Abstract
Recent developments in computer vision have shown that local features can provide efficient representations suitable for robust object recognition. Support Vector Machines have been established as powerful learning algorithms with good generalization capabilities. In this paper, we combine these two approaches and propose a general kernel method for recognition with local features. We show that the proposed kernel satisfies the Mercer condition and that it is suitable for many established local feature frameworks. Large-scale recognition results are presented on three different databases, which demonstrate that SVMs with the proposed kernel perform better than standard matching techniques on local features. In addition, experiments on noisy and occluded images show that local feature representations significantly outperform global approaches. 1.
Keywords
Kernel (algebra)Computer scienceArtificial intelligencePattern recognition (psychology)Tree kernelSupport vector machineKernel methodGeneralizationFeature (linguistics)Matching (statistics)Cognitive neuroscience of visual object recognitionFeature extractionRadial basis function kernelMachine learningMathematics
Affiliated Institutions
Related Publications
The pyramid match kernel: discriminative classification with sets of image features
Discriminative learning is challenging when examples are sets of features, and the sets vary in cardinality and lack any sort of meaningful ordering. Kernel-based classification...
Asymptotic Behaviors of Support Vector Machines with Gaussian Kernel
Support vector machines (SVMs) with the gaussian (RBF) kernel have been popular for practical use. Model selection in this class of SVMs involves two hyper parameters: the penal...
Local Features and Kernels for Classification of Texture and Object Categories: An In-Depth Study
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 rep...
Local feature view clustering for 3D object recognition
There have been important recent advances in object recognition through the matching of invariant local image features. However, the existing approaches are based on matching to...
RGB-D Object Recognition via Incorporating Latent Data Structure and Prior Knowledge
For the task of RGB-D object recognition, it is important to identify suitable representations of images, which can boost the performance of object recognition. In this work, we...
Publication Info
- Year
- 2003
- Type
- article
- Pages
- 257-264 vol.1
- Citations
- 342
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
342
OpenAlex
Cite This
Christian Wallraven,
Barbara Caputo,
Gräf
(2003).
Recognition with local features: the kernel recipe.
, 257-264 vol.1.
https://doi.org/10.1109/iccv.2003.1238351
Identifiers
- DOI
- 10.1109/iccv.2003.1238351