Unsupervised Segmentation Evaluation for Image Annotation

Annette Morales-González, Edel García-Reyes, Luis Enrique Sucar

2015

Abstract

Unsupervised segmentation evaluation measures are usually validated against human-generated ground-truth. Nevertheless, with the recent growth of image classification methods that use hierarchical segmentation-based representations, it would be desirable to assess the performance of unsupervised segmentation evaluation to select the most suitable levels to perform recognition tasks. Another problem is that unsupervised segmentation evaluation measures use only low-level features, which makes difficult to evaluate how well an object is outlined. In this paper we propose to use four semantic measures, that combined with other state-of-the-art measures improve the evaluation results and also, we validate the results of each unsupervised measure against an image annotation algorithm ground truth, showing that using measures that try to emulate human behaviour is not necessarily what an automatic recognition algorithm may need. We employed the Stanford Background Dataset to validate an image annotation algorithm that includes segmentation evaluation as starting point, and the proposed combination of unsupervised measures showed the best annotation accuracy results.

Paper Citation

in Harvard Style

Morales-González A., García-Reyes E. and Sucar L. (2015). Unsupervised Segmentation Evaluation for Image Annotation . In Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015) ISBN 978-989-758-090-1, pages 148-155. DOI: 10.5220/0005314201480155

in Bibtex Style

@conference{visapp15,
author={Annette Morales-González and Edel García-Reyes and Luis Enrique Sucar},
title={Unsupervised Segmentation Evaluation for Image Annotation},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)},
year={2015},
pages={148-155},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005314201480155},
isbn={978-989-758-090-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2015)
TI - Unsupervised Segmentation Evaluation for Image Annotation
SN - 978-989-758-090-1
AU - Morales-González A.
AU - García-Reyes E.
AU - Sucar L.
PY - 2015
SP - 148
EP - 155
DO - 10.5220/0005314201480155