EURASIP Journal on Advances in Signal Processing
Volume 2008 (2008), Article ID 287061, 13 pages
doi:10.1155/2008/287061
Research Article

Feature Point Detection Utilizing the Empirical Mode Decomposition

Jesmin Farzana Khan,1 Kenneth Barner,2 and Reza Adhami1

1Department of Electrical and Computer Engineering, University of Alabama in Huntsville, Huntsville, AL 35899, USA
2Department of Electrical and Computer Engineering, University of Delaware, Delaware, DE 19716, USA

Received 22 June 2007; Revised 18 January 2008; Accepted 3 March 2008

Academic Editor: Ray Zhang

Copyright © 2008 Jesmin Farzana Khan et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

This paper introduces a novel contour-based method for detecting largely affine invariant interest or feature points. In the first step, image edges are detected by morphological operators, followed by edge thinning. In the second step, corner or feature points are identified based on the local curvature of the edges. The main contribution of this work is the selection of good discriminative feature points from the thinned edges based on the 1D empirical mode decomposition (EMD). Simulation results compare the proposed method with five existing approaches that yield good results. The suggested contour-based technique detects almost all the true feature points of an image. Repeatability rate, which evaluates the geometric stability under different transformations, is employed as the performance evaluation criterion. The results show that the performance of the proposed method compares favorably against the existing well-known methods.