论文部分内容阅读
高光谱成像技术可以用在无损检测水果品质方面。可见-近红外波段(400nm至1000nm)的光谱可以用来检测梨的可溶性固体含量(SSC)和硬度。用搭建的可见-近红外光谱范围的高光谱成像系统可以拍摄得到不同种类的梨的光谱图,再通过计算机软件提取光谱图中的有效信息进行分析。用于预测建立模型的两个品种共200个梨样品的光谱图经过连续投影算法(SPA)和多元线性回归算法(MLR)的处理分析可以建立回归模型以及回归方程来有效的预测梨的可溶性固体含量(SSC)和硬度。最终得到硬度模型的相关系数为0.923,SSC模型的相关系数为0.898。
Hyperspectral imaging can be used in nondestructive testing of fruit quality. Visible - The spectrum of the near-infrared (400 nm to 1000 nm) spectrum can be used to detect pears soluble solid content (SSC) and hardness. With the built-in visible-near-infrared spectral range hyperspectral imaging system can be obtained by shooting different types of pear spectrogram, and then extracted by computer software to analyze the effective information in the spectrogram. Spectra of a total of 200 pear samples from two cultivars used to predict model establishment. Through the analysis of the continuous projection algorithm (SPA) and multivariate linear regression (MLR) analysis, regression models and regression equations can be established to effectively predict pear soluble solids Content (SSC) and hardness. The final correlation coefficient of the hardness model was 0.923, and the correlation coefficient of the SSC model was 0.898.