ONLINE HYPERSPECTRAL LINE-SCAN FLUORESCENCE IMAGING FOR SAFETY INSPECTION OF APPLES

Authors: Kim, Moon; Chen, Yud; Cho, Byoung Kwan

Submitted to: Acta Horticulture Proceedings
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 8/13/2006
Publication Date: 5/15/2008
Citation: Kim, M.S., Chen, Y.R., Cho, B. 2008. Online hyperspectral line-scan fluorescence imaging for safety inspection of apples. Acta Horticulture Proceedings. 768:385-390.

Interpretive Summary: A scientist at the Instrumentation and Sensing Laboratory developed a rapid line-scan imaging system for safety inspection of apples. For the online inspection of apples, the line-scan imaging system was integrated with a commercial apple-sorting machine. As a major source of harmful pathogens, animal fecal contamination on fruits and vegetables presents a significant health hazard. A fluorescence sensing technique with UV-A excitation was implemented in the line-scan imaging for detection of animal fecal contamination on apples. Fluorescence images of 30 contiguous 10 nm wide spectral bands from 400 to 700 nm were acquired from samples moving at a processing sorting-line speed of three apples per second. Based on two-band fluorescence ratio, 660 nm over 530 nm, as a multispectral image fusion method, a 100% fecal spot detection rate (118 out of 118 feces treated apples) with no false positives (0 out of 120 apples, 60 wholesome and 60 apples with defects acquired prior to the feces treatment) was achieved. Presented online inspection system and methodologies are useful to food scientists, engineers, regulatory government agencies (FSIS and FDA), and food processing industries.

Technical Abstract: A recently developed fast hyperspectral line-scan imaging system integrated with a commercial apple-sorting machine was evaluated for rapid detection of animal feces matter on apples online. Golden Delicious apples obtained from a local orchard were artificially contaminated with a thin smear of cow feces. For the online trial, hyperspectral fluorescence images of 30 contiguous spectral channels from 400 to 700 nm were acquired from samples moving at a processing sorting-line speed of three apples per second. Based on fluorescence ratio as a multispectral image fusion method, a 100% detection rate (118 out of 118 feces treated apples) with no false positives (0 out of 120 apples, 60 wholesome and 60 apples with defects acquired prior to the feces treatment) was achieved.