Exploiting Term Co-occurrence for Enhancing Automated Image Annotation
This paper describes an application of statistical co-occurrence techniques that built on top of a probabilistic image annotation framework is able to increase the precision of an image annotation system. We observe that probabilistic image analysis by itself is not enough to describe the rich semantics of an image. Our hypothesis is that more accurate annotations can be produced by introducing additional knowledge in the form of statistical co-occurrence of terms. This is provided by the context of images that otherwise independent keyword generation would miss. We applied our algorithm to the dataset provided by ImageCLEF 2008 for the Visual Concept Detection Task (VCDT). Our algorithm not only obtained better results but also it appeared in the top quartile of all methods submitted in ImageCLEF 2008.
Keywordsautomated image annotation statistical co-occurrence image analysis semantic similarity
Unable to display preview. Download preview PDF.
- 1.Yavlinsky, A., Schofield, E., Rüger, S.: Automated image annotation using global features and robust nonparametric density estimation. In: Proceedings of the International ACM Conference on Image and Video Retrieval, pp. 507–517 (2005)Google Scholar
- 4.Deselaers, T., Hanbury, A.: The visual concept detection task in ImageCLEF 2008. In: Peters, C., et al. (eds.) CLEF 2008. LNCS, vol. 5706, pp. 531–538. Springer, Heidelberg (2009)Google Scholar
- 5.Pedersen, Banerjee, Patwardhan: Maximizing semantic relatedness to perform word sense disambiguation. Technical report, University of Minnesota (2003)Google Scholar
- 9.Llorente, A., Rüger, S.: Can a probabilistic image annotation system be improved using a co-occurrence approach? In: Workshop on Cross-Media Information Analysis, Extraction and Management at the 3rd International Conference on Semantic and Digital Media Technologies (2008)Google Scholar
- 10.Tollari, S., Detyniecki, M., Fakeri-Tabrizi, A., Amini, M.R., Gallinari, P.: UPMC/LIP6 at ImageCLEFphoto 2008: On the exploitation of visual concepts (VCDT). In: Evaluating Systems for Multilingual and Multimodal Information Access – 9th Workshop of the Cross-Language Evaluation Forum (2008)Google Scholar