TELECOM ParisTech at ImageCLEF 2010 Photo Annotation Task: Combining Tags and Visual Features for Learning-Based Image Annotation

Hichem Sahbi, Xi Li
2010 Conference and Labs of the Evaluation Forum  
In this paper, we describe the participation of TELECOM ParisTech in the ImageCLEF 2010 Photo Annotation challenge. This edition focuses on promoting combination between visual and tag features in order to enhance photo annotation. An image collection is supplied with tags which are used both for training and testing. Our training approach consists of building SVM classifiers and kernels which take into account the similarity between visual features as well as tags. The results clearly
more » ... te (i) the complementarity of tags and visual descriptors and (ii) the effectiveness of SVM classifiers in photo annotation.
dblp:conf/clef/SahbiL10 fatcat:whbokooqf5hdnf63zdjw2fkanq