Issue No. 01 - January (2011 vol. 33)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TPAMI.2010.54
Matthew Brown , Ecole Polytechnique Fédérale de Lausanne, Lausanne
Gang Hua , Nokia Research Center Hollywood, Santa Monica
Simon Winder , Microsoft Research Redmond, Redmond
In this paper, we explore methods for learning local image descriptors from training data. We describe a set of building blocks for constructing descriptors which can be combined together and jointly optimized so as to minimize the error of a nearest-neighbor classifier. We consider both linear and nonlinear transforms with dimensionality reduction, and make use of discriminant learning techniques such as Linear Discriminant Analysis (LDA) and Powell minimization to solve for the parameters. Using these techniques, we obtain descriptors that exceed state-of-the-art performance with low dimensionality. In addition to new experiments and recommendations for descriptor learning, we are also making available a new and realistic ground truth data set based on multiview stereo data.
Image descriptors, local features, discriminative learning, SIFT.
G. Hua, M. Brown and S. Winder, "Discriminative Learning of Local Image Descriptors," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 33, no. , pp. 43-57, 2010.