Finding semantic structures in image hierarchies using Laplacian graph energy

Reference:

Song, Y.-Z., Arbelaez, P., Hall, P., Li, C. and Balikai, A., 2010. Finding semantic structures in image hierarchies using Laplacian graph energy. In: Daniilidis, K., Maragos, P. and Paragios, N., eds. Computer Vision, ECCV 2010: 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part IV. Berlin: Springer-Verlag, pp. 694-707. (Lecture Notes in Computer Science; 6314)

Related documents:

PDF (Song_LNCS_2010.pdf) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader Download (2472kB)

Official URL:

http://dx.doi.org/10.1007/978-3-642-15561-1_50

Abstract

Many segmentation algorithms describe images in terms of a hierarchy of regions. Although such hierarchies can produce state of the art segmentations and have many applications, they often contain more data than is required for an efficient description. This paper shows Laplacian graph energy is a generic measure that can be used to identify semantic structures within hierarchies, independently of the algorithm that produces them. Quantitative experimental validation using hierarchies from two state of art algorithms show we can reduce the number of levels and regions in a hierarchy by an order of magnitude with little or no loss in performance when compared against human produced ground truth. We provide a tracking application that illustrates the value of reduced hierarchies.

Export

Actions (login required)