基于高光谱成像和凸多边形尺寸测量的冬瓜子水分及尺寸检测

摘要：冬瓜种子的含水量和尺寸对其储存、发芽和生长过程具有重要影响。适中的含水量和尺寸是种子发芽和生长的关 键因素。因此，检测冬瓜种子的含水量和尺寸有助于提高其发芽率。传统的种子含水量检测方法操作复杂，且需要进行 破坏性样品制备或化学处理。常见的尺寸测量方法也耗时耗力。高光谱成像技术能够分别获取目标表面和内部结构的信 息，可用于快速、无损地检测冬瓜种子的含水量和尺寸。本研究利用反射和透射光谱数据，建立了偏最小二乘回归（（PLSR） 和偏最小二乘支持向量机（（LSSVM）模型，以预测冬瓜种子的含水量。模型通过五种变量选择方法进行了优化。基于CARS 算法的LSSVM模型在单一反射和透射光谱中均表现出最佳性能。基于反射光谱的模型的R2 和RMSEP分别为0.9667% P 和0.0215%，而基于透射光谱的模型的R2 和RMSEP分别为0.9644%和0.0223%。在低层次数据融合中，基于CARS算 P 法的LSSVM模型也表现出最佳性能，但相较于单一模型（反射光谱或透射光谱）仅有小幅提升，R2 和RMSEP分别为 P 0.9679%和0.0212%。在中层次数据融合中，同样基于CARS算法的LSSVM模型表现出最佳性能，且模型性能进一步提 升，R2 和RMSEP分别为0.9738%和0.0191%。最后，提出了图像处理算法和凸多边形尺寸测量方法用于测量冬瓜种子 P 的尺寸。校准后的冬瓜种子长度和宽度与真实值的绝对误差小于 0.22 毫米，相对误差小于 2%。结果表明，高光谱成像 技术能够准确检测冬瓜种子的含水量。基于 CARS 算法的数据融合方法和 LSSVM 模型能够更精确地检测冬瓜种子的含 水量。图像处理算法结合凸多边形尺寸测量方法能够高效、高精度地检测冬瓜种子的尺寸。

关键词：高光谱成像技术；数据融合；凸多边形尺寸测量

期刊：Journal of Food Composition and Analysis

DOI：https://doi.org/10.1016/j.jfca.2024.106789

设备：GaiaSorter

Detection of moisture and size of winter melon seeds based on hyperspectral imaging and convex polygon size measurement

Abstract：The level of moisture content and size of winter melon seeds affect their storage, germination and growth processes. Moderate moisture and size are essential for seed germination and growth. Therefore, detecting the moisture and size of winter melon seeds is beneffcial to improve their germination rate. Traditional seed moisture testing methods are complex to operate and require destructive sample preparation or chemical treatment. Common dimensional measurement methods are also time- consuming and laborious. Hyperspectral imaging technology can acquire information about the surface and internal structure of the target separately, it can be used to quickly and non-destructively detect the moisture and size of winter melon seeds. In this study, partial least squares regression (PLSR) and partial least squares support vector machine (LSSVM) models were established to predict the moisture content of winter melon seeds by using reffection and transmittance spectral data. The models were optimized using ffve variable selection methods. The optimal performance of the LSSVM model based on the CARS algorithm was achieved in both single reffection and transmission spectra. The R2 and RMSEP of the model based on the reffection spectra were 0.9667 % P and 0.0215 %, respectively. The R2 and RMSEP of the model based on the transmission spectra were 0.9644 % and 0.0223 %, P respectively. In low-level data fusion, the LSSVM model based on the CARS algorithm also achieved optimal performance, but with only a little improvement compared to a single model (reffection spectra or transmission spectra), with R2 and RMSEP of P 0.9679 % and 0.0212 %, respectively. In the mid-level data fusion, the LSSVM model also based on the CARS algorithm achieved the optimal performance, and the performance of the model was further improved. The R2 and RMSEP of the model were 0.9738 % P and 0.0191%, respectively. Finally, the image processing algorithm and the convex polygon size measurement method was proposed to measure the size of winter melon seeds. The absolute error between the calibrated winter melon seed length and width and the true length and width was less than 0.22 mm, and the relative error was less than 2 %. The results show that hyperspectral imaging technology can accurately detect the water content of winter melon seeds. Data fusion method and LSSVM model based on CARS algorithm can detect the water content of winter melon seeds more accurately. The image processing algorithm combined with the convex polygon size measurement method can be effectively used to detect the size of winter melon seeds with high precision.

Keywords：Hyperspectral imaging technology; Data fusion; Convex polygon size measurement