Faculty of Agriculture, Shimane University
ISSN:0370-940X
number of downloads : ?
Use this link to cite this item : https://ir.lib.shimane-u.ac.jp/2034
Bulletin of the Faculty of Agriculture, Shimane University 26
1992-12-21 発行
画像処理システムによる青果物の傷検出に関する研究(I) : モモ損傷の検出
Study on Damage Fruit Inspection by Machine Vision : Detection of Peach Defects
Iwao, Toshio
Li, Xiao Ming
Fujiura, Tateshi
Shibusawa, Sakae
Takeyama, Kouichi
Mohri, Kentaro
Endo, Junji
File
Description
The object of this study is for developing defective fruit inspection system by machine vision. Spectral reflectances of the normal peach surface and defects were measured in the wavelength between 390nm and 2000nm.
The report deals with a trial of developing an image analysis algorithms based on NTSC r, g, b chromaticity in color image and the gray level of infrared image to indentify defects.
The image data was filtered to removed interferance due to pixel to pixel variation in the camera and back ground noise, and then, the defect parts were separated from the rest by a threshold.
As the result, it was admitted that the defects such as compression, cut, insect pest, bruise and etc. could be separated from normal peach surface by chromatic cluster of the color image or gray level of the infrared image.
The report deals with a trial of developing an image analysis algorithms based on NTSC r, g, b chromaticity in color image and the gray level of infrared image to indentify defects.
The image data was filtered to removed interferance due to pixel to pixel variation in the camera and back ground noise, and then, the defect parts were separated from the rest by a threshold.
As the result, it was admitted that the defects such as compression, cut, insect pest, bruise and etc. could be separated from normal peach surface by chromatic cluster of the color image or gray level of the infrared image.
About This Article
NCID
AN00108015
Other Article
PP. 21 - 26