Edge-enhancement postprocessing using artificial dissipation

Research output: Contribution to journalArticlepeer-review

Abstract

We present a method to enhance, by postprocessing, the performance of gradient-based edge detectors. It improves the performance of the edge detector by adding terms which are similar to the artificial dissipation that appear in the numerical solution of hyperbolic PDEs. This term is added to the output of the edge detector. The edges that are missed or blurred by the edge detector are reconstructed through the addition of the artificial dissipation terms. Edges that are detected correctly by the edge detector are preserved. We present the theory of the artificial dissipation and its improvement of the quality of the detected edges. We demonstrate the performance of the algorithm on diverse images.

Original languageEnglish
Pages (from-to)1486-1498
Number of pages13
JournalIEEE Transactions on Image Processing
Volume15
Issue number6
DOIs
StatePublished - Jun 2006

Keywords

  • Artificial dissipation
  • Canny
  • Edge detector
  • Hyperbolic partial differential equations (PDE)

Fingerprint

Dive into the research topics of 'Edge-enhancement postprocessing using artificial dissipation'. Together they form a unique fingerprint.

Cite this