Hyperspectral near-infrared imaging for the detection of physical damages of pear

详细信息    查看全文

• 作者：Wang-Hee Lee^a ; Moon S. Kim^b ; Hoonsoo Lee^a ; Stephen R. Delwiche^c ; Hanhong Bae^d ; Dae-Yong Kim^a ; Byoung-Kwan Cho^a ; ^{chobk@cnu.ac.kr" class="auth_mail}
• 关键词：Hyperspectral imaging ; F-value classification algorithm ; Image processing ; Near infrared spectrum ; Pear bruise
• 刊名：Journal of Food Engineering
• 出版年：June, 2014
• 年：2014
• 卷：130
• 期：Complete
• 页码：1-7
• 全文大小：1194 K

文摘

Bruise damage on pears is one of the most crucial internal quality factors, which needs to be detected in postharvest quality sorting processes. Near-infrared imaging techniques (NIR) have effective potentials for identifying and detecting bruises since bruises result in the rupture of internal cell walls due to defects on agricultural materials. In this study, a novel NIR technique, hyperspectral imaging with beyond NIR range of 950-1650 nm, was investigated for detecting bruise damages underneath the pear skin, which has never been examined in the past. A classification algorithm based on F-value was applied for analysis of image to find the optimal waveband ratio for the discrimination of bruises against sound surface. The result demonstrated that the best threshold waveband ratio detected bruises with the accuracy of 92%, illustrating that the hyperspectral infra-red imaging technique with the region beyond NIR could be a potential detection method for pear bruises.