Texture classification with minimal training images

The objective of this work is classifying texture from a single image under unknown lighting conditions. The current and successful approach to this task is to treat it as a statistical learning problem and learn a classifier from a set of training images, but this requires a sufficient number and variety of training images. We show that the number of training images required can be drastically reduced (to as few as three) by synthesizing additional training data using photometric stereo. We demonstrate the method on the PhoTex and ALOT texture databases. Despite the limitations of photometric stereo, the resulting classification performance surpasses the state of the art results.

[1]  Shree K. Nayar,et al.  Reflectance and texture of real-world surfaces , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  Christopher G. Harris,et al.  A Combined Corner and Edge Detector , 1988, Alvey Vision Conference.

[3]  Jitendra Malik,et al.  Representing and Recognizing the Visual Appearance of Materials using Three-dimensional Textons , 2001, International Journal of Computer Vision.

[4]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[5]  M. Chantler,et al.  Illumination-invariant texture classification using simple training images , 2005 .

[6]  Mario Fritz,et al.  On the Significance of Real-World Conditions for Material Classification , 2004, ECCV.

[7]  Andrew Zisserman,et al.  A Statistical Approach to Texture Classification from Single Images , 2004, International Journal of Computer Vision.

[8]  Jean Ponce,et al.  Computer Vision: A Modern Approach , 2002 .

[9]  Dariu Gavrila,et al.  Virtual sample generation for template-based shape matching , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[10]  Robert J. Woodham,et al.  Photometric method for determining surface orientation from multiple images , 1980 .

[11]  C. V. Jawahar,et al.  Computing Eigen Space from Limited Number of Views for Recognition , 2006, ICVGIP.

[12]  Barbara Caputo,et al.  Class-Specific Material Categorisation , 2005, ICCV.

[13]  Kristin J. Dana,et al.  Compact representation of bidirectional texture functions , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[14]  Robert E. Broadhurst.  Statistical Estimation of Histogram Variation for Texture Classification , 2005 .

[15]  Arnold W. M. Smeulders,et al.  The Amsterdam Library of Object Images , 2004, International Journal of Computer Vision.

[16]  A. M. Burton,et al.  100% Accuracy in Automatic Face Recognition , 2008, Science.

[17]  Daniel Snow,et al.  Determining Generative Models of Objects Under Varying Illumination: Shape and Albedo from Multiple Images Using SVD and Integrability , 1999, International Journal of Computer Vision.

[18]  Maria Petrou,et al.  Classifying Surface Texture while Simultaneously Estimating Illumination Direction , 2005, International Journal of Computer Vision.