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.

Development of Automatic Sorting System for Green Pepper Using Machine Vision

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

Citation:  2007 ASAE Annual Meeting  076106.(doi:10.13031/2013.23330)
Authors:   Nam-Hong Cho, Dong-Il Chang, Soo-Hee Lee, Hak-jin Kim, Young-Hee Lee
Keywords:   Green pepper, machine vision system, on-line grading algorithm, length, flexure

Abstract Production of green pepper in Korea has increased due to customer's preference and a projected ten-year boom. This study was carried out to develop an automatic grading system for green pepper using machine vision. The system consisted of three main components - a feeding and individuation mechanism, an image inspection and processing system, and a discharging system. The green peppers were separately fed into the machine vision system by a vibration motion and a velocity difference transport provided by a bowl feeder and a belt conveyor, respectively. Images were taken using a CCD camera and a color frame grabber. Using an on-line grading algorithm developed with Visual C/C++, the green peppers could be graded into four classes (large, medium, small sizes, and high curved shape), based on the measurement of two geometric parameters (length and flexure), by automatically activating air nozzles located at each container of different grades in the discharging system. The first derivative of thickness profile was used as a parameter to remove the stem area of segmented image of each pepper. At a sorting speed of 0.45 m/s, the grading accuracies for large, medium and small peppers were 86.0, 81.3 and 90.6 %, respectively. The system provided the performance capability of 121 kg/hr, which is about five times higher than that obtained with conventional manual sorting operations. The prototype system was economically feasible to sort green peppers by showing a cost reduction of about 40 %.

(Download PDF)    (Export to EndNotes)