Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Image Processing in Automated Pattern Classification of Oranges

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan

Citation:  Pp. 56-61 in Proceedings of the World Congress of Computers in Agriculture and Natural Resources (13-15, March 2002, Iguacu Falls, Brazil)  701P0301.(doi:10.13031/2013.8312)
Authors:   P. E. Cruvinel and E. R. Minatel
Keywords:   Machine Vision, Agricultural Instrumentation, Orange Measurement

A rapid method for automated classification of oranges in living trees by size has been developed. It is based on image processing with correlation analysis in the frequency domain. This technique has the advantage of being a direct measurement method that automatically identifies and counts oranges for quality control. Calibration was performed using standard image with known orange sizes. Oranges sizes, ranging from less then 2 cm to over 10 cm in diameter have been automatically recognized and successfully measured. Error was not larger than 1.4%. In addition, practical examples of use of the method for determining characteristics of oranges are presented.

(Download PDF)    (Export to EndNotes)