Abstract
Image annotation is usually formed as a multiclass classification problem. Traditional methods learn the co-occurrence of keywords and images while they ignore the correlation between keywords, which turned out to be one of the reasons causing poor experiment results. In this paper, we propose an automatic image annotation approach by using multiclass SVM with ontology to achieve a higher accuracy. In our paper, we choose semantic dictionary Word Net in which hierarchy defined words are derived from the text ontology to calculate the correlations between keywords. Specifically, we use Bags of Visual Words model to present the image visual feature and apply a mixed kernel in multiclass SVM. Finally, we combine the probability outputs to get the final results. Compared to other state-of-the-art multiclass classification methods, our approach tested in typical Corel dataset maintain a high level of accuracy in classification.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call