Peng Hehuan, Zhang Chang, Sun Zhizhong, Sun Tong, Hu Dong, Yang Zidong, Wang Jinshuang
College of Optical, Mechanical and Electrical Engineering, Zhejiang A&F University, Hangzhou, China.
Office of Educational Administration, Zhejiang A&F University, Hangzhou, China.
Front Plant Sci. 2022 Apr 25;13:873065. doi: 10.3389/fpls.2022.873065. eCollection 2022.
This paper reports on the measurement of optical property mapping of apples at the wavelengths of 460, 527, 630, and 710 nm using spatial-frequency domain imaging (SFDI) technique, for assessing the soluble solid content (SSC), firmness, and color parameters. A laboratory-based multispectral SFDI system was developed for acquiring SFDI of 140 "Golden Delicious" apples, from which absorption coefficient ( ) and reduced scattering coefficient () mappings were quantitatively determined using the three-phase demodulation coupled with curve-fitting method. There was no noticeable spatial variation in the optical property mapping based on the resulting effect of different sizes of the region of interest (ROI) on the average optical properties. Support vector machine (SVM), multiple linear regression (MLR), and partial least square (PLS) models were developed based on , and their combinations ( × and ) for predicting apple qualities, among which SVM outperformed the best. Better prediction results for quality parameters based on the were observed than those based on the , and the combinations further improved the prediction performance, compared to the individual or . The best prediction models for SSC and firmness parameters [slope, flesh firmness (FF), and maximum force (Max.F)] were achieved based on the × , whereas those for color parameters of b* and C* were based on the , with the correlation coefficients of prediction as 0.66, 0.68, 0.73, 0.79, 0.86, and 0.86, respectively.
本文报道了使用空间频域成像（SFDI）技术在460、527、630和710nm波长下对苹果光学特性映射的测量，以评估可溶性固形物含量（SSC）、硬度和颜色参数。开发了一种基于实验室的多光谱SFDI系统，用于获取140个“金冠”苹果的SFDI，通过三相解调结合曲线拟合方法定量确定吸收系数（ ）和约化散射系数（ ）映射。基于不同大小的感兴趣区域（ROI）对平均光学特性的影响，光学特性映射中没有明显的空间变化。基于 、 及其组合（ × 和 ）开发了支持向量机（SVM）、多元线性回归（MLR）和偏最小二乘（PLS）模型来预测苹果品质，其中SVM表现最佳。观察到基于 的品质参数预测结果优于基于 的结果，并且与单独的 或 相比，组合进一步提高了预测性能。基于 × 获得了SSC和硬度参数[斜率、果肉硬度（FF）和最大力（Max.F）]的最佳预测模型，而b和C颜色参数的最佳预测模型基于 ，预测相关系数分别为0.66、0.68、0.73、0.79、0.86和0.86。
