Can a probabilistic image annotation system be improved using a co-occurrence approach?

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. [24] 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 cooccurrence 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.