y. and Siew, C.-K., Extreme learning machine: theory and applications. Neurocomputing. v70 i1-3. 489-501.
[20]
Optimization method based extreme learning machine for classification. Neurocomputing. v74 i1-3. 155-163.
[21]
G.-B. Huang, H. Zhou, X. Ding, R. Zhang, Extreme learning machine for regression and multiclass classification, IEEE Transactions on Systems, Man, and Cybernetics - Part B, 45 (2) (2012) 513-529
[22]
Huang, J.-C., Su, T.-S., Wang, L.-J. and Hsieh, W.-S., Double-change-detection method for wavelet-based moving-object segmentation. Electronics Letters. v40 i13. 798-799.
[23]
G. Huang, M. Ramesh, T. Berg, E. Learned-Miller, Labeled Faces in the Wild: A database for studying face recognition in unconstrained environments, University of Massachusetts, Amherst, Technical Report, (2007) 07-49. Available {online} at: {http://vis-www.cs.umass.edu/lfw/}.
[24]
Principal Component Analysis. 1989. Springer-Verlag, New York.
[25]
Kingsbury, N.G., Complex wavelets for shift invariant analysis and filtering of signals. Journal of Applied and Computational Harmonic Analysis. v10 i3. 234-253.
[26]
Land, E.H., The Retinex. American Scientist. v52 i2. 247-264.
[27]
Land, E.H. and McCann, J.J., Lightness and Retinex Theory. Journal of Optical Society of America. v61 i1. 1-11.
[28]
Lee, K.-C., Ho, J. and Kriegman, D., Acquiring linear subspaces for face recognition under variable lighting. IEEE Transactions on Pattern Analysis and Machine Intelligence. v27 i5. 684-698.
[29]
K.-C. Lee, J. Ho, D. Kriegman, Nine points of light: acquiring subspaces for face recognition under variable lighting, in: IEEE International Conference on Computer Vision and Pattern Recognition (CVPR01), Kauai, HI, vol. 1, 2001, pp. 519-526.
[30]
Mandal, T., Jonathan Wu, Q.M. and Yuan, Y., Curvelet based face recognition via dimension reduction. Signal Processing. v89 i12. 2345-2353.
[31]
Nabatchian, A., Abdel-Raheem, E. and Ahmadi, M., Illumination invariant feature extraction and mutual information based local matching for face recognition under illumination variation and occlusion. Pattern Recognition. v44 i10-11. 2576-2587.
[32]
Ojala, T., Pietikäinen, M. and Harwood, D., A comparative study of texture measures with classification based on featured distributions. Pattern Recognition. v29 i1. 51-59.
[33]
Phillips, P.J., Moon, H., Rauss, P.J. and Rizvi, S., The FERET evaluation methodology for face recognition algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence. v22 i10. 1090-1104.
[34]
Selesnick, I.W., The double-density dual-tree DWT. IEEE Transactions on Signal Processing. v52 i5. 1304-1314.
[35]
The dual-tree complex wavelet transform-a coherent framework for multiscale signal and image processing. IEEE Signal Processing Magazine. v22 i6. 123-151.
[36]
I.W. Selesnick, Double-Density Wavelet Software, Available {online} at: {http://taco.poly.edu/selesi/DoubleSoftware.index.html}.
[37]
S. Shan, W. Gao, B. Cao, D. Zhao, Illumination normalization for robust face recognition against varying lighting conditions, in: IEEE International Workshop on Analysis and Modeling Faces Gestures (AMFG03), 2003, pp. 157-164.
[38]
Shashua, A. and Raviv, T.R., The quotient image: class-based re-rendering and recognition with varying illuminations. IEEE Transactions on Pattern Analysis and Machine Intelligence. v23 i2. 129-139.
[39]
Solar, J.R.D. and Quinteros, J., Illumination compensation and normalization in eigenspace-based face recognition: a comparative study of different pre-processing approaches. Pattern Recognition Letters. v29 i14. 1966-1979.
[40]
X. Tan, B. Triggs. Enhanced local texture feature sets for face recognition under difficult lighting conditions, in: IEEE International Workshop on Analysis and Modeling Faces Gestures (AMFG07), 2007, pp. 168-182.
[41]
H. Wang, S.Z. Li, Y. Wang. Face recognition under varying lighting conditions using self quotient image, in: IEEE International Conference on Automatic Face Gesture Recognition (AFGR04), 2004, pp. 819-824.
[42]
Wright, J., Yang, A.Y., Ganesh, A., Sastry, S.S. and Ma, Y., Robust face recognition via sparse representation. IEEE Transactions on Pattern Analysis and Machine Intelligence. v31 i2. 210-227.
[43]
Y. Taigman, L. Wolf, T. Hassner. Multiple one-shots for utilizing class label information, in: The British Machine Vision Conference (BMVC), 2009, pp. 1-12.
[44]
Xie, X. and Lam, K.-M., An efficient illumination normalization method for face recognition. Pattern Recognition Letters. v27 i6. 609-617.
[45]
S. Georghiades, P.N. Belhumeur, D.J. Kriegman, From few to many: illumination cone models for face recognition under variable lighting and pose, IEEE Transactions on Pattern Analysis and Machine Intelligence 23 (6) (2001) 643-660, The Yale B Face Database, Available (online) at: {http://cvc.yale.edu/projects/yalefacesB/yalefacesB.htm}.
[46]
K.C. Lee, J. Ho, D. Kriegman, Acquiring linear subspaces for face recognition under variable lighting, IEEE Transactions on Pattern Analysis and Machine Intelligence 27 (5) (2005) 684-698, The Extended-Yale B Face Database, Available (online) at: {http://vision.ucsd.edu\leekc/ExtYaleDatabase}
[47]
Yang, J., Zhang, D., Frangi, A.F. and -Y Yang, J., Two-dimensional PCA: a new approach to appearance-based face representation and recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence. v26 i1. 131-137.
[48]
Zhang, T., Fang, B., Yuan, Y., Tang, Y.Y., Shang, Z., Li, D. and Lang, F., Multiscale facial structure representation for face recognition under varying illumination. Pattern Recognition. v42 i2. 251-258.
[49]
Zhang, Y., Tian, J., He, X. and Yang, X., MQI based face recognition under uneven illumination. Springer Advances in Biometrics. v4642. 290-298.
[50]
Zhao, J., Su, Y., Wang, D. and Luo, S., Illumination ratio image: synthesizing and recognition with varying illuminations. Pattern Recognition Letters. v24 i15. 2703-2710.
[51]
Cao, X., Shen, W., Yu, L.G., Wang, Y.L., Yang, J.Y. and Zhang, Z.W., Illumination invariant extraction for face recognition using neighboring wavelet coefficients. Pattern Recognition. v45 i4. 1299-1305.

Cited By

View all
  • (2023)Multilayer extreme learning machine: a systematic reviewMultimedia Tools and Applications10.1007/s11042-023-14634-482:26(40269-40307)Online publication date: 22-Mar-2023
  • (2021)Statistical texture image retrieval in DD-DTCWT domain using magnitudes and relative phasesMultimedia Tools and Applications10.1007/s11042-021-11124-380:19(29893-29913)Online publication date: 1-Aug-2021
  • (2019)Illumination Classification based on No-Reference Image Quality Assessment (NR-IQA)Proceedings of the 2019 Asia Pacific Information Technology Conference10.1145/3314527.3314529(70-74)Online publication date: 25-Jan-2019
  • Show More Cited By

Recommendations

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Pattern Recognition
Pattern Recognition  Volume 46, Issue 1
January, 2013
462 pages

Publisher

Elsevier Science Inc.

United States

Publication History

Published: 01 January 2013

Author Tags

  1. Double-density dual-tree complex wavelets
  2. Extreme learning machine
  3. Face recognition
  4. Illumination invariance
  5. Subband filtering

Qualifiers

  • Article

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)0
  • Downloads (Last 6 weeks)0
Reflects downloads up to 21 Dec 2024

Other Metrics

Citations

Cited By

View all
  • (2023)Multilayer extreme learning machine: a systematic reviewMultimedia Tools and Applications10.1007/s11042-023-14634-482:26(40269-40307)Online publication date: 22-Mar-2023
  • (2021)Statistical texture image retrieval in DD-DTCWT domain using magnitudes and relative phasesMultimedia Tools and Applications10.1007/s11042-021-11124-380:19(29893-29913)Online publication date: 1-Aug-2021
  • (2019)Illumination Classification based on No-Reference Image Quality Assessment (NR-IQA)Proceedings of the 2019 Asia Pacific Information Technology Conference10.1145/3314527.3314529(70-74)Online publication date: 25-Jan-2019
  • (2019)General logarithm difference model for severe illumination variation face recognitionMultimedia Tools and Applications10.1007/s11042-019-07830-878:19(27425-27447)Online publication date: 1-Oct-2019
  • (2017)Feature selection for regression problems based on the Morisita estimator of intrinsic dimensionPattern Recognition10.1016/j.patcog.2017.05.00870:C(126-138)Online publication date: 1-Oct-2017
  • (2017)Bi-histogram equalization using modified histogram binsApplied Soft Computing10.1016/j.asoc.2017.01.05355:C(31-43)Online publication date: 1-Jun-2017
  • (2017)Illumination-insensitive features for face recognitionThe Visual Computer: International Journal of Computer Graphics10.1007/s00371-017-1357-x33:11(1483-1493)Online publication date: 1-Nov-2017
  • (2016)Face recognition under varying illuminations using logarithmic fractal dimension-based complete eight local directional patternsNeurocomputing10.1016/j.neucom.2016.01.094199:C(16-30)Online publication date: 26-Jul-2016
  • (2016)Multiscale morphology based illumination normalization with enhanced local textures for face recognitionExpert Systems with Applications: An International Journal10.1016/j.eswa.2016.06.03962:C(347-357)Online publication date: 15-Nov-2016
  • (2016)A novel illumination-robust local descriptor based on sparse linear regressionDigital Signal Processing10.1016/j.dsp.2015.09.01048:C(269-275)Online publication date: 1-Jan-2016
  • Show More Cited By

View Options

View options

Media

Figures

Other

Tables

Share

Share

Share this Publication link

Share on social media