Region similarity arrangement for large-scale image retrieval

We propose a promising method of geometric verification to improve the precision of Bag-of-Words (BoW) model in image retrieval. Most previous methods focus on the positions of interest points or the absolute differences of regions' scales and angles. In contrast, our method, named Region Similarity Arrangement (RSA), exploits the spatial arrangement of interest regions. For each image, RSA constructs a Region Property Space, regarding each region's (scale, angle) pair as a point in a polar coordinate system, and encodes the arrangement of these points into the BoW vector. Furthermore, based on the particular distribution of points in Region Property Space, we design a Spatial Weighting to reduce the burstiness phenomenon during query. From experimental results on Holidays, Oxford5K and Paris, RSA could get comparable results with state-of-the-art methods. In addition, RSA increases no extra memory and negligible computational consumption compared with the baseline BoW approach.