Specular Free Spectral Imaging Using Orthogonal Subspace Projection

Specularity is an important issue in computer vision. Many algorithms have been proposed to remove highlights for color images. However, to our knowledge, no work has been done so far which specifically handles highlights in spectral imaging. In this paper, we introduce a specular invariant representation for hyperspectral images based on the dichromatic model and orthogonal subspace projection. It is a simple one step algorithm which only involves pixel-level operations, thus it does not require any segmentation. Nor does it require any pre/postprocessing or explicit spectral normalization. Importantly, unlike the previous methods for color images, it can be theoretically extended to handle highlights caused by multicolored illuminations. Experimental results demonstrate the effectiveness of our algorithm

[1]  Shree K. Nayar,et al.  Separation of Reflection Components Using Color and Polarization , 1997, International Journal of Computer Vision.

[2]  Zhouyu Fu,et al.  An Energy Minimisation Approach to Attributed Graph Regularisation , 2007, EMMCVPR.

[3]  Chein-I Chang,et al.  Hyperspectral image classification and dimensionality reduction: an orthogonal subspace projection approach , 1994, IEEE Trans. Geosci. Remote. Sens..

[4]  Zhouyu Fu,et al.  Efficient Graph Cuts for Multiclass Interactive Image Segmentation , 2007, ACCV.

[5]  Stephen Lin,et al.  Highlight removal by illumination-constrained inpainting , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[6]  Elli Angelopoulou,et al.  Objective Colour from Multispectral Imaging , 2000, ECCV.

[7]  Katsushi Ikeuchi,et al.  Separating Reflection Components of Textured Surfaces Using a Single Image , 2005, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Antonio Robles-Kelly,et al.  Shape-From-Shading Using the Heat Equation , 2007, IEEE Transactions on Image Processing.

[9]  Antonio Robles-Kelly,et al.  Stereo techniques for 3D mapping of object surface temperatures , 2007 .

[10]  Zhouyu Fu,et al.  A fast hierarchical approach to image segmentation , 2008, 2008 19th International Conference on Pattern Recognition.

[11]  Cong Phuoc Huynh,et al.  Optimal Solution of the Dichromatic Model for Multispectral Photometric Invariance , 2008, SSPR/SPR.

[12]  Steven A. Shafer,et al.  Using color to separate reflection components , 1985 .

[13]  Stephen Lin,et al.  Separation of diffuse and specular reflection in color images , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[14]  Zhouyu Fu,et al.  On Mixtures of Linear SVMs for Nonlinear Classification , 2008, SSPR/SPR.

[15]  Huang Yumin,et al.  A PHYSICAL APPROACH TO COLOR IMAGE UNDERSTANDING , 1991 .

[16]  Zhouyu Fu,et al.  Fast multiple instance learning via L1,2 logistic regression , 2008, 2008 19th International Conference on Pattern Recognition.