Abstract
This paper describes a novel setup to capture images of the spectral response of different materials to improve their classification. The proposed system involves a Liquid Crystal Tunable Filter (LCTF) that, placed in front of the camera, allows the capture of narrow spectral band images for each material from different illumination directions. We analyze the captured spectral images and propose a learning based method to select a subset of bands (or filters), the corresponding images of which can be used without compromising on material classification performance. Results on both binary and multi-class classification tasks are reported in the experimental section.
C. Liu—Currently Ph.D. candidate at Carnegie Mellon University, PA, USA.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Jehle, M., Sommer, C., Jähne, B.: Learning of optimal illumination for material classification. In: Goesele, M., Roth, S., Kuijper, A., Schiele, B., Schindler, K. (eds.) Pattern Recognition. LNCS, vol. 6376, pp. 563–572. Springer, Heidelberg (2010)
Gu, J., Liu, C.: Discriminative illumination: per-pixel classification of raw materials based on optimal projections of spectral BRDF. In: IEEE Conference on Computer Vision and Pattern Recognition (2012)
Picón, A., Ghita, O., Bereciartua, A., Echazarra, J., Whelan, P., Iriondo, P.: Real-time hyperspectral processing for automatic nonferrous material sorting. J. Electron. Imaging 21(1), 1–8 (2012)
Bajcsy, P., Groves, P.: Methodology for hyperspectral band selection. Photogram. Eng. Remote Sens. J. 70, 793–802 (2004)
Chang, C.I., Wang, S.: Constrained band selection for hyperspectral imagery. IEEE Trans. Geosci. Remote Sens. 44, 1575–1585 (2006)
Martínez-Usó, A., Pla, F., Sotoca, J., Garcia-Sevilla, P.: Clustering-based hyperspectral band selection using information measures. IEEE Trans. Geosci. Remote Sens. 45, 4158–4171 (2007)
Qian, Y., Yao, F., Jia, S.: Band selection for hyperspectral imagery using affinity propagation. IET Comput. Vision 3, 213–222 (2009)
Kumar, V., Hahn, J., Zoubir, A.: Band selection for hyperspectral images based on self-tuning spectral clustering. In: European Signal Processing Conference (2013)
Fu, Z., Robles-Kelly, A.: Discriminant absorption feature learning for material classification. IEEE Trans. Geosci. Remote Sens. 49, 1536–1556 (2010)
Tominaga, S., Kimachi, A.: Polarization imaging for material classification. Opt. Eng. 47 (2008)
Chen, H., Wolff, L.: Polarization phase-based method for material classification in computer vision. Int. J. Comput. Vision 28, 73–83 (1998)
Wolff, L.: Polarization-based material classification from specular reflection. IEEE Trans. Pattern Anal. Mach. Intell. 12, 1059–1071 (1990)
Salamati, N., Fredembach, C., Süsstrunk, S.: Material classification using color and NIR images. In: IS&T Color Imaging Conference (2009)
Ibrahim, A., Tominaga, S., Horiuchi, T.: Spectral imaging method for material classification and inspection of printed circuit boards. Opt. Eng. 49, 057201–057210 (2010)
Ali, M., Sato, I., Okabe, T., Sato, Y.: Toward efficient acquisition of BRDFs with fewer samples. In: IEEE Asian Conference on Computer Vision (2012)
Freund, Y., Schapire, R.: Experiments with a new boosting algorithm. In: International Conference on Machine Learning (1996)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Liu, C., Skaff, S., Martinello, M. (2015). Learning Discriminative Spectral Bands for Material Classification. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2015. Lecture Notes in Computer Science(), vol 9474. Springer, Cham. https://doi.org/10.1007/978-3-319-27857-5_60
Download citation
DOI: https://doi.org/10.1007/978-3-319-27857-5_60
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-27856-8
Online ISBN: 978-3-319-27857-5
eBook Packages: Computer ScienceComputer Science (R0)