Image reduction for object recognition

B. Z. Shaick, L. Yaroslavsky

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The problem addressed is that of the fast generation of accurate multiple downscaled copies of an input image, with an arbitrary non-integer reduction factor, for object detection and recognition. Three algorithms that can be implemented in parallel, recursive and hybrid architectures are introduced and compared in terms of their accuracy and computational complexity. It is shown that the recursive algorithm is the most advantageous in terms of computational complexity, while the parallel algorithm performs better in terms of accuracy reduction. The hybrid algorithm combines advantages of both.

Original languageEnglish
Title of host publicationProceedings VIPromCom 2002 - 4th EURASIP - IEEE Region 8 International Symposium on Video / Image Processing and Multimedia Communications
EditorsMislav Grgic
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages333-338
Number of pages6
ISBN (Electronic)9537044017, 9789537044015
DOIs
StatePublished - 2002
Event4th EURASIP - IEEE Region 8 International Symposium on Video / Image Processing and Multimedia Communications, VIPromCom 2002 - Zadar, Croatia
Duration: 16 Jun 200219 Jun 2002

Publication series

NameProceedings VIPromCom 2002 - 4th EURASIP - IEEE Region 8 International Symposium on Video / Image Processing and Multimedia Communications

Conference

Conference4th EURASIP - IEEE Region 8 International Symposium on Video / Image Processing and Multimedia Communications, VIPromCom 2002
Country/TerritoryCroatia
CityZadar
Period16/06/0219/06/02

Keywords

  • Image Magnification
  • Image Reduction
  • Object Detection
  • Object Recognition

Fingerprint

Dive into the research topics of 'Image reduction for object recognition'. Together they form a unique fingerprint.

Cite this