Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study
Citations Over TimeTop 10% of 2006 papers
Abstract
Recently, methods based on local image features have shown promise for texture and object recognition tasks. This paper presents a large-scale evaluation of an approach that represents images as distributions (signatures or histograms) of features extracted from a sparse set of keypoint locations and learns a Support Vector Machine classifier with kernels based on two effective measures for comparing distributions, the Earth Mover’s Distance and the ÷2 distance. We first evaluate the performance of our approach with different keypoint detectors and descriptors, as well as different kernels and classifiers. We then conduct a comparative evaluation with several state-of-the-art recognition methods on 4 texture and 5 object databases. On most of these databases, our implementation exceeds the best reported results and achieves comparable performance on the rest. Finally, we investigate the influence of background correlations on recognition performance.
Related Papers
- → Texture classification based on succolarity(2013)14 cited
- The Method of Image Restoration Based on the Compensation of Texture(2009)
- A Woman, Object of Love or a Fetish?(2013)
- → Modes of presentation and ways of appearing: a critical revision of Evans’s account*(2019)
- → Reference Counting(1999)