Chapter 6: Feature detection in scale-space

Chapter 6 in Scale-Space Theory in Computer Vision shows how the methodology for discrete derivative approximations proposed in chapter 5 leads to a conceptually simple scheme of computations for multi-scale low-level feature extraction, consisting of four basic steps;
  • large support convolution smoothing,
  • small support difference computations,
  • point operations for computing differential geometric entities, and
  • nearest neighbour operations for feature detection.
Applications are given demonstrating how the proposed scheme can be used for edge detection and junction detection based on derivatives up to order three.
Responsible for this page: Tony Lindeberg