Support Vector Machines for Object Recognition under Varying Illumination

†† In this paper, we propose an appearance-based method for object recognition under varying illumination. It has been shown that images of an object under varying illumination lie in a convex cone formed in the image space. Accordingly, cones of two objects are separated by a hyperplane passing through the origin of the image space, provided that there is no intersection between those two cones. In addition, variations due to changes in light intensities can be canceled by normalizing images. Based on these observations, our proposed method combines two-class discriminations using a hyperplane in the normalized image space. To demonstrate the effectiveness of the proposed method, we have conducted a number of experiments using the Yale Face Database B and shown that support vector machines are well suited for obtaining discriminant hyperplanes for object recognition under varying illumination.

[1]  Alexander J. Smola,et al.  Support Vector Machine Reference Manual , 1998 .

[2]  Takeshi Shakunaga,et al.  Decomposed eigenface for face recognition under various lighting conditions , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[3]  Hiroshi Murase,et al.  Visual learning and recognition of 3-d objects from appearance , 2005, International Journal of Computer Vision.

[4]  A. Shashua.  Geometry and Photometry in 3D Visual Recognition , 1992 .

[5]  David J. Kriegman,et al.  Illumination cones for recognition under variable lighting: faces , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

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

[7]  David G. Stork,et al.  Pattern classification, 2nd Edition , 2000 .

[8]  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..

[9]  Alex Pentland,et al.  Face recognition using eigenfaces , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[10]  David J. Kriegman,et al.  What is the set of images of an object under all possible lighting conditions? , 1996, Proceedings CVPR IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[11]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[12]  P. Hanrahan,et al.  On the relationship between radiance and irradiance: determining the illumination from images of a convex Lambertian object. , 2001, Journal of the Optical Society of America. A, Optics, image science, and vision.

[13]  Massimiliano Pontil,et al.  Support Vector Machines for 3D Object Recognition , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Roberto Brunelli,et al.  Face Recognition: Features Versus Templates , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Pat Hanrahan,et al.  A signal-processing framework for inverse rendering , 2001, SIGGRAPH.

[16]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[17]  Ronen Basri,et al.  Lambertian reflectance and linear subspaces , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[18]  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.

[19]  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.

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