Skip to main content
ARS Home » Midwest Area » East Lansing, Michigan » Sugarbeet and Bean Research » Research » Publications at this Location » Publication #359793

Research Project: Nondestructive Quality Assessment and Grading of Fruits and Vegetables

Location: Sugarbeet and Bean Research

Title: Defect detection of pickling cucumbers using emerging optical imaging techniques

item LU, YUZHEN - Michigan State University
item Lu, Renfu

Submitted to: Michigan State University Cucumber Reporting Session
Publication Type: Experiment Station
Publication Acceptance Date: 11/29/2018
Publication Date: N/A
Citation: N/A

Interpretive Summary:

Technical Abstract: Pickling cucumbers are susceptible to mechanical and chilling injuries during harvest and postharvest refrigerated storage. It is thus desirable to sort out the injured fruit before they are marketed as fresh products or processed as pickles at the processing plant. Structured-illumination reflectance imaging (SIRI) and chlorophyll fluorescence imaging (CFI) are two emerging optical imaging techniques in food quality and safety inspection. In this study, SIRI and CFI were utilized to detect bruising and chilling injury (CI) in fresh pickling cucumbers. In SIRI, two set of images, direct component (DC) and amplitude component (AC), were acquired at 740 nm; AC was found more effective than DC for ascertaining subsurface tissue bruises. Classification models based on support vector machine (SVM) were built using extracted image features, to classify cucumbers into bruised and normal classes. The highest classification accuracy of 91% was achieved by the combination of DC, AC and their ratio (AC/DC) images. Chlorophyll fluorescence images at 675 nm and 750 nm were effective for detecting CI, even for slight visual symptoms. The two-class SVM model built for classifying cucumbers into chill-injured and normal classes achieved an overall accuracy of 97%, while the three-class SVM model, in which chill-injured cucumbers were further divided into mild and severe classes, resulted in six percentage point accuracy reduction. This study demonstrated that SIRI and CFI can provide an effective means for defect detection of pickling cucumbers. More research is, however, needed to implement the two technologies for real-time inspection of cucumber defects.