New benchmark for image segmentation evaluation
- 1 July 2007
- journal article
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 16 (3), 033011-033011-16
- https://doi.org/10.1117/1.2762250
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.Keywords
This publication has 34 references indexed in Scilit:
- Efficient Graph-Based Image SegmentationInternational Journal of Computer Vision, 2004
- Image segmentation with ratio cutIeee Transactions On Pattern Analysis and Machine Intelligence, 2003
- Watersnakes: Energy-driven watershed srgmentationIeee Transactions On Pattern Analysis and Machine Intelligence, 2003
- Stochastic image segmentation by typical cutsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Blobworld: image segmentation using expectation-maximization and its application to image queryingIeee Transactions On Pattern Analysis and Machine Intelligence, 2002
- Mean shift: a robust approach toward feature space analysisIeee Transactions On Pattern Analysis and Machine Intelligence, 2002
- Normalized cuts and image segmentationIeee Transactions On Pattern Analysis and Machine Intelligence, 2000
- Fast Marching MethodsSiam Review, 1999
- Watersheds in digital spaces: an efficient algorithm based on immersion simulationsIeee Transactions On Pattern Analysis and Machine Intelligence, 1991
- Image segmentation techniquesComputer Vision, Graphics, and Image Processing, 1985