Abstract
This paper introduces an efficient way of representing textures using connected regions which are formed by coherent multi-scale over-segmentations. We show that the recently introduced covariance-based similarity measure, initially applied on rectangular windows, can be used with our newly devised, irregular structure-coherent patches; increasing the discriminative power and consistency of the texture representation. Furthermore, by treating texture in multiple scales, we allow for an implicit encoding of the spatial and statistical texture properties which are persistent across scale. The meaningfulness and efficiency of the covariance based texture representation is verified utilizing a simple binary segmentation method based on min-cut. Our experiments show that the proposed method, despite the low dimensional representation in use, is able to effectively discriminate textures and that its performance compares favorably with the state of the art.
The research has been supported by the Austrian Science Foundation (FWF) under the grant S9101, and the European Union projects MOVEMENT (IST-2003-511670), Robots@home (IST-045350), and MUSCLE (FP6-507752).
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Malik, J., Belongie, S., Leung, T., Shi, J.: Contour and texture analysis for image segmentation. IJCV 43(1), 7–27 (2001)
Mičušík, B., Pajdla, T.: Multi-label image segmentation via max-sum solver. In: Proc. CVPR (2007)
Tuzel, O., Porikli, F., Meer, P.: Region covariance: A fast descriptor for detection and classification. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3952, pp. 589–600. Springer, Heidelberg (2006)
Rother, C., Kolmogorov, V., Blake, A.: ”grabcut”: interactive foreground extraction using iterated graph cuts. In: Proc. ACM SIGGRAPH, pp. 309–314. ACM Press, New York (2004)
Kolmogorov, V., Criminisi, A., Blake, A., Cross, G., Rother, C.: Probabilistic fusion of stereo with color and contrast for bi-layer segmentation. PAMI 28(9), 1480–1492 (2006)
Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images. In: Proc. ICCV, pp. 105–112 (2001)
Hadjidemetriou, E., Grossberg, M., Nayar, K.S.: Multiresolution histograms and their use for recognition. PAMI 26(7), 831–847 (2004)
Turek, W., Freedman, D.: Multiscale modeling and constraints for max-flow/min-cut problems in computer vision. In: Proc. CVPR Workshop, vol. 180 (2006)
Förstner, W., Moonen, B.: A metric for covariance matrices. Technical report, Dpt. of Geodesy and Geoinformatics, Stuttgart University (1999)
Ren, X., Malik, J.: Learning a classification model for segmentation (2003)
Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. IJCV 59(2), 167–181 (2004)
Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. PAMI 26(9), 1124–1137 (2004)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91–110 (2004)
Lindeberg, T.: Scale-Space Theory in Computer Vison. Kluwer Academic Publishers, Dordrecht (1994)
Deng, H., Zhang, W., Diettrich, T., Shapiro, L.: Principal curvature-based region detector for object recognition. In: Proc. CVPR (2007)
Pennec, X., Fillard, P., Ayache, N.: A riemannian framework for tensor computing. International Journal of Computer Vision 66(1), 41–66 (2006)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wildenauer, H., Mičušík, B., Vincze, M. (2007). Efficient Texture Representation Using Multi-scale Regions. In: Yagi, Y., Kang, S.B., Kweon, I.S., Zha, H. (eds) Computer Vision – ACCV 2007. ACCV 2007. Lecture Notes in Computer Science, vol 4843. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-76386-4_5
Download citation
DOI: https://doi.org/10.1007/978-3-540-76386-4_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-76385-7
Online ISBN: 978-3-540-76386-4
eBook Packages: Computer ScienceComputer Science (R0)