Optimal adaptive learning for image retrieval

Learning-enhanced relevance feedback is one of the most promising and active research directions in recent year's content-based image retrieval. However, the existing approaches either require prior knowledge of the data or consume high computation cost, making them less practical. To overcome these difficulties and motivated by the successful history of optimal adaptive filters, in this paper, we present a new approach to interactive image retrieval. Specifically, we cast the image retrieval problem in the optimal filtering framework, which does not require prior knowledge of the data, supports incremental learning, is simple to implement and achieves better performance than the state-of-the-art approaches. To evaluate the effectiveness and robustness of the proposed approach, extensive experiments have been carried out on a large heterogeneous image collection with 17,000 images. We report promising results on a wide variety of queries.