An Adaptive Technique for Accurate Feature Extraction from Regular and Irregular Image Data

  • Sonya Coleman
  • Shanmuglingam Suganthan
  • Bryan Scotney
Conference paper

DOI: 10.1007/978-3-642-04146-4_97

Part of the Lecture Notes in Computer Science book series (LNCS, volume 5716)
Cite this paper as:
Coleman S., Suganthan S., Scotney B. (2009) An Adaptive Technique for Accurate Feature Extraction from Regular and Irregular Image Data. In: Foggia P., Sansone C., Vento M. (eds) Image Analysis and Processing – ICIAP 2009. ICIAP 2009. Lecture Notes in Computer Science, vol 5716. Springer, Berlin, Heidelberg

Abstract

We present a single multi-scale gradient-based feature extraction algorithm that can be directly applied to irregular or regular image data and hence can be used on both range and intensity images. We illustrate the accuracy of this approach using the Figure of Merit evaluation technique on real images, demonstrating that the application of this approach to both range and intensity images is more accurate than the equivalent approach of applying a gradient operator, such as Sobel, to an intensity image and, separately, the scan-line approximation approach to range images.

Keywords

Range Data Gradient Operator Feature Extraction 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Sonya Coleman
    • 1
  • Shanmuglingam Suganthan
    • 2
  • Bryan Scotney
    • 3
  1. 1.University of UlsterMageeNorthern Ireland
  2. 2.Smart Sensors LtdUniversity of Bath Innovation CentreBathUK
  3. 3.University of UlsterColeraineNorthern Ireland

Personalised recommendations