Neighbor gray levels as features in pixel classification

Narendra Ahuja, Azriel Rosenfeld, Robert M. Haralick

Research output: Contribution to journalArticlepeer-review


In segmenting an image by pixel classification, the sequence of gray levels of the pixel's neighbors can be used as a feature vector. This yields classifications at least as good as those obtained using other local properties (e.g., averages or values of difference operators) as features.

Original languageEnglish (US)
Pages (from-to)251-260
Number of pages10
JournalPattern Recognition
Issue number4
StatePublished - 1980
Externally publishedYes


  • Image Segmentation
  • Neighborhood operators
  • Pixel classification

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence


Dive into the research topics of 'Neighbor gray levels as features in pixel classification'. Together they form a unique fingerprint.

Cite this