Image retrieval on large-scale image databases

Eva Hörster, Rainer Lienhart, Malcolm Slaney
2007 Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07  
Online image repositories such as Flickr contain hundreds of millions of images and are growing quickly. Along with that the needs for supporting indexing, searching and browsing is becoming more and more pressing. In this work we will employ the image content as a source of information to retrieve images. We study the representation of images by Latent Dirichlet Allocation (LDA) models for content-based image retrieval. Image representations are learned in an unsupervised fashion, and each
more » ... e is modeled as the mixture of topics/object parts depicted in the image. This allows us to put images into subspaces for higher-level reasoning which in turn can be used to find similar images. Different similarity measures based on the described image representation are studied. The presented approach is evaluated on a real world image database consisting of more than 246,000 images and compared to image models based on probabilistic Latent Semantic Analysis (pLSA). Results show the suitability of the approach for large-scale databases. Finally we incorporate active learning with user relevance feedback in our framework, which further boosts the retrieval performance.
doi:10.1145/1282280.1282283 dblp:conf/civr/HorsterLS07 fatcat:av6ycxhv3bhffamp4wmatrwn4m