Materials Classification Using Sparse Gray-Scale Bidirectional Reflectance Measurements

Material recognition applications use typically color texture-based features; however, the underlying measurements are in several application fields unavailable or too expensive e.g., due to a limited resolution in remote sensing. Therefore, bidirectional reflectance measurements are used, i.e., dependent on both illumination and viewing directions. But even measurement of such BRDF data is very time- and resources-demanding. In this paper we use dependency-aware feature selection method to identify very sparse set of the most discriminative bidirectional reflectance samples that can reliably distinguish between three types of materials from BRDF database --- fabric, wood, and leather. We conclude that ten gray-scale samples primarily at high illumination and viewing elevations are sufficient to identify type of material with accuracy over 96%. We analyze estimated placement of the bidirectional samples for discrimination between different types of materials. The stability of such directional samples is very high as was verified by an additional leave-one-out classification experiment. We consider this work a step towards automatic method of material classification based on several reflectance measurements only.

[1]  Jirí Filip,et al.  Template‐Based Sampling of Anisotropic BRDFs , 2014, Comput. Graph. Forum.

[2]  Michael Weinmann,et al.  Material Classification Based on Training Data Synthesized Using a BTF Database , 2014, ECCV.

[3]  Pavel Pudil,et al.  Fast dependency-aware feature selection in very-high-dimensional pattern recognition , 2011, 2011 IEEE International Conference on Systems, Man, and Cybernetics.

[4]  Chao Liu,et al.  Discriminative illumination: Per-pixel classification of raw materials based on optimal projections of spectral BRDF , 2012, CVPR.

[5]  John Shawe-Taylor,et al.  Learning Non-Linear Feature Maps , 2013, ArXiv.

[6]  T. Painter,et al.  Reflectance quantities in optical remote sensing - definitions and case studies , 2006 .

[7]  Yann Kerr,et al.  Leaf area index estimates using remotely sensed data and BRDF models in a semiarid region. , 2000 .

[8]  N. C. Strugnell,et al.  First operational BRDF, albedo nadir reflectance products from MODIS , 2002 .

[9]  F. E. Nicodemus,et al.  Geometrical considerations and nomenclature for reflectance , 1977 .

[10]  S. Sandmeier,et al.  Structure Analysis and Classification of Boreal Forests Using Airborne Hyperspectral Brdf Data from Asas Imagery and Processing Techniques Have Also Been Used Potential for Combining Both High Spectral Resolution And , 2022 .

[11]  G. Meister,et al.  Large scale multispectral BRDF of an urban area , 1999, IEEE 1999 International Geoscience and Remote Sensing Symposium. IGARSS'99 (Cat. No.99CH36293).

[12]  Bernd Jähne,et al.  Learning of Optimal Illumination for Material Classification , 2010, DAGM-Symposium.

[13]  Christian Wöhler,et al.  Single view single light multispectral object segmentation , 2013, WSCG.

[14]  Oliver Wang,et al.  Material classification using BRDF slices , 2009, CVPR.