© The Institution of Engineering and Technology
Gradient phase, which is treated as an illumination insensitive measure, is an important feature for visual detection and recognition applications, especially under illumination variations. However, fewer statistical characteristics of the gradient phase have been reported till now. First, the statistical characteristics of the gradient phase against gradient signal-to-noise ratios (gradient SNRs) were investigated. The analysed results show that the confidence (or standard deviation) of gradient phases against gradient SNRs should never be linearly related, as is usually supposed. With the help of the statistical analyses of the gradient phase, the gradient-based visual detection and recognition were improved by incorporating confidence information into the cost function. Moreover, inspired by the analysed characteristics of the gradient phase, an enhanced gradientface method is proposed to improve the performance of the gradient phase-based face recognition. Intensive simulations and comparisons are performed to show its superior performance without the side effect of discrimination loss that existed in some illumination normalisation approaches.
References
-
-
1)
-
19. Phong, B.T.: ‘Illumination for computer generated pictures’, Commun. ACM, 1975, 18, (6), pp. 311–317 (doi: 10.1145/360825.360839).
-
2)
-
8. Georghiades, A.S., Belhumeur, P.N.: ‘Illumination cone models for recognition under variable lighting: Faces’. Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, 1998.
-
3)
-
22. Theodoridis, S., Koutroumbas, K.: ‘Pattern recognition’ (Academic Press, 2008, 4th edn.), .
-
4)
-
10. Shim, H., Luo, J., Chen, T.: ‘A subspace model-based approach to face relighting under unknown lighting and poses’, IEEE Trans. Image Process., 2008, 17, pp. 1331–1341 (doi: 10.1109/TIP.2008.925390).
-
5)
-
17. Gross, R., Brajovie, V.: ‘An image preprocessing algorithm for illumination invariant face recognition’. Proc. Fourth Int. Conf. Audio and Video Based Biometric Person Authentication, 2003, pp. 10–18.
-
6)
-
27. Li, S.Z., Jain, A.J. (eds.): ‘Handbook of face recognition’ (Springer, 2011, 2nd edn.).
-
7)
-
13. Lee, D., Seung, H.: ‘Algorithms for non-negative matrix factorization’. Proc. Advances Neural Information Process Systems, 2001, vol. 13, pp. 556–562.
-
8)
-
6. Vu, N.-S., Caplier, A.: ‘Illumination-robust face recognition using retina modeling’. Proc. 16th IEEE Int. Conf. Image Processing, November 2009, pp. 3289–3292.
-
9)
-
10)
-
25. Phillips, P., Flynn, P., Scruggs, T., et al: ‘Overview of the face recognition grand challenge’. Proc. IEEE Conf. Computer Vision and Pattern Recognition, San Diego, California, USA, 20–25 June 2005.
-
11)
-
D.J. Jobson ,
Z. Rahman ,
G.A. Woodell
.
A multiscale retinex for bridging the gap between color images and human observation of scenes.
IEEE Trans. Image Process
,
7 ,
965 -
976
-
12)
-
13)
-
3. Wang, H., Li, S.Z., Wang, Y.: ‘Face recognition under varying lighting conditions using self-quotient image’. Proc. IEEE Int. Conf. Automatic Face and Gesture Recognition, 2004, pp. 819–824.
-
14)
-
T. Chen ,
W.T. Yin ,
X.S. Zhou ,
D. Comaniciu ,
T.S. Huang
.
Total variation models for variable lighting face recognition.
IEEE Trans. Pattern Anal. Mach. Intell.
,
1519 -
1524
-
15)
-
23. Nelson, L.S.: ‘The folded normal distribution’, J. Qual. Technol., 1980, 12, (4), pp. 236–238.
-
16)
-
20. Yang, C.-H.T., Lai, S.-H., Chang, L.-W.: ‘Robust face image matching under illumination variations’, EURASIP J. Appl. Signal Process., 2004, 16, pp. 2533–2543 (doi: 10.1155/S1110865704410014).
-
17)
-
4. Yin, W., Goldfarb, D., Osher, S.: ‘Image cartoon-texture decomposition and feature selection using the total variation regularized L1 functional’. Proc. Third Int. Workshop Variational, Geometric, and Level Set Methods in Computer Vision, 2005, pp. 73–84.
-
18)
-
R. Basri ,
D.W. Jacobs
.
Lambertian reflectance and linear subspaces.
IEEE Trans Pattern Anal. Mach. Intell.
,
2 ,
218 -
233
-
19)
-
5. Zhang, T., Tang, Y.Y., Fang, B., Shang, Z., Liu, X.: ‘Face recognition under illumination using gradientfaces’, IEEE Trans. Image Process., 2009, 18, (11), pp. 2599–2606 (doi: 10.1109/TIP.2009.2028255).
-
20)
-
D.J. Jobson ,
Z. ur Rahman ,
G.A. Woodell
.
Properties and performance of a center/surround retinex.
IEEE Trans. Image Process.
,
3 ,
451 -
462
-
21)
-
7. Belhumeur, P.N., Kriegman, D.J.: ‘What is the set of images of an object under all possible lighting conditions?’. Proc. IEEE Int. Conf. Computer Vision and Pattern Recognition, 1996.
-
22)
-
20. Stark, H., Woods, J. W.: ‘Probability, statistics, and random processes for engineers’ (Prentice-Hall, 2011, 4th edn.), .
-
23)
-
14. Yang, C.-H.T., Lai, S.-H., Chang, L.-W.: ‘A reliable face recognition algorithm based on matching normalized gradients’. Proc. Conf. Information Technology: Research and Education, 2003.
-
24)
-
A.S. Georghiades ,
P.N. Belhumeur ,
D.J. Kriegman
.
From few to many: illumination cone models for face recognition under variable lighting and pose.
IEEE Trans. Pattern Anal. Mach. Intell.
,
6 ,
643 -
660
-
25)
-
22. Chen, C.-P., Chen, C.-S.: ‘Intrinsic illumination subspace for lighting insensitive face recognition’, IEEE Trans. Syst. Man Cybern., B, Cybern., 2012, 42, (2), pp. 422–433 (doi: 10.1109/TSMCB.2011.2167322).
-
26)
-
21. Leon-Garcia, A.: ‘Probability and random processes for electrical engineering’ (Addison-Wesley, 1993, 2nd edn.).
-
27)
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2013.0168
Related content
content/journals/10.1049/iet-cvi.2013.0168
pub_keyword,iet_inspecKeyword,pub_concept
6
6