Image annotation by incorporating word correlations into multi-class SVM

Image annotation systems aim at automatically annotating images with semantic keywords. Machine learning approaches are often used to develop these systems. In this paper, we propose an image annotation approach by incorporating word correlations into multi-class support vector machine (SVM). At first, each image is segmented into five fixed-size blocks instead of time-consuming object segmentation. Every keyword from training images is manually assigned to the corresponding block and word correlations are computed by a co-occurrence matrix. Then, MPEG-7 visual descriptors are applied to these blocks to represent visual features and the minimal-redundancy-maximum-relevance (mRMR) method is used to reduce the feature dimension. A block-feature-based multi-class SVM classifier is trained for 80 semantic concepts. At last, the probabilistic outputs from SVM and the word correlations are integrated to obtain the final annotation keywords. The experiments on Corel 5000 dataset demonstrate our approach is effective and efficient.