Detection of internal defect in pickling cucumbers using hyperspectral transmittance imaging.

摘要

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 cv. Journey and Vlaspik cucumbers over a 6-day period after they were subjected to mechanical stress. Partial least squares discriminant analysis (PLS-DA) was performed on mean and s.d. spectra extracted from 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. 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-IR 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 cv. Journey, Vlaspik and pooled data, respectively. Results suggest that hyperspectral transmittance imaging can be used for rapid detection of internal defects in pickling cucumbers.