Loading...
Loading...

Go to the content (press return)

Measures and meta-measures for the supervised evaluation of image segmentation

Author
Pont, J.; Marques, F.
Type of activity
Presentation of work at congresses
Name of edition
26th IEEE Conference on Computer Vision and Pattern Recognition
Date of publication
2013
Presentation's date
2013-06-23
Book of congress proceedings
CVRP 2013: 2013 IEEE Conference on Computer Vision and Pattern Recognition: proceedings: 23-28 June 2013: Portland, Oregon, USA
First page
2131
Last page
2138
Publisher
IEEE Computer Society Publications
DOI
https://doi.org/10.1109/CVPR.2013.277 Open in new window
Project funding
Procesado de vídeo multicámara empleando información de la escena: aplicación a eventos deportivos, interacción visual y 3DTV
Repository
http://hdl.handle.net/2117/22498 Open in new window
URL
http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6619121&tag=1 Open in new window
Abstract
This paper tackles the supervised evaluation of image segmentation algorithms. First, it surveys and structures the measures used to compare the segmentation results with a ground truth database, and proposes a new measure: the precision-recall for objects and parts. To compare the goodness of these measures, it defines three quantitative meta-measures involving six state of the art segmentation methods. The meta-measures consist in assuming some plausible hypotheses about the results and assess...
Citation
Pont, J.; Marques, F. Measures and meta-measures for the supervised evaluation of image segmentation. A: IEEE Conference on Computer Vision and Pattern Recognition. "CVRP 2013: 2013 IEEE Conference on Computer Vision and Pattern Recognition: proceedings: 23-28 June 2013: Portland, Oregon, USA". Portland, Oregon: IEEE Computer Society Publications, 2013, p. 2131-2138.
Keywords
Benchmark testing, Context, Current measurement, Databases, Image segmentation, Object detection, Partitioning algorithms
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants