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

SA Coleman, S Suganthan, BW Scotney

Research output: Chapter in Book/Report/Conference proceedingConference contribution


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.
Original languageEnglish
Title of host publicationUnknown Host Publication
Number of pages9
Publication statusPublished - Sep 2009
Event15th International Conference on Image Analysis and Processing (ICIAP 2009) - Vietri sul Mare, Italy
Duration: 1 Sep 2009 → …


Conference15th International Conference on Image Analysis and Processing (ICIAP 2009)
Period1/09/09 → …



  • Range Data
  • Gradient Operator
  • Feature Extraction

Cite this