Feature extraction for biological images

John Ostuni, Stanley Dunn, Peter Meer

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

Abstract

An elegant method to perform recognition and classification of similar features taken from different perspectives is proposed. The method is based upon the principles of projective invariants. By sliding two separate windows over a segment containing two intersecting curves, a distribution is obtained of invariant values due to parameterizing all points in each window. This distribution has two peaks. One is centered at three which is due to both windows lying on the same conic. Another is centered at the invariant of the two conics. This former peak can be backprojected to extract homogeneous regions while the latter peak can be backprojected to extract the transition areas.

Original languageEnglish (US)
Title of host publicationProceedings of the Annual Conference on Engineering in Medicine and Biology
PublisherPubl by IEEE
Pages350-351
Number of pages2
Editionpt 1
ISBN (Print)0780302168
StatePublished - 1991
EventProceedings of the 13th Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Orlando, FL, USA
Duration: Oct 31 1991Nov 3 1991

Publication series

NameProceedings of the Annual Conference on Engineering in Medicine and Biology
Numberpt 1
Volume13
ISSN (Print)0589-1019

Other

OtherProceedings of the 13th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
CityOrlando, FL, USA
Period10/31/9111/3/91

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Fingerprint

Dive into the research topics of 'Feature extraction for biological images'. Together they form a unique fingerprint.

Cite this