Résumé

This articles describes the ImageCLEF 2015 Medical Classification task. The task contains several subtasks that all use a data set of figures from the biomedical open access literature (PubMed Central). Particularly compound figures are targeted that are frequent in the literature. For more detailed information analysis and retrieval it is important to extract targeted information from the compound figures. The proposed tasks include compound figure detection (separating compound from other figures), multi-label classification (define all sub types present), figure separation (find boundaries of the subfigures) and modality classification (detecting the figure type of each subfigure). The tasks are described with the participation of international research groups in the tasks. The results of the participants are then described and analysed to identify promising techniques.

Détails

Actions

PDF