Symbolic pixel labeling for curvilinear feature detection

John Canning, J. John Kim, Nathan Netanyahu, Azriel Rosenfeld

Research output: Contribution to journalArticlepeer-review

10 Scopus citations


This paper describes a method of detecting thin curvilinear features in an image based on a detailed analysis of the local gray level patterns at each pixel. This allows operations such as thinning and gap filling to be based on more accurate information.

Original languageEnglish
Pages (from-to)299-310
Number of pages12
JournalPattern Recognition Letters
Issue number5
StatePublished - Dec 1988
Externally publishedYes

Bibliographical note

Funding Information:
The support of the Defense Mapping Agency under Contract DMA 85 C 0007 is gratefully acknowledged, as is the help of Sandy German in preparing this paper.


  • curve detection
  • line detection
  • pixel labeling


Dive into the research topics of 'Symbolic pixel labeling for curvilinear feature detection'. Together they form a unique fingerprint.

Cite this