Sciweavers

CVPR
2006
IEEE

Image-Segmentation Evaluation From the Perspective of Salient Object Extraction

15 years 26 days ago
Image-Segmentation Evaluation From the Perspective of Salient Object Extraction
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 extended to other applications. We present in this paper a new benchmark for evaluating image segmentation. Specifically, we formulate image segmentation as identifying the single most perceptually salient structure from an image. We collect a large variety of test images that conforms to this specific formulation, construct unambiguous ground truth for each image, and define a reliable way to measure the segmentation accuracy. We then present two special strategies to further address two important issues: (a) the most salient structures in some real images may not be u...
Feng Ge, Song Wang, Tiecheng Liu
Added 12 Oct 2009
Updated 28 Oct 2009
Type Conference
Year 2006
Where CVPR
Authors Feng Ge, Song Wang, Tiecheng Liu
Comments (0)