Measuring the Quality of Figure/Ground Segmentations

Figure/Ground segmentation is of great interest within the analysis of video streams. We propose a new, continu-ous evaluation measure for figure/ground segmentation al-gorithms which allows for assessing the quality of a seg-mentation. The evaluation approach is based on set similar-ities and logic-motivated considerations. Results obtained with the new measure are shown for several well-known al-gorithms. Compared to existing detection rate/false alarm considerations, the proposed measure reveals advantages and shortcommings of different algorithms much better and can therefore be used as a selection criterion. 1