|Ariana, Diwan - FAS|
Submitted to: Pickle Packers International Meeting Proceedings
Publication Type: Abstract Only
Publication Acceptance Date: October 3, 2005
Publication Date: October 25, 2005
Citation: Lu, R., Ariana, D. 2005. Near-infrared hyperspectral imaging for detection of mechanical injury on pickling cucumbers. Pickle Packers International Meeting Proceedings. Technical Abstract: Mechanical harvesting and subsequent transport and handling contribute greatly to the occurrence of mechanical injuries on and/or in cucumber fruit. These injuries are cumulative thus care should be taken during these operations to minimize losses due to bruising. Severely injured fruit are easily identified visually and can be discarded during the sorting/inspection process. However, mechanical injury often causes physical damage to cucumber fruit that is difficult to detect by the human inspector or a machine vision system, which can lead to carpel separation and bloating in brine-stock cucumbers. To overcome the problem, a non-destructive method was developed for detecting mechanical injury on pickling cucumbers. A near-infrared hyperspectral imaging system was assembled and used to capture both spatial and spectral information from cucumbers in the spectral region of 950 – 1700 nm. The system consisted of an imaging spectrograph attached to an InGaAs camera and line-light fiber bundles as an illumination source. Freshly harvested cucumber samples were subjected to two forms of mechanical loading, dropping and rolling, to simulate stress caused by mechanical harvesting. Hyperspectral images were acquired from the cucumbers over time periods of 0, 1, 2, 3, and 6 days after mechanical stress. Image processing algorithms were developed to separate normal and mechanically injured cucumbers. Results showed that reflectance from normal or non-bruised cucumbers was consistently higher than that from bruised cucumbers. The hyperspectral imaging system effectively detected all mechanically injured cucumbers immediately after they were bruised. One day after bruising, the detection accuracy for bruised cucumbers was 87%, and it was lower as time progressed. Lower detection accuracies for the prolonged times after bruising were attributed to the self-curing of the bruised tissue after mechanical injury. This research demonstrated that hyperspectral imaging is useful for detecting mechanical injury on pickling cucumbers.