The Proceedings of JSME annual Conference on Robotics and Mechatronics (Robomec)
Online ISSN : 2424-3124
2008
Session ID : 2A1-B07
Conference information
2A1-B07 A Machine Vision System for Citrus Fruit Grading and for Rotten Part Detection
Mitsutaka KURITANaoshi KONDOTakahisa NISHIZUMakoto KURAMOTOYuichi OGAWAKazuya YAMAMOTOYoshihide MINAMI
Author information
CONFERENCE PROCEEDINGS FREE ACCESS

Details
Abstract
There are many types of orange fruit grading machines with machine vision systems, but it is still difficult to detect rotten parts, because their colors are similar with normal parts. Objectives of this research are to investigate the excitation wavelengths of the substances for determination of lighting device specification, and to construct an inspection system for fruit grading by color image and for the rotten part detection by UV lighting device. From an analysis of orange fruit skins, it was found one of major fluorescent substances was flavonoid methyl whose exciting wavelength was 365nm and fluorescence wavelength was about 530nm. A machine vision system consisting of a pair of white and UV LED lighting devices and a color CCD camera was proposed for orange fruit grading. Since the time between color and fluorescence image inputs was short enough (14ms), it was considered that UV LEDs addition to white LEDs-color TV camera system installed in fruit grading lines made rotten fruit detection possible.
Content from these authors
© 2008 The Japan Society of Mechanical Engineers
Previous article Next article
feedback
Top