Automatic Web Image Annotation via Web-Scale Image Semantic Space Learning

摘要

The correlation between keywords has been exploited to improve Automatic Image Annotation(AIA). Differing from the traditional lexicon or training data based keyword correlation estimation, we propose using Web-scale image semantic space learning to explore the keyword correlation for automatic Web image annotation. Specifically, we use the Social Media Web site: Flickr as Web scale image semantic space to determine the annotation keyword correlation graph to smooth the annotation probability estimation. To further improve Web image annotation performance, we present a novel constraint piecewise penalty weighted regression model to estimate the semantics of the Web image from the corresponding associated text. We integrate the proposed approaches into our Web image annotation framework and conduct experiments on a real Web image data set. The experimental results show that both of our approaches can improve the annotation performance significantly.