Scale Detection and Region Extraction from a Scale-Space Primal Sketch

Tony Lindeberg and Jan-Olof Eklundh

Technical report ISRN KTH/NA/P--90/13--SE.

Shortened version in Proc. 3rd International Conference on Computer Vision, (Osaka, Japan), pages 416--426, Dec. 1990.


We present:
  • A multi-scale representation of grey-level shape, called scale-space primal sketch, which makes explicit both features in scale-space and the relations between features at different levels of scale.
  • A theory for extraction of significant image structure from this representation.
  • Applications to edge detection, histogram analysis and junction classification demonstrating how the proposed method can be used for guiding later stage processing.
The representation gives a qualitative description of the image structure that allows for detection of stable scales and regions of interest in a solely bottom-up data-driven way. In other words, it generates coarse segmentation cues and can be hence seen as preceding further processing, which can then be properly tuned. We argue that once such information is available many other processing tasks can become much simpler. Experiments on real imagery demonstrate that the proposed theory gives perceptually intuitive results.

PDF: (4.0 Mb)

Extension: (Abstract and PostScript)

Tony Lindeberg