Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
407225 | Neurocomputing | 2013 | 12 Pages |
In this paper, we propose an efficient indexing method for content-based image retrieval. The proposed method introduces the ordered quantization to increase the distinction among the quantized feature descriptors. Thus, the feature point correspondences can be determined by the quantized feature descriptors, and they are used to measure the similarity between query image and database image. To implement the above scheme efficiently, a multi-dimensional inverted index is proposed to compute the number of feature point correspondences, and then approximate RANSAC is investigated to estimate the spatial correspondences of feature points between query image and candidate images returned from the multi-dimensional inverted index. The experimental results demonstrate that our indexing method improves the retrieval efficiency while ensuring the retrieval accuracy in the content-based image retrieval.
► An efficient indexing method is proposed for content-based image retrieval. ► The indexing method employs feature point correspondences to retrieve images. ► The ordered quantization determines the feature point correspondences. ► Multi-dimensional inverted index counts the number of feature point correspondences. ► Approximate RANSAC estimates the spatial correspondences of feature points.