Authors:
Annette Morales-González
1
;
Edel García-Reyes
1
and
Luis Enrique Sucar
2
Affiliations:
1
Advanced Technologies Application Center, Cuba
;
2
Instituto Nacional de Astrofísica and Óptica y Electrónica, Mexico
Keyword(s):
Unsupervised Segmentation Evaluation, Automatic Image Annotation, Irregular Graph Pyramid.
Related
Ontology
Subjects/Areas/Topics:
Computer Vision, Visualization and Computer Graphics
;
Image and Video Analysis
;
Segmentation and Grouping
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 im
age annotation algorithm that includes segmentation evaluation as starting point, and the proposed combination of unsupervised measures showed the best annotation accuracy results.
(More)