Advertisement

Gram-Schmidt Orthonormalization-Based Color Model for Object Detection

  • Mariusz Borawski
  • Paweł Forczmański
Conference paper

Abstract

The paper presents two methods of creating custom color models used in object detection in digital images. Developed methods are based on Gram-Schmidt orthonormalization procedure and can be applied in different fields of recognition (human faces, remotely sensed images, etc.). Their main advantage over other ones is the efficient description and representation of color variations.

Keywords

Object detection color model orthonormalization 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

4 References

  1. [1]
    Białasiewicz J. T. „Falki i aproksymacje“ Warszawa 2000 [in Polish]Google Scholar
  2. [2]
    Lathi B. P. „Teoria sygnałów i układów telekomunikacyjnych“ Warszawa 1970 [in Polish]Google Scholar
  3. [3]
    Earth Sciences and Image Analysis, NASA-Johnson Space Center. „The Gateway to Astronaut Photography of Earth.“ <http://eol.jsc.nasa.gov/>Google Scholar
  4. [4]
    Arbib M. A. and Uchiyama T. „'Color image segmentation using competitive learning“. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol 16, 1994Google Scholar
  5. [5]
    Yang Ming-Hsuan and Ahuja Narendra. „Detecting Human Faces in Color Images“. International Conference on Image Processing. Vol. 1. 1998Google Scholar
  6. [6]
    Garcia C., Tziritas G., „Face Detection Using Quantized Skin Color Regions Merging and Wavelet Packet Analysis“, IEEE Transactions on Multimedia, 1(3) 1999Google Scholar

Copyright information

© Springer Science+Business Media, Inc. 2005

Authors and Affiliations

  • Mariusz Borawski
    • 1
  • Paweł Forczmański
    • 1
  1. 1.Technical University of SzczecinSzczecin

Personalised recommendations