Abstract
A novel approach to superpixel generation is presented that aims to reconcile image information with superpixel coverage. It is described as content-driven as the number of superpixels in any given area is dictated by the underlying image properties. By using a combination of well-established computer vision techniques, superpixels are grown and subsequently divided on detecting simple image variation. It is designed to have no direct control over the number of superpixels as this can lead to errors. The algorithm is subject to performance metrics on the Berkeley Segmentation Dataset including: explained variation; mode label analysis, as well as a measure of oversegmentation. The results show that this new algorithm can reduce the superpixel oversegmentation and retain comparable performance in all other metrics. The algorithm is shown to be stable with respect to initialisation, with little variation across performance metrics on a set of random initialisations.
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
Preview
Unable to display preview. Download preview PDF.
References
Ren, X., Malik, J.: Learning a classification model for segmentation. In: IEEE Proc. Computer Vision, pp. 10–17 (2003)
Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. PAMI 22, 888–905 (2000)
Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. IJCV 59, 167–181 (2004)
Levinshtein, A., Stere, A., Kutulakos, K.N., Fleet, D.J., Dickinson, S.J., Siddiqi, K.: TurboPixels: Fast Superpixels Using Geometric Flows. IEEE Trans. PAMI 31, 2290–2297 (2009)
Caselles, V., Kimmel, R., Sapiro, G.: Geodesic active contours. IJCV 22, 61–79 (1997)
Moore, A.P., Prince, S.J.D., Warrell, J.: “Lattice Cut”-Constructing superpixels using layer constraints. In: IEEE CVPR, pp. 2117–2124 (2010)
Moore, A.P., Prince, S.J.D., Warrell, J., Mohammed, U., Jones, G.: Superpixel lattices. In: IEEE CVPR, pp. 998–1005 (2008)
Moore, A.P., Prince, S.J.D., Warrell, J., Mohammed, U., Jones, G.: Scene shape priors for superpixel segmentation. In: ICCV, pp. 771–778 (2009)
Tuytelaars, T., Mikolajczyk, K.: Local Invariant Feature Detectors: A Survey. Foundations and Trends in Computer Graphics and Vision 3, 177 (2007)
Borgefors, G.: Distance transformations in digital images. Computer Vision, Graphics, and Image Processing 34, 344–371 (1986)
Chan, T., Sandberg, B., Vese, L.: Active Contours without Edges for Vector-Valued Images. Visual Communication and Image Representation 11, 130 (2000)
Chan, T.F., Vese, L.A.: Active Contours Without Edges. IEEE Trans. Image Processing 10 (2001)
Mumford, D., Shah, J.: Optimal approximations by piecewise smooth functions and associated variational problems. Comm. Pure Appl. Math 42, 577–685 (1989)
Shapiro, L.G., Stockman, G.C.: Computer Vision. Prentice Hall, Englewood Cliffs (2001)
Martin, D., Fowlkes, C., Tal, D., Malik, J.: A Database of Human Segmented Natural Images and its Application to Evaluating Segmentation Algorithms and Measuring Ecological Statistics. In: Proc. 8th Int’l. Conf. Computer Vision, pp. 416–423 (2001)
Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. IEEE Trans. PAMI 12, 629–639 (1990)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lowe, R.J., Nixon, M.S. (2011). Evolving Content-Driven Superpixels for Accurate Image Representation. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2011. Lecture Notes in Computer Science, vol 6938. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24028-7_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-24028-7_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24027-0
Online ISBN: 978-3-642-24028-7
eBook Packages: Computer ScienceComputer Science (R0)