Object categorization via local kernels

Barbara Caputo, Christian Wallraven, Maria Elena Nilsback

Research output: Chapter in Book/Report/Conference proceedingConference contribution

17 Citations (Scopus)

Abstract

This paper considers the problem of multi-object categorization. We present an algorithm that combines support vector machines with local features via a new class of Mercer kernels. This class of kernels allows us to perform scalar products on feature vectors consisting of local descriptors, computed around interest points (like corners); these feature vectors are generally of different lengths for different images. The resulting framework is able to recognize multi-object categories in different settings, from lab-controlled to real-world scenes. We present several experiments, on different databases, and we benchmark our results with state-of-the-art algorithms for categorization, achieving excellent results.

Original languageEnglish
Title of host publicationProceedings - International Conference on Pattern Recognition
EditorsJ. Kittler, M. Petrou, M. Nixon
Pages132-135
Number of pages4
Volume2
Publication statusPublished - 2004
Externally publishedYes
EventProceedings of the 17th International Conference on Pattern Recognition, ICPR 2004 - Cambridge, United Kingdom
Duration: 2004 Aug 232004 Aug 26

Other

OtherProceedings of the 17th International Conference on Pattern Recognition, ICPR 2004
CountryUnited Kingdom
CityCambridge
Period04/8/2304/8/26

    Fingerprint

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Hardware and Architecture
  • Electrical and Electronic Engineering

Cite this

Caputo, B., Wallraven, C., & Nilsback, M. E. (2004). Object categorization via local kernels. In J. Kittler, M. Petrou, & M. Nixon (Eds.), Proceedings - International Conference on Pattern Recognition (Vol. 2, pp. 132-135)