Ensemble one-class support vector machines for content-based image retrieval

In order to narrow semantic gap between user query concept and low-level features in content-based image retrieval, SVM-based relevance feedback techniques are developed to learn user’s query concept by labeling some samples. The major difficulty in relevance feedback is to estimate the support of target image in high-dimensional feature space with small number of training samples. To overcome this limitation, we propose an ensemble method to boost image retrieval accuracy and to improve its generalization performance. Images are segmented into multiple instances. A set of moderate accurate one-class support vector machine classifiers are trained separately by using different sub-features extracted from instances. The ensemble method results in a highly accurate by combining moderately accurate weak classifiers. Our propose ensemble scheme not only provides a robust mechanism in selecting strong query concept related images for relevant feedback, but also achieves a generalization performance in image retrieval.