Location: Sugarbeet and Bean Research
Title: Development of a Hyperspectral Imaging System for Online Quality Inspection of Pickling Cucumbers Authors
|Ariana, Diwan - MICHIGAN ST UNIVERSITY|
Submitted to: ASABE Food Processing Automation Conference
Publication Type: Proceedings
Publication Acceptance Date: May 30, 2008
Publication Date: June 28, 2008
Citation: Lu, R., Ariana, D. 2008. Development of a Hyperspectral Imaging System for Online Quality Inspection of Pickling Cucumbers. In: Proceedings of the ASABE Food Processing Automation Conference, June 28-29, 2008, Providence, Rhode Island. 2008 CDROM. Technical Abstract: This paper reports on the development of a hyperspectral imaging prototype for evaluation of external and internal quality of pickling cucumbers. The prototype consisted of a two-lane round belt conveyor, two illumination sources (one for reflectance and one for transmittance), and a hyperspectral imaging unit. It had a novel feature of simultaneous imaging under reflectance mode covering the visible region of 400-675 nm and transmittance mode for 675-1000 nm, coupled with real-time, continuous calibration of reflectance and transmittance images for each cucumber using inline reference standards. Reflectance information was used for evaluating the external characteristics of cucumbers (i.e., skin color), whereas transmittance information was intended for internal defect detection (hollow center). The prototype was tested on ‘Journey’ pickling cucumbers harvested in 2006 and 2007 for predicting skin and flesh color, flesh firmness, and internal defect. Hyperspectral images were processed to extract spectral information for individual cucumbers, and partial least squares analysis was performed to predict flesh firmness, skin and flesh color, and the presence of internal defect. The prototype performed relatively well in predicting skin color (chroma and hue) with the coefficient of determination ranging between 0.67 and 0.79; however, it had poor prediction of flesh color and firmness. Transmittance data in the spectral region of 675-1000 nm provided excellent detection of internal defect for the test pickling cucumbers, with the detection accuracy being greater than 90%. The hyperspectral imaging technique would be useful for online inspection of surface color and internal defect on picking cucumbers.