Abstract Hyperspectral images integrate spatial and spectral details together. They can provide valuable information about both external physical and internal chemical characteristics of agricultural and food products rapidly and non-destructively. Despite rapid improvements in instruments and acquisition techniques, the collected high-quality hyperspectral images still contain much useless information, like uneven illumination, background, specular reflection, and bad pixels that need to be removed. That is, hyperspectral image preprocessing is necessary for almost each hyperspectral image to get pure images or pixels, or to reduce negative influences on the subsequent detection, classification, and prediction analysis. This manuscript will enumerate some possible solutions to deal with issues mentioned above before further image analyzing. The advantages and disadvantages of different methods when dealing with a specific problem are also discussed. Obtained clean images or pure signals can be used for further data analysis. Finally, post-processing of hyperspectral images can be carried out to enhance the classification result of images or to generate chemical images/distribution maps to show spatial component concentration distributions of non-homogeneous samples.

中文翻译：

---

农产品和食品高光谱图像的基本处理方法

摘要 高光谱图像将空间和光谱细节整合在一起。它们可以快速、无损地提供有关农产品和食品的外部物理和内部化学特征的宝贵信息。尽管仪器和采集技术得到了快速改进，但采集到的高质量高光谱图像仍然包含许多无用信息，如光照不均、背景、镜面反射和需要去除的坏像素等。也就是说，几乎每幅高光谱图像都需要进行高光谱图像预处理，以获得纯图像或像素，或者减少对后续检测、分类和预测分析的负面影响。在进一步的图像分析之前，这份手稿将列举一些可能的解决方案来处理上述问题。还讨论了处理特定问题时不同方法的优缺点。获得的干净图像或纯信号可用于进一步的数据分析。最后，可以对高光谱图像进行后处理以增强图像的分类结果或生成化学图像/分布图以显示非均匀样本的空间分量浓度分布。