Skip to main content
ARS Home » Midwest Area » East Lansing, Michigan » Sugarbeet and Bean Research » Research » Publications at this Location » Publication #220173

Title: Quality evaluation of pickling cucumbers using hyperspectral reflectance and transmittance imaging – Part 2. Performance of a prototype

Author
item ARIANA, DIWAN - USDA-FAS
item Lu, Renfu

Submitted to: Sensing and Instrumentation for Food Quality and Safety
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 6/3/2008
Publication Date: 6/27/2008
Citation: Ariana, D., Lu, R. 2008. Quality evaluation of pickling cucumbers using hyperspectral reflectance and transmittance imaging. Part 2. Performance of a prototype. Sensing and Instrumentation for Food Quality and Safety. DOI 10.1007/s11694-008-9058-9. Available: www.springerlink.com/content/r3715505p0155360/?.

Interpretive Summary: Pickling cucumbers are susceptible to internal damage (e.g., soft, hollow center) that may occur due to adverse growth condition as well as improper harvesting and postharvest handling operations. Inferior, defective pickling cucumbers would lead to inconsistent and poor quality pickled products. Hence, individual pickling cucumbers need to be inspected after harvest to ensure the quality of final pickled products. Currently, machine vision systems are being used for inspecting external characteristics (color, size and/or shape) of cucumbers; however, sorting and grading for internal quality is still a problem. This research was aimed at the development of a hyperspectral imaging prototype that is able to operate under simultaneous reflectance and transmittance modes for online sorting and grading of both external characteristics (color and size) and internal defect (soft and hollow cucumbers) on individual cucumbers. Hyperspectral imaging combines the main features of imaging and spectroscopy and thus can be advantageous over conventional imaging or spectroscopy techniques in quality inspection of horticultural products. The prototype was designed to operate at a speed of up to two fruit per second. Mathematical methods and computer algorithms were developed to process and analyze spectral images acquired from individual pickling cucumbers by the prototype under three different sensing modes (reflectance, transmittance, and their combination). Results from the two-year experiments showed that the prototype gave good predictions of fruit color and was able to correctly identify up to 99% of the defective cucumbers that had a hollow center. This research demonstrated that it is technically feasible and advantageous to use this novel hyperspectral imaging technique for online sorting and grading of pickling cucumbers for external and internal quality. The technology will provide the pickle industry a new means for inspection of cucumbers and pickled products. It could also be potentially used for sorting and grading other horticultural products.

Technical Abstract: This paper reports on the development and evaluation of methods and algorithms for detecting both external and internal quality of pickling cucumbers using the hyperspectral reflectance and transmittance images acquired by an online prototype described in a previous paper. Experiments were performed in two years on ‘Journey’ pickling cucumbers, some of which were subjected to mechanical stress to induce internal defect in seed cavity. Hyperspectral line-scan images of the ‘Journey’ pickling cucumbers were collected under reflectance, transmittance, and their combination modes. Partial least squares analysis was performed on spectra extracted from the hyperspectral line scan images to predict firmness, color, and the presence of internal defect. The system performed well on prediction of skin color (chroma and hue) with the coefficient of determination ranging between 0.75 and 0.77; however, it had poor prediction of fruit firmness. Transmittance data in the near-infrared region (675-1000 nm) provided the best detection of internal defect for the test pickling cucumbers, with the detection accuracy up to 99.0%. Up to the best four wavelength combinations were identified using linear discriminant analysis for internal defect detection. The hyperspectral imaging technique can be used for simultaneous detection of color and internal defect on cucumbers.