Affine-invariant pattern recognition using momentums in log-polar images

  • Authors:

  • Young-Ho Son;Bum-Jae You;Sang-Rok Oh;Gwi-Tae Park

  • Affiliations:

  • Intelligent Robotics Research Center, KIST, Seoul, Korea and Department of Electrical Engineering, Korea University, Seoul, Korea;Intelligent Robotics Research Center, KIST, Seoul, Korea;Intelligent Robotics Research Center, KIST, Seoul, Korea;Department of Electrical Engineering, Korea University, Seoul, Korea

  • Venue:
  • FGR' 04 Proceedings of the Sixth IEEE international conference on Automatic face and gesture recognition
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

Log-polar images are useful in the sense that their image data size is reduced dramatically comparing with conventional images and it is possible to develop faster pattern recognition algorithms. Especially, the log-polar image is very similar with the structure of human eyes and is used in a face detection and tracking. However, there are almost no researches on pattern recognition using the log-polar images while a number of researches on visual tracking have been executed. In this paper, an affine-invariant pattern recognition technique for log-polar images using momentums. We handle basic distortions of a pattern including translation, rotation, scaling, and skew in a log-polar image. The algorithm is experimented in a PC-based real-time vision system successfully.