A kernelized sparsity-based approach for best spectral bands selection for face recognition

详细信息    查看全文

• 作者：Hamdi Jamel Bouchech ; Sebti Foufou ; Andreas Koschan…
• 关键词：MBLBP ; HGPP ; POEM ; WPCA ; LGBPHS ; IRIS ; M3 ; Subspectral images ; Bands selection
• 刊名：Multimedia Tools and Applications
• 出版年：2015
• 出版时间：October 2015
• 年：2015
• 卷：74
• 期：19
• 页码：8631-8654
• 全文大小：1,925 KB
• 参考文献：1. Ahonen T, Hadid A, Pietikainen M (2006) Face description with local binary patterns: application to face recognition. IEEE Trans Pattern Anal Mach Intell 28(12):2037鈥?041CrossRef
  2.Aizerman MA, Braverman EA, Rozonoer L (1964) Theoretical foundations of the potential function method in pattern recognition learning. in Automation and Remote Control, ser. Autom Remote Control 25:821鈥?37
  3. Andreas K, Abidi MA (2009) Digital color image processing, 2nd ed. Wiley-Interscience
  4. Becker S, Candes E, Grant M (2011) Templates for convex cone problems with applications to sparse signal recovery. Math Program Comput 3(3):165鈥?18
  5. Bouchech H, Foufou S, Koschan A, Abidi M (2013) Studies on the effectiveness of multispectral images for face recognition: comparative studies and new approaches, in Signal-Image Technology Internet-Based Systems (SITIS), 2013 International Conference on. 58鈥?4
  6. Byvatov E, Fechner U, Sadowski J, Schneider G (2003) Comparison of support vector machine and \artificial neural network systems for drug/nondrug classification. J Chem Inf Comput Sci 43:1882鈥?889. doi:10.鈥?021/鈥媍i0341161
  7. Chang H, Koschan A, Abidi B, Abidi M (2010) Fusing continuous spectral images for face recognition under indoor and outdoor illuminants. Mach Vis Appl 21:201鈥?15CrossRef
  8. Chang H, Koschan A, Abidi B (2008) Fusing continuous spectral images for face recognition under indoor and outdoor illuminants. Mach Vis Appl 19(4):1432鈥?769
  9. Chang H, Yao Y, Koschan A, Abidi B, Abidi M (2009) Improving face recognition via narrowband spectral range selection using jeffrey divergence. Trans Info For Sec 4(1):122. doi:10.鈥?109/鈥婽IFS.鈥?008.鈥?012211
  10. Chen Y, Nasrabadi N, Tran T (2013) Hyperspectral image classification via kernel sparse representation. IEEE Trans Geosci Remote Sens 51(1):217鈥?31CrossRef
  11. Dian-ting L, Xiao-dan Z, Cheng-wen W (2008) Wavelet-based multispectral face recognition. Optoelectron Lett 4(5):451鈥?62
  12. Duda RO, Hart PE, Stork DG (2001) Pattern classification, 2nd ed. Wiley
  13. Gao Y, Leung M, Hui S, Tananda M (2003) Facial expression recognition from line-based caricatures. IEEE Trans Syst Man Cybern Syst Hum 33(3):407鈥?12CrossRef
  14. Lei Z, Pietikainen M, Li SZ (2013) Learning discriminant face descriptor. IEEE Trans Pattern Anal Mach Intell 99:1, no. PrePrints
  15. Li SZ, Chu R, Liao S, Zhang L (2007) Illumination invariant face recognition using near-infrared images. IEEE Trans Pattern Anal Mach Intell 29(4):627鈥?39CrossRef
  16. Li S, Lei Z, Ao M (2009) The hfb face database for heterogeneous face biometrics research, in IEEE Computer Society Conference on Computer Vision and Pattern RecognitionWorkshops, CVPRWorkshops 2009: pp. 1鈥?
  17. Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60
  18. Moon S, Kong SG, Yoo JH, and Chung K (2006) Face recognition with multiscale data fusion of visible and thermal images, in IEEE International Conference on Computational Intelligence for Homeland Security and Personal Safety, Alexandria: 24鈥?7
  19. Moosmann F, Nowak E, Jurie F (2008) Randomized clustering forests for image classification. IEEE Trans Pattern Anal Mach Intell 30(9):1632鈥?646CrossRef
  20. Panda R, Naik MK (2012) Fusion of infrared and visual images using bacterial foraging strategy, WSEAS Trans Signal Proc 8(4)
  21. Perlibakas V (2004) Distance measures for pca-based face recognition. Pattern Recogn Lett 25(6):711鈥?24CrossRef
  22. Ruiz-del Solar J, Verschae R, Correa M (2009) Recognition of faces in unconstrained environments: a comparative study. EURASIP J Adv Signal Process 1(1鈥?):19
  23. Vu N-S, Caplier A (2012) Enhanced patterns of oriented edge magnitudes for face recognition and image matching. Trans Image Process 21(3):1352鈥?365MathSciNet CrossRef
  24. Zahran EG, Abbas AM, Dessouky MI, Ashour MA, Sharshar KA (2009) High performance face recognition using pca and zm on fused lwir and visible images on the wavelet domain, in Computer Engineering & Systems. ICCES 2009. International Conference on: 449鈥?54
  25. Zhang B, Shan S, Chen X, Gao W (2007) Histogram of Gabor phase patterns (hgpp): a novel objectrepresentation approach for face recognition. Trans Image Process 16(1):57鈥?8MathSciNet CrossRef
  26. Zhang D, Zhou Z (2005) (2d)2pca: 2-directional 2-dimensional pca for efficient face representation and recognition. Neurocomput 69(1鈥?):224鈥?31CrossRef
  27. Zou J, Ji Q, Nagy G (2007) A comparative study of local matching approach for face recognition. Trans Image Process 16(10):2617鈥?628MathSciNet CrossRef
  
• 作者单位：Hamdi Jamel Bouchech (1) (2)
  Sebti Foufou (1) (2)
  Andreas Koschan (3)
  Mongi Abidi (3)
  
  1. LE2i Laboratory, University of Burgundy, Dijon, France
  2. Computer Science and Engineering, CENG, Qatar University, P.O. Box 2713, Doha, Qatar
  3. Imaging, Robotics, and Intelligent Systems Laboratory, Department of Electrical Engineering and Computer Science, University of Tennessee, Knoxville, USA
  
• 刊物类别：Computer Science
• 刊物主题：Multimedia Information Systems
  Computer Communication Networks
  Data Structures, Cryptology and Information Theory
  Special Purpose and Application-Based Systems
  
• 出版者：Springer Netherlands
• ISSN：1573-7721

文摘

We study face recognition in unconstrained illumination conditions. A twofold contribution is proposed: First, the robustness of four state-of-the-art algorithms, namely Multi-block Local Binary Pattern (MBLBP), Histogram of Gabor Phase Patterns (HGPP), Local Gabor Binary Pattern Histogram Sequence (LGBPHS) and Patterns of Oriented Edge Magnitudes (POEM-WPCA) against high illumination variation is studied. Second, we propose to enhance the performance of the four mentioned algorithms, which has been drastically decreased upon the day lighted face images provided by IRIS-M3 face database. For this purpose, we use visible narrow band subspectral images selected from the mentioned database. We formulate best spectral bands selection as a pursuit optimization problem wherein the vector of weights determining the importance of each visible spectral band is supposed to be sparse, and hence can be determined by minimizing its L1-norm. Several fusing approaches are then applied on selected best spectral bands using multi-scale and multi-orientation Gabor wavelets. The results highlight further the still challenging problem of face recognition in conditions with high illumination variation, as well as the effectiveness of our subspectral images based approach with its two components; bands selection and bands fusion, to increase the accuracy of the studied algorithms by at least 14 % upon the proposed database. Keyword MBLBP HGPP POEM-WPCA LGBPHS IRIS-M3 Subspectral images Bands selection