Abstract
Automatic image annotation is a promising solution to enable more effective image retrieval by keywords. Different statistical models and machine learning methods have been introduced for image auto-annotation. In this paper, we propose a collaborative approach, in which multiple different statistical models are combined effectively to predict the annotation for each image. Moreover, we combine both low-level feature of image and semantic information naturally. In addition, we also combine the correspondence between keywords and image visual tokens/regions, and the word-to-word correlation to enhance the annotation. We employ the conditional probability to express two kinds of correlation uniformly and obtain the correspondence between keyword and visual feature with two typical statistical models. Experiments conducted on standard Corel dataset demonstrate the effectiveness of the proposed method for image automatic annotation.