The discrete cosine transform (DCT) plus local normalization: a novel two-stage method for de-illumination in face recognition

To deal with illumination variations in face recognition, a novel two-stage illumination normalization method is proposed in this paper. Firstly, a discrete cosine transform (DCT) is used on the original images in logarithm domain. DC coefficient is set based on the average pixel value of all the within-class training samples and some low frequency AC coefficients are set to zero to eliminate illumination variations in large areas. Secondly, local normalization method, which can minimize illumination variations in small areas, is used on the inverse DCT images. This makes the pixel values on the processed images be close to or equal to that of the normal illumination condition. Experimental results, both on Yale B database and Extended Yale B database, show that the proposed method can eliminate effect of illumination variations effectively and improve performance of face recognition methods significantly. The present method does not demand modeling step and can eliminate the effect of illumination variations before face recognition. In this way, it can be used as a preprocessing step for any existing face recognition method.

[1]  M. Turk,et al.  Eigenfaces for Recognition , 1991, Journal of Cognitive Neuroscience.

[2]  Zia-ur Rahman,et al.  Properties and performance of a center/surround retinex , 1997, IEEE Trans. Image Process..

[3]  Meng Joo Er,et al.  Illumination compensation and normalization for robust face recognition using discrete cosine transform in logarithm domain , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[4]  Rama Chellappa,et al.  Human and machine recognition of faces: a survey , 1995, Proc. IEEE.

[5]  Hany Farid,et al.  Blind inverse gamma correction , 2001, IEEE Trans. Image Process..

[6]  Rama Chellappa,et al.  SFS based view synthesis for robust face recognition , 2000, Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580).

[7]  Siwei Luo,et al.  Illumination ratio image: synthesizing and recognition with varying illuminations , 2003, Pattern Recognit. Lett..

[8]  David J. Kriegman,et al.  What Is the Set of Images of an Object Under All Possible Illumination Conditions? , 1998, International Journal of Computer Vision.

[9]  Ronen Basri,et al.  Lambertian Reflectance and Linear Subspaces , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  E. Land,et al.  Lightness and retinex theory. , 1971, Journal of the Optical Society of America.

[11]  David J. Kriegman,et al.  Acquiring linear subspaces for face recognition under variable lighting , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  John D. Austin,et al.  Adaptive histogram equalization and its variations , 1987 .

[13]  David J. Kriegman,et al.  Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection , 1996, ECCV.

[14]  David W. Jacobs,et al.  In search of illumination invariants , 2001, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[15]  Azriel Rosenfeld,et al.  Face recognition: A literature survey , 2003, CSUR.

[16]  Lei Zhang,et al.  Face recognition under variable lighting using harmonic image exemplars , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[17]  Shimon Ullman,et al.  Face Recognition: The Problem of Compensating for Changes in Illumination Direction , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Marian Stewart Bartlett,et al.  Face recognition by independent component analysis , 2002, IEEE Trans. Neural Networks.

[19]  P. Yip,et al.  Discrete Cosine Transform: Algorithms, Advantages, Applications , 1990 .

[20]  David J. Kriegman,et al.  From Few to Many: Illumination Cone Models for Face Recognition under Variable Lighting and Pose , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Joongkyu Kim,et al.  Retinex method based on adaptive smoothing for illumination invariant face recognition , 2008, Signal Process..

[22]  Wen Gao,et al.  Illumination normalization for robust face recognition against varying lighting conditions , 2003, 2003 IEEE International SOI Conference. Proceedings (Cat. No.03CH37443).

[23]  Peter W. Hallinan.  A low-dimensional representation of human faces for arbitrary lighting conditions , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[24]  Amnon Shashua,et al.  The Quotient Image: Class-Based Re-Rendering and Recognition with Varying Illuminations , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Martin Bichsel,et al.  Illumination invariant object recognition , 1995, Proceedings., International Conference on Image Processing.

[26]  Kin-Man Lam,et al.  An efficient illumination normalization method for face recognition , 2006, Pattern Recognit. Lett..

[27]  Reginald L. Lagendijk,et al.  An adaptive order-statistic noise filter for gamma-corrected image sequences , 1997, IEEE Trans. Image Process..