Automatic fruit recognition: a survey and new results using range/attenuation images

An automatic fruit recognition system and a review of previous fruit detect ion work are reported. The methodology presented is able to recognize spher ical fruits in natural conditions facing difficult situations: shadows, bri ght areas, occlusions and overlapping fruits. The sensor used is a laser ra nge-finder giving range/attenuation data of the sensed surface. The recogni tion system uses a laser range-finder model and a dual color/shape analysis algorithm to locate the fruit. The three-dimensional position of the fruit , radius and the reflectance are obtained after the recognition stages. Res ults for a set of artificial orange tree images and real-time consideration s are presented. (C) 1999 Published by Elsevier Science Ltd on behalf of th e Pattern Recognition Society. All rights reserved.