Material Classification Using Random Forest


Article Preview

Random forest has demonstrated excellent performance to deal with many problems of computer vision, such as image classification and keypoint recognition. This paper proposes an approach to classify materials, which combines random forest with MR8 filter bank. Firstly, we employ MR8 filter bank to filter the texture image. These filter responses are taken as texture feature. Secondly, Random forest grows on sub-window patches which are randomly extracted from these filter responses, then we use this trained forest to classify a given image (under unknown viewpoint and illumination) into texture classes. We carry out experiments on Columbia-Utrecht database. The experimental results show that our method successfully solves plain texture classification problem with high computational efficiency.



Advanced Materials Research (Volumes 301-303)

Edited by:

Riza Esa and Yanwen Wu






Z. M. Zhao et al., "Material Classification Using Random Forest", Advanced Materials Research, Vols. 301-303, pp. 73-79, 2011

Online since:

July 2011




[1] M. Varma, A. Zisserman, A statistical approach to texture classification from single images, International Journal of Computer Vision, Vol. 62(1-2), pp.61-81, 25 April (2005).

DOI: 10.1023/

[2] O. G. Cula, K. J. Dana, 3D texture recognition using bidirectional feature histogram, International Journal of Compter Vision, Vol. 59(1), pp.33-60, (2004).

DOI: 10.1023/b:visi.0000020670.05764.55

[3] S. Konishi, A. L. Yuille, Statistical cues for domain specific image segmentation with performance analysis, IEEE Conference on Computer Vision and Pattern Recognition, Hiltor Head, South Carolina, vol. 1, p.1125, June, (2000).

DOI: 10.1109/cvpr.2000.855809

[4] T. Leung, Malik. J, Representing and recognizing the visual appearance of materials using three-dimensional textons, International Journal of Computer Vision, vol. 43(1), pp.29-44, (2001).

[5] L. Breiman. Random forests, Machine Learning Journal, 45(1): 5-32, (2001).

[6] P. Geurts, D. Ernst and L. Wehenkel, Extremely randomized trees, Machine Learning Journal, 36(1), 3-42, (2006).

[7] V. Lepetit, P. Fua, Keypoint recognition using randomized trees, IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. 28(9), pp.1465-1479, (2006).

DOI: 10.1109/tpami.2006.188

[8] R. Maree, P. Geurts, J. Piater, and L. Wehenkel, Random subwindows for robust image classification, IEEE International Conference on Computer Vision and Pattern Recogntion, vol. 1, pp.34-40, (2005).

DOI: 10.1109/cvpr.2005.287

[9] F. Moosmann, B. Triggs, and F. Jurie, Fast discriminative visual codebooks using randomized clustering forests, Neural Information Processing Systems, pp.985-992, (2006).

[10] J. Shotton, M. Johnson, and R. Cipolla, Semantic texton forests for image categorization and segmentation, IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, Alaska, USA. pp.1-8, June (2008).

DOI: 10.1109/cvpr.2008.4587503

[11] C. Schmid, Constructing models for content-based image retriveval, IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp.39-45, (2001).

[12] K. J. Dana, B. van Ginneken, S. K. Nayar, and J. J. Koenderink, Reflectance and texture of teal world surfaces, ACM Transation on Graphics, vol. 18(1), pp.1-34, Jan, (1999).

DOI: 10.1145/300776.300778

In order to see related information, you need to Login.