Nondestructive classification of soft rot disease in napa cabbage using hyperspectral imaging analysis

Abstract

Identification of soft rot disease in napa cabbage, an essential ingredient of kimchi, is challenging at the industrial scale. Therefore, nondestructive imaging techniques are necessary. Here, we investigated the potential of hyperspectral imaging (HSI) processing in the near-infrared region (900-1700 nm) for classifying napa cabbage quality using nondestructive measurements. We determined the microbiological and physicochemical qualitative properties of napa cabbage for intercomparison of HSI information, extracted HSI characteristics from hyperspectral images to predict and classify freshness, and established a novel approach for classifying healthy and rotten napa cabbage. The second derivative Savitzky-Golay method for data preprocessing was implemented, followed by wavelength selection using variable importance in projection scores. For multivariate data of the classification models, partial least square discriminant analysis (PLS-DA), support vector machine (SVM), and random forests were used for predicting cabbage conditions. The SVM model accurately distinguished the cabbage exhibiting soft rot disease symptoms from the healthy cabbage. This study presents the potential of HSI systems for separating soft rot disease-infected napa cabbages from healthy napa cabbages using the SVM model, especially under the most effective wavelengths (970, 980, 1180, 1070, 1120, and 978 nm), prior to processing. These results are applicable to industrial multispectral images.

Figure 1

The quantity of Pectobacterium carotovorum ssp. carotovorum cells recovered from napa cabbage (A) and water content of cabbage samples (B). Healthy napa cabbage stored at 5 °C (F1), healthy napa cabbage stored at 30 °C (F2), napa cabbage inoculated with PCC and stored at 5 °C (P1), and napa cabbage inoculated with PCC and stored at 30 °C (P2).

Figure 2

A headspace solid-phase microextraction coupled with gas chromatography–mass spectrometry (HS–SPME–GC–MS) chromatogram. (A-1) Volatile compounds in four kinds of napa cabbage samples at different conditions. The area values were obtained from values integrated from area of peaks on Total Ion Chromatogram Total Ion Chromatogram. Healthy napa cabbage stored at 5 °C (F1), healthy napa cabbage stored at 30 °C (F2), napa cabbage inoculated with PCC and stored at 5 °C (P1), and napa cabbage inoculated with PCC and stored 30 °C (P2); (A-2) a standard solution containing 2,3-butanediol; (A-3) 2,3-Butanediol in napa cabbage samples showing soft rot disease symptom.

Figure 3

The reflectance spectra of napa cabbages of all samples (A) and average spectra for different napa cabbage sample groups (F1, F2, P1, and P2) (B).

Figure 4

Significant wavelengths by the PLS-DA model, which efficiently classifies soft rot disease infection (A), and the comparison of boxplot of the top six significant relatively important wavelengths (p < 0.05) in four groups of napa cabbage samples (B).

Figure 5

Comparison of Pectobacterium carotovorum subsp. carotovorum (PCC) bacterial counts and soft rot development between healthy cabbages and PCC-inoculated cabbages under different storage temperatures after 3 days.