Nonparametric algorithm for local frequency estimation of multidimensional signals

IEEE Trans Image Process. 2004 Apr;13(4):467-74. doi: 10.1109/tip.2004.823824.

Abstract

Local frequency (LF) estimation of multidimensional (md) signals is considered. The md-Wigner distribution (WD) is used as the LF estimator. The LF is estimated based on the positions of the WD maxima. A nonparametric algorithm for the LF estimation is developed. It is based on the intersection of confidence intervals rule. This algorithm produces an adaptive window size in the WD which gives almost minimal mean squared error of the estimate. A simplified version of this algorithm is developed, with the starting estimate being produced with the WD of one-dimensional signals. Theory is illustrated in examples.

Publication types

  • Comparative Study
  • Evaluation Study
  • Research Support, Non-U.S. Gov't
  • Validation Study

MeSH terms

  • Algorithms*
  • Artificial Intelligence
  • Feedback
  • Image Enhancement / methods*
  • Image Interpretation, Computer-Assisted / methods*
  • Information Storage and Retrieval / methods*
  • Pattern Recognition, Automated*
  • Reproducibility of Results
  • Sensitivity and Specificity
  • Signal Processing, Computer-Assisted*