Discriminative Learning of Local Image Descriptors
Top Cited Papers
- 18 March 2010
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Ieee Transactions On Pattern Analysis and Machine Intelligence
- Vol. 33 (1), 43-57
- https://doi.org/10.1109/tpami.2010.54
Abstract
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.Keywords
This publication has 40 references indexed in Scilit:
- Semantic texton forests for image categorization and segmentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Modeling the World from Internet Photo CollectionsInternational Journal of Computer Vision, 2007
- Learning Local Image DescriptorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Discriminant Embedding for Local Image DescriptorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Multi-View Stereo for Community Photo CollectionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Task Specific Local Region MatchingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Keypoint recognition using randomized treesIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- Unsupervised 3D Object Recognition and Reconstruction in Unordered DatasetsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Scale & Affine Invariant Interest Point DetectorsInternational Journal of Computer Vision, 2004
- Learning to detect natural image boundaries using local brightness, color, and texture cuesIeee Transactions On Pattern Analysis and Machine Intelligence, 2004