A Low-Cost Color Vision System for Automatic Estimation of Apple Fruit Orientation and Maximum Equatorial Diameter

摘要

The overall objective of this research was to develop an in-field presorting and grading system to separate undersized and defective fruit from fresh market-grade apples. To achieve this goal, a cost-effective machine vision inspection prototype was built, which consisted of a low-cost color camera, LED lights, and a generic bi-cone conveyor. Algorithms were developed for accurate estimation of pixels per unit dimension from images acquired under the close-range imaging configuration and for real-time estimation of apple orientation, shape, and maximum equatorial diameter. The machine vision system was tested and evaluated for 'Delicious' (D), 'Empire' (EM), 'Golden Delicious' (GD), and 'Jonagold' (JG) apples at a speed of four fruit per second. Thevariable pixels per unit dimension method achieved superior results for area estimation, compared to the conventional image distortion correction and area estimation methods. The orientation estimation algorithm had 87.6% and 86.2% accuracies for D andGD apples, respectively, within +20° of actual fruit orientation, but it performed less satisfactorily for round-shaped EM and JG apples. The machine vision system achieved good fruit maximum equatorial diameter estimations, with an overall root mean squared error of 1.79 mm for the four varieties of apple, and it had a two-size grading error of 4.3%, versus 15.1% by a mechanical sizing machine. The system provides a cost-effective means for sorting apples for size.