On-line fruit grading according to external quality using machine vision.

This paper presents apple grading into four classes according to European standards. Two varieties were tested, the Golden delicious and the Jonagold. The image database included more than thousand images of fruits (528 Golden, 642 Jonagold) belonging to three categories Extra, I, II and to reject. The image grading was achieved in six steps : the image acquisition, the ground colour classification, the defect segmentation, the calyx and stem recognition, the defects characterisation and finally the fruit classification in quality classes. The proposed method for apple external quality grading showed correct classification rates of 78 and 72% respectively for Golden delicious and for Jonagold apples. Taking into account that the healthy fruits were far better graded and considering that this class was under represented, the results of the proposed method (an error rate reaching respectively 5 and 10%) are compatible with the requirements of the European standards.