University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Finding semantic structures in image hierarchies using laplacian graph energy

Song, Yi-Zhe, Arbelaez, P., Hall, P., Li, C. and Balikai, A. (2010) Finding semantic structures in image hierarchies using laplacian graph energy In: 11th European Conference on Computer Vision (ECCV 2010), 05-11 Sep 2010, Heraklion, Crete, Greece.

Full text not available from this repository.

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.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Song, Yi-Zhey.song@surrey.ac.uk
Arbelaez, P.
Hall, P.
Li, C.
Balikai, A.
Date : October 2010
DOI : 10.1007/978-3-642-15561-1_50
Uncontrolled Keywords : Regular Graph; Graph Complexity; Maximally Stable Extremal Region; Graph Energy; Benchmark Score
Related URLs :
Depositing User : Clive Harris
Date Deposited : 12 Aug 2019 15:12
Last Modified : 12 Aug 2019 15:12
URI: http://epubs.surrey.ac.uk/id/eprint/852156

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800