Share Email Print

Journal of Electronic Imaging

New benchmark for image segmentation evaluation
Author(s): Feng Ge; Song Wang; Tiecheng Liu
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

Image segmentation and its performance evaluation are very difficult but important problems in computer vision. A major challenge in segmentation evaluation comes from the fundamental conflict between generality and objectivity: For general-purpose segmentation, the ground truth and segmentation accuracy may not be well defined, while embedding the evaluation in a specific application, the evaluation results may not be extensible to other applications. We present a new benchmark to evaluate five different image segmentation methods according to their capability to separate a perceptually salient structure from the background with a relatively small number of segments. This way, we not only find a large variety of images that satisfy the requirement of good generality, but also construct ground-truth segmentations to achieve good objectivity. We also present a special strategy to address two important issues underlying this benchmark: (1) most image-segmentation methods are not developed to directly extract a single salient structure; (2) many real images have multiple salient structures. We apply this benchmark to evaluate and compare the performance of several state-of-the-art image segmentation methods, including the normalized-cut method, the watershed method, the efficient graph-based method, the mean-shift method, and the ratio-cut method.

Paper Details

Date Published: 1 July 2007
PDF: 16 pages
J. Electron. Imaging. 16(3) 033011 doi: 10.1117/1.2762250
Published in: Journal of Electronic Imaging Volume 16, Issue 3
Show Author Affiliations
Feng Ge, Virginia Polytechnic Institute and State Univ. (United States)
Song Wang, Univ. of South Carolina (United States)
Tiecheng Liu, Univ. of South Carolina (United States)

© SPIE. Terms of Use
Back to Top