Incorporating multiple SVMs for automatic image annotation

13 years 4 months ago

Download sci2s.ugr.es

In this paper, a novel automatic image annotation system is proposed, which integrates two sets of support vector machines (SVMs), namely the multiple instance learning (MIL)-based and global-feature-based SVMs, for annotation. The MIL-based bag features are obtained by applying MIL on the image blocks, where the enhanced diversity density (DD) algorithm and a faster searching algorithm are applied to improve the efﬁciency and accuracy. They are further input to a set of SVMs for ﬁnding the optimum hyperplanes to annotate training images. Similarly, global color and texture features, including color histogram and modiﬁed edge histogram, are fed into another set of SVMs for categorizing training images. Consequently, two sets of image features are constructed for each test image and are, respectively, sent to the two sets of SVMs, whose outputs are incorporated by an automatic weight estimation method to obtain the ﬁnal annotation results. Our proposed annotation approach demon...

Xiaojun Qi, Yutao Han

Real-time Traffic