A Statistical Approach to Material Classification Using Image Patch Exemplars
Top Cited Papers
- 18 July 2008
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 31 (11), 2032-2047
- https://doi.org/10.1109/tpami.2008.182
Abstract
In this paper, we investigate material classification from single images obtained under unknown viewpoint and illumination. It is demonstrated that materials can be classified using the joint distribution of intensity values over extremely compact neighborhoods (starting from as small as 3times3 pixels square) and that this can outperform classification using filter banks with large support. It is also shown that the performance of filter banks is inferior to that of image patches with equivalent neighborhoods. We develop novel texton-based representations which are suited to modeling this joint neighborhood distribution for Markov random fields. The representations are learned from training images and then used to classify novel images (with unknown viewpoint and lighting) into texture classes. Three such representations are proposed and their performance is assessed and compared to that of filter banks. The power of the method is demonstrated by classifying 2,806 images of all 61 materials present in the Columbia-Utrecht database. The classification performance surpasses that of recent state-of-the-art filter bank-based classifiers such as Leung and Malik (IJCV 01), Cula and Dana (IJCV 04), and Varma and Zisserman (IJCV 05). We also benchmark performance by classifying all of the textures present in the UIUC, Microsoft Textile, and San Francisco outdoor data sets. We conclude with discussions on why features based on compact neighborhoods can correctly discriminate between textures with large global structure and why the performance of filter banks is not superior to that of the source image patches from which they were derived.Keywords
This publication has 44 references indexed in Scilit:
- Near-regular texture analysis and manipulationACM Transactions on Graphics, 2004
- 10.1162/153244303322753643Applied Physics Letters, 2000
- 10.1162/153244303322753616Applied Physics Letters, 2000
- Filtering for texture classification: a comparative studyIEEE Transactions on Pattern Analysis and Machine Intelligence, 1999
- Reflectance and texture of real-world surfacesACM Transactions on Graphics, 1999
- Wrappers for feature subset selectionArtificial Intelligence, 1997
- Learning texture discrimination masksIEEE Transactions on Pattern Analysis and Machine Intelligence, 1996
- Preattentive texture discrimination with early vision mechanismsJournal of the Optical Society of America A, 1990
- Early vision and texture perceptionNature, 1988
- Textons, the elements of texture perception, and their interactionsNature, 1981