Improving junction detection by semantic interpretation

Kalkan S. , Shi Y., Pilz F., Kruger N.

Proceedings of the Second International Conference on Computer Vision Theory and Applications , Barcelona, Spain, 8 - 11 March 2007, pp.264-271

  • Publication Type: Conference Paper / Full Text
  • City: Barcelona
  • Country: Spain
  • Page Numbers: pp.264-271


Every junction detector has a set of thresholds to make decisions about the junctionness of image points. Low-contrast junctions may pass such thresholds and may not be detected. Lowering the thresholds to find such junctions will lead to spurious junction detections at other image points. In this paper, we implement a junction-regularity measure to improve localization of junctions, and we develop a method to create semantic interpretations of arbitrary junction configurations at improved junction positions. We propose to utilize such a semantic interpretation as a feedback mechanism to filter false-positive junctions. We show results of our proposals on natural images using Harris and SUSAN operators as well as a continuous concept of intrinsic dimensionality.