Object retrieval with large vocabularies and fast spatial matching

• Published in: 2007 IEEE Conference on Computer Vision and Pattern Recognition pp. 1 - 8
• Main Authors: Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2007
• Subjects: Humans; Image retrieval; Information filtering; Information filters; Information retrieval; Large-scale systems; Quantization; Scalability; Silicon; Vocabulary
• ISBN: 9781424411795; 1424411793
• ISSN: 1063-6919; 1063-6919
• DOI: 10.1109/CVPR.2007.383172

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 bag-of-words model and show that this consistently improves search quality, though by less of a margin when the visual vocabulary is large. We view this work as a promising step towards much larger, "web-scale " image corpora.