Object retrieval with large vocabularies and fast spatial matching

In this paper, we present a large-scale object retrieval system. The user supplies a query object by selecting a region of a query image, and the system returns a ranked list of images that contain the same object, retrieved from a large corpus. We demonstrate the scalability and performance of our system on a dataset of over 1 million images crawled from the photo-sharing site, Flickr [3], using Oxford landmarks as queries. Building an image-feature vocabulary is a major time and performance bottleneck, due to the size of our dataset. To address this problem we compare different scalable methods for building a vocabulary and introduce a novel quantization method based on randomized trees which we show outperforms the current state-of-the-art on an extensive ground-truth. Our experiments show that the quantization has a major effect on retrieval quality. To further improve query performance, we add an efficient spatial verification stage to re-rank the results returned from our bagof-...

• Type: Conference
• Year: 2007
• Where: CVPR
• Authors: James Philbin, Ondrej Chum, Michael Isard, Josef Sivic, Andrew Zisserman
• Keywords: Computer Vision, CVPR 2007, Efficient Spatial Verification, Large-scale Object Retrieval, Query Image, Query Object, Query Performance