Skip to main content
ARS Home » Northeast Area » Beltsville, Maryland (BARC) » Beltsville Agricultural Research Center » Environmental Microbial & Food Safety Laboratory » Research » Publications at this Location » Publication #331607
Research Project: Sensing Technologies for the Detection and Characterization of Microbial, Chemical, and Biological Contaminants in Foods

Location: Environmental Microbial & Food Safety Laboratory

Title: On-line fresh-cut lettuce quality measurement system using hyperspectral imaging

Author
item MO, CHANGYEUN - Korean Rural Development Administration
item KIM, KIYOUNG - Korean Rural Development Administration
item Kim, Moon
item LIM, JONGGUK - Korean Rural Development Administration
item LEE, KANGJIN - Korean Rural Development Administration
item LEE, WANG-HEE - Chungnam National University
item CHO, BYOUNG-KWAN - Chungnam National University

Submitted to: Biosystems Engineering
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 1/17/2017
Publication Date: 2/21/2017
Citation: Mo, C., Kim, K., Kim, M.S., Lim, J., Lee, K., Lee, W., Cho, B. 2017. On-line fresh-cut lettuce quality measurement system using hyperspectral imaging. Biosystems Engineering. 156:38-50.

Interpretive Summary: In this study, a recently developed whole-surface online produce inspection system based on hyperspectral imaging techniques was evaluated for detection of foreign materials on both surfaces of fresh-cut lettuce. The main sensing component of the online system utilized a hyperspectral imaging camera in the range of 400 to 1000 nm. Spectral algorithms were developed for the online system to detect slugs and worms on the lettuce surfaces. After determining two optimal wavebands for discriminating between contaminants and lettuce surfaces, a ratio imaging algorithm was developed that allowed contaminant classification accuracy, sensitivity, and specificity rates of 99.5%, 100.0%, and 99.0%, respectively. The prototype whole-surface online inspection techniques presented in this research can potentially be used to simultaneously discriminate foreign substances on fresh-cut lettuce and will benefit the fresh-produce-processing industries.

Technical Abstract: Lettuce, which is a main type of fresh-cut vegetable, has been used in various fresh-cut products. In this study, an online quality measurement system for detecting foreign substances on the fresh-cut lettuce was developed using hyperspectral reflectance imaging. The online detection system with a single hyperspectral camera in the range of 400 to 1000 nm was capable to detect defects on both surfaces of fresh-cut lettuce. Algorithms were developed for this system to detect defects such as slugs and worms. The optimal wavebands for discriminating between defects and sound lettuce as well as between defects and the conveyor belt were investigated using the one-way analysis of variance (ANOVA) method. The subtraction imaging (SI) algorithm to classify slugs resulted in a classification accuracy of 97.5%, sensitivity of 98.0%, and specificity of 97.0%. The ratio imaging (RI) algorithm to discriminate worms achieved classification accuracy, sensitivity, and specificity rates of 99.5%, 100.0%, and 99.0%, respectively. The overall results suggest that the online quality measurement system using hyperspectral reflectance imaging could potentially be used to simultaneously discriminate foreign substances on fresh-cut lettuces.