Title :
Measuring the quality of figure/ground segmentations
Author :
Arens, Michael ; Anderer, Claus
Author_Institution :
Fraunhofer Inst. of Optronics, Syst. Technol. & Image Exploitation, Ettlingen, Germany
Abstract :
Figure/Ground segmentation is of great interest within the analysis of video streams. We propose a new, continuous evaluation measure for figure/ground segmentation algorithms which allows for assessing the quality of a segmentation. The evaluation approach is based on set similarities and logic-motivated considerations. Results obtained with the new measure are shown for several well-known algorithms. 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.
Keywords :
image segmentation; video signal processing; figure segmentations; ground segmentations; video streams analysis; Image analysis; Image segmentation; Infrared imaging; Layout; Motion detection; Object detection; Optical computing; Partitioning algorithms; Pixel; Streaming media;
Conference_Titel :
Computer Vision and Pattern Recognition Workshops (CVPRW), 2010 IEEE Computer Society Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
978-1-4244-7029-7
DOI :
10.1109/CVPRW.2010.5543793