Sodium pyrosulfite is a browning inhibitor used for the storage of fresh-cut potato slices. Excessive use of sodium pyrosulfite can lead to sulfur dioxide residue, which is harmful for the human body. The sulfur dioxide residue on the surface of fresh-cut potato slices immersed in different concentrations of sodium pyrosulfite solution was classified by near-infrared hyperspectral imaging (NIR-HSI) system and portable near-infrared (NIR) spectrometer. Principal component analysis was used to analyze the object-wise spectra, and support vector machine (SVM) model was established. The classification accuracy of calibration set and prediction set were 98.75% and 95%, respectively. Savitzky–Golay algorithm was used to recognize the important wavelengths, and SVM model was established based on the recognized important wavelengths. The final classification accuracy was slightly less than that based on the full spectra. In addition, the pixel-wise spectra extracted from NIR-HSI system could realize the visualization of different samples, and intuitively reflect the differences among the samples. The results showed that it was feasible to classify the sulfur dioxide residue on the surface of fresh-cut potato slices immersed in different concentration of sodium pyrosulfite solution by NIR spectra. It provided an alternative method for the detection of sulfur dioxide residue on the surface of fresh-cut potato slices.

中文翻译：

---

近红外高光谱成像系统和便携式近红外光谱仪检测鲜切马铃薯片表面二氧化亚硫酸残留

焦亚硫酸钠是一种褐变抑制剂，用于储存鲜切土豆片。过量使用焦亚硫酸钠会导致二氧化硫残留，对人体有害。采用近红外高光谱成像（NIR-HSI）系统和便携式近红外（NIR）光谱仪对浸在不同浓度焦亚硫酸钠溶液中的鲜切马铃薯片表面二氧化硫残留进行分类。主成分分析用于分析object-wise 光谱，并建立支持向量机（SVM）模型。校准集和预测集的分类准确率分别为98.75%和95%。采用Savitzky-Golay算法识别重要波长，并根据识别出的重要波长建立SVM模型。最终分类精度略低于基于全光谱的分类精度。此外，从NIR-HSI系统提取的像素级光谱可以实现不同样品的可视化，直观地反映样品之间的差异。结果表明，利用近红外光谱对浸在不同浓度焦亚硫酸钠溶液中的鲜切马铃薯片表面二氧化硫残留进行分类是可行的。为鲜切马铃薯切片表面二氧化硫残留的检测提供了一种替代方法。结果表明，利用近红外光谱对浸在不同浓度焦亚硫酸钠溶液中的鲜切马铃薯片表面二氧化硫残留进行分类是可行的。为鲜切马铃薯切片表面二氧化硫残留的检测提供了一种替代方法。结果表明，利用近红外光谱对浸在不同浓度焦亚硫酸钠溶液中的鲜切马铃薯片表面二氧化硫残留进行分类是可行的。为鲜切马铃薯切片表面二氧化硫残留的检测提供了一种替代方法。