Skip to content

Advertisement

  • Research Article
  • Open Access

Fast Pattern Detection Using Normalized Neural Networks and Cross-Correlation in the Frequency Domain

EURASIP Journal on Advances in Signal Processing20052005:404897

https://doi.org/10.1155/ASP.2005.2054

  • Received: 12 January 2004
  • Published:

Abstract

Neural networks have shown good results for detection of a certain pattern in a given image. In our previous work, a fast algorithm for object/face detection was presented. Such algorithm was designed based on cross-correlation in the frequency domain between the input image and the weights of neural networks. Our previous work also solved the problem of local subimage normalization in the frequency domain. In this paper, the effect of image normalization on the speedup ratio of pattern detection is presented. Simulation results show that local subimage normalization through weight normalization is faster than subimage normalization in the spatial domain. Moreover, the overall speedup ratio of the detection process is increased as the normalization of weights is done offline.

Keywords and phrases

  • fast pattern detection
  • neural networks
  • cross-correlation
  • image normalization

Authors’ Affiliations

(1)
Multimedia Devices Laboratory, University of Aizu, Aizu Wakamatsu 965-8580, Japan

Copyright

Advertisement