African Journal of
Agricultural Research

  • Abbreviation: Afr. J. Agric. Res.
  • Language: English
  • ISSN: 1991-637X
  • DOI: 10.5897/AJAR
  • Start Year: 2006
  • Published Articles: 6693

Full Length Research Paper

Potato surface defect detection in machine vision system

Hassankhani R1*, Navid H1 and Seyedarabi H2
1Department of Agricultural Machinery, University of Tabriz, Tabriz, Iran. 2Department of Telecommunication, Faculty of Electrical and Computer Engineering, University of Tabriz, Tabriz, Iran.
Email: [email protected]

  •  Accepted: 21 December 2011
  •  Published: 04 February 2012


Potato is cultivated as a major food resource in some countries that have moderate climate. Potato is sensitive to many diseases. Sorting is necessary for decreasing the transfer rate of diseases and preparing favourite conditions. Grading with workers has disadvantages such as: instability, time needed and its expensive, to solve these problems, use of machine vision system is necessary. 90 Agria potatoes were prepared. The potatoes were graded to 6 classes with 15 samples that they were: healthy, cracked, rhizoctonia fouled, cutting, rotting and greening. The samples were placed in lighting chamber and images of them were captured by means of a CCD camera. The images were transferred to a personal computer by a frame grabber. These images were analyzed by MATLAB software. For different defect sorting had been used a compound of colour and physical properties of defects. Sorting accuracy was 97.67%.
Key words: Colour analysis, physical properties, potatoes, sorting, surface defects.