Can a probabilistic image annotation system be improved using a co-occurrence approach?
This event took place on Wednesday 26 November 2008 at 11:30
The research challenge that we address in this work is to examine whether a traditional automated annotation system can be improved by using external knowledge. Traditional means any machine learning approach together with image analysis techniques. We use as a baseline for our experiments the work done by Yavlinsky et al. who deployed non-parametric density estimation. 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 test our algorithm with two datasets: Corel 5k and ImageCLEF 2008. For the Corel dataset, we obtain statistically significant better results while our algorithm appears in the top quartile of all methods submitted in ImageCLEF 2008. Regarding future work, we intend to apply Semantic Web technologies.
Watch the webcast replay >>
We are also inviting top experts in AI and Knowledge Technologies to discuss major socio-technological topics with an audience that comprises both members of the Knowledge Media Institute, as well as the wider staff at The Open University. Differently from our seminar series, these events follow a Q&A format.