Translator Disclaimer
1 July 2007 New benchmark for image segmentation evaluation
Author Affiliations +
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.
©(2007) Society of Photo-Optical Instrumentation Engineers (SPIE)
Feng Ge, Song Wang, and Tiecheng Liu "New benchmark for image segmentation evaluation," Journal of Electronic Imaging 16(3), 033011 (1 July 2007).
Published: 1 July 2007


Textural discrimination in unconstrained environment
Proceedings of SPIE (March 03 2014)
Patch forest a hybrid framework of random forest...
Proceedings of SPIE (March 21 2016)
AWM: Adaptive Weight Matting for medical image segmentation
Proceedings of SPIE (February 24 2017)
Metrics for image segmentation
Proceedings of SPIE (July 06 1998)
Finding regions of interest for content extraction
Proceedings of SPIE (December 17 1998)

Back to Top