Pattern recognition with local invariant features

C. Schmid, G. Dorkó, S. Lazebnik, K. Mikolajczyk, J. Ponce

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Local invariant features have shown to be very successful for recognition. They are robust to occlusion and clutter, distinctive as well as invariant to image transformations. In this chapter recent progress on local invariant features is summarized. It is explained how to extract scale and affine-invariant regions and how to obtain discriminant descriptors for these regions. It is then demonstrated that combining local features with pattern classification techniques allows for texture and category-level object recognition in the presence of varying viewpoints and background clutter.

Original languageEnglish (US)
Title of host publicationHandbook of Pattern Recognition and Computer Vision, 3rd Edition
PublisherWorld Scientific Publishing Co.
Pages71-92
Number of pages22
ISBN (Electronic)9789812775320
ISBN (Print)9812561056, 9789812561053
DOIs
StatePublished - Jan 1 2005

ASJC Scopus subject areas

  • Computer Science(all)

Fingerprint Dive into the research topics of 'Pattern recognition with local invariant features'. Together they form a unique fingerprint.

Cite this