Image-processing algorithms for tomato classification

Shachar Laykin, Victor Alchanatis, Elazar Fallik, Yael Edan

Research output: Contribution to journalArticlepeer-review

62 Scopus citations


Image-processing algorithms were developed and implemented to provide the following quality parameters for tomato classification: color, color homogeneity, defects, shape, and stem detection. The vision system consisted of two parts: a bottom vision cell with one camera facing upwards, and an upper vision cell with two cameras viewing the fruit at 60°. The bottom vision cell determined fruit stem and shape. The upper vision cell determined fruit color, defects, and color homogeneity. Experiments resulted in 90% correct bruise classification with 2% severely misclassified; 90% correct color homogeneity classification; 92% correct color detection with 2% severely misclassified, and 100% stem detection.

Original languageEnglish
Pages (from-to)851-858
Number of pages8
JournalTransactions of the ASABE
Issue number3
StatePublished - 1 May 2002


  • Classification
  • Image processing
  • Machine vision
  • Tomatoes


Dive into the research topics of 'Image-processing algorithms for tomato classification'. Together they form a unique fingerprint.

Cite this