Nondestructive Cucumber Quality Evaluation System Using Machine Vision


Article Preview

This study was aimed at developing a new quality evaluation system for classifying the cucumber based on its length and curvature, and removing the taper and dumbbell shaped cucumbers using the thickness changes. Especially machine vision technique was used in carrying out field application. The cucumber image was obtained from a frame grabber, and the image was improved by minimizing the nonuniform illumination and image blurring due to line movement. From the obtained image, background was separated from the original image, and cucumber length and curvature was calculated after thinning and post-processing operation. After thinning operation, cucumber region was sliced and the thickness was calculated. From the thickness calculation, cucumber can be classified as straight, cudgel and dumbbell shape. The classification rate for bowing was close to 100%. The overall average recognition rate for good, dumbbell and cudgel cucumber fruits was 90.7%



Key Engineering Materials (Volumes 321-323)

Edited by:

Seung-Seok Lee, Joon Hyun Lee, Ik Keun Park, Sung-Jin Song, Man Yong Choi






S. W. Kang et al., "Nondestructive Cucumber Quality Evaluation System Using Machine Vision", Key Engineering Materials, Vols. 321-323, pp. 1205-1208, 2006

Online since:

October 2006




In order to see related information, you need to Login.

In order to see related information, you need to Login.