Abstract
Internal quality is an important aspect in the quality control and assurance of pickled products. A rapid and nondestructive method for internal defect detection would be of value to the pickle industry. A hyperspectral transmittance imaging technique was developed to detect internal defect in the form of carpel suture separation or hollow cucumbers resulting from dropping and rolling under load. Hyperspectral transmittance line scan images were collected from 'Journey' and 'Vlaspik' cucumbers over the six-day period after they were subjected to mechanical stress. Partial least squares discriminant analysis (PLS-DA) was performed on mean and standard deviation spectra extracted from the hyperspectral transmittance images to classify cucumber samples into defective or normal classes. A spectral-based pixel classification method using Euclidean distance was applied to classify pixels along the spatial dimension of the image into normal or defective class. The transmittance spectra of defective cucumbers were similar in shape to, but higher in magnitude than, those of normal cucumbers. Transmittance values for both defective and normal cucumbers were higher in the near-infrared range of 700-1000 nm than those in the visible range (450-700 nm). Average classification accuracies of 90.2%, 98.7%, and 95.4% were achieved using PLS-DA, whereas accuracies of 89.1%, 94.6%, and 90.5% were achieved using the spectral-based pixel classification method for Journey, Vlaspik, and the pooled data, respectively. The hyperspectral transmittance imaging technique can be used for rapid detection of internal defect in pickling cucumbers.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have