Dragi Kocev, Ivica Dimitrovski: Large Scale System for Detection of Visual Concepts and Hierarchical Annotation of Images

Dragi and Ivica will present a large scale system for detection of visual concepts and annotation of images. The system is composed of two parts: feature extraction and classification/annotation. The feature extraction part provides global and local descriptions of the images. These descriptions are then used to learn a classifier and to annotate an image with the corresponding concepts. To this end, we use ensembles of predictive clustering trees (PCTs), which are able to classify target concepts that are organized in a hierarchy. We tested our system on the image database (annotated Flickr images) from the ImageCLEF@ICPR 2010 photo annotation task. The extensive experiments conducted on the benchmark database show that our system has very high predictive performance and can be easily scaled to large amounts of visual concepts and data.

Thursday, 11.3.2010, 13:00, Orange Room