Distinctive Interest Point Selection for Efficient Near-duplicate Image Retrieval

Abstract

Distinctive subset of the interest points creation for near-duplicate image retrieval is significant in two terms. The former is that the query time decreases reasonably. The latter is that using the distinctive subsets performs better than the ordinary subsets. In this paper, we focus on the creation of such subsets for effective near-duplicate retrieval and propose a novel interest point selection method. In this method, the distinctive subset is created with a ranking according to a density map calculated from the interest points. We examined a number of experiments to show the performance of the proposed method and we got a convincing result of 95.46% recall while the precision is still 96.04%.