Pixel-level similarity fusion for image classification

Alex Pappachen James

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

Abstract

Recent research shows that local similarity calculations play a significant role in improving the recognition performance of template matching systems. We present a new scheme for parametric similarity calculation and fusion for image classification. State-of-the-art recognition results are obtained using the proposed method for a difficult task involving face images.

Original languageEnglish
Title of host publication2010 7th International Multi-Conference on Systems, Signals and Devices, SSD-10
DOIs
Publication statusPublished - 2010
Event2010 7th International Multi-Conference on Systems, Signals and Devices, SSD-10 - Amman, Jordan
Duration: Jun 27 2010Jun 29 2010

Publication series

Name2010 7th International Multi-Conference on Systems, Signals and Devices, SSD-10

Other

Other2010 7th International Multi-Conference on Systems, Signals and Devices, SSD-10
CountryJordan
CityAmman
Period6/27/106/29/10

Keywords

  • Classification
  • Similarity
  • Template matching

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing
  • Control and Systems Engineering

Fingerprint Dive into the research topics of 'Pixel-level similarity fusion for image classification'. Together they form a unique fingerprint.

Cite this