Accurate feature matching and scoring for re-ranking image retrieval results

In this paper, a new reranking approach is proposed to refine the results obtained with a bag-of-visual words (BoVW) image retrieval method. First, a simple but effective criterion to reject unreliable feature matches is proposed, where the information of nearest neighbors from a large dataset is used to accurately estimate feature density. Second, by adopting a product quantization-based nearest neighbor method in both the voting and reranking steps, it becomes possible to reuse the information obtained in the BoVW method in the reranking step. Finally, a density ratio-based scoring method is naturally integrated to calculate a new score from inliers.