Multi-Manifold Ranking: Using Multiple Features for Better Image Retrieval

Manifold Ranking (MR) is one of the most popular graphbased ranking methods and has been widely used for information retrieval. Due to its ability to capture the geometric structure of the image set, it has been successfully used for image retrieval. The existing approaches that use manifold ranking rely only on a single image manifold. However, such methods may not fully discover the geometric structure of the image set and may lead to poor precision results. Motivated by this, we propose a novel method named Multi-Manifold Ranking (MMR) which embeds multiple image manifolds each constructed using a different image feature. We propose a novel cost function that is minimized to obtain the ranking scores of the images. Our proposed multi-manifold ranking has a better ability to explore the geometric structure of image set as demonstrated by our experiments. Furthermore, to improve the efficiency of MMR, a specific graph called anchor graph is incorporated into MMR. The extensive experiments on real world image databases demonstrate that MMR outperforms existing manifold ranking based methods in terms of quality and has comparable running time to the fastest MR algorithm.