Evolving Content-Driven Superpixels for Accurate Image Representation
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.
KeywordsActive Contour Random Initialisation Gaussian Smoothing Local Invariant Feature Berkeley Segmentation Dataset
Unable to display preview. Download preview PDF.
- 1.Ren, X., Malik, J.: Learning a classification model for segmentation. In: IEEE Proc. Computer Vision, pp. 10–17 (2003)Google Scholar
- 6.Moore, A.P., Prince, S.J.D., Warrell, J.: “Lattice Cut”-Constructing superpixels using layer constraints. In: IEEE CVPR, pp. 2117–2124 (2010)Google Scholar
- 7.Moore, A.P., Prince, S.J.D., Warrell, J., Mohammed, U., Jones, G.: Superpixel lattices. In: IEEE CVPR, pp. 998–1005 (2008)Google Scholar
- 8.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)Google Scholar
- 12.Chan, T.F., Vese, L.A.: Active Contours Without Edges. IEEE Trans. Image Processing 10 (2001)Google Scholar
- 14.Shapiro, L.G., Stockman, G.C.: Computer Vision. Prentice Hall, Englewood Cliffs (2001)Google Scholar
- 15.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)Google Scholar