SIFT-based object recognition with fast alphabet creation and reduced curse of dimensionality
Authors:
- 1 November 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 136-141
Abstract
This article presents a SIFT-based object recognition method that avoids the typical problems of time-consuming code-book generation and curse of dimensionality in feature comparison. The first problem is solved by using an alphabet of completely synthetic feature vectors. The second problem is solved by using the Hamming-distance on binarised SIFT-features. The method is supported by competitive results on the Graz'02 image data base.Keywords
This publication has 17 references indexed in Scilit:
- Feature selection, mutual information, and the classification of high-dimensional patternsPattern Analysis and Applications, 2008
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories2006
- Multiple Object Class Detection with a Generative Model2006
- Efficient Clustering and Matching for Object Class Recognition2006
- Spatial Priors for Part-Based Recognition Using Statistical Models2005
- The pyramid match kernel: discriminative classification with sets of image features2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- On the "dimensionality curse" and the "self-similarity blessing"IEEE Transactions on Knowledge and Data Engineering, 2001
- Object recognition from local scale-invariant features1999
- The representational capacity of the distributed encoding of information provided by populations of neurons in primate temporal visual cortexExperimental Brain Research, 1997