| 摘要: |
| 【目的】研究应用高光谱成像技术无损检测生长发育后期苹果糖度的可行性。【方法】以生长发育后期的“富士”苹果为对象，基于采集到的波长900~1 700 nm高光谱数据，建立预测苹果糖度的偏最小二乘（PLS）、支持向量机（SVM）和极限学习机（ELM）模型，并比较主成分分析（PCA）和连续投影算法（SPA）2种数据压缩或特征波提取方法对预测模型精度的影响。【结果】采用PCA方法可将全光谱压缩至9个主成分，采用SPA从全光谱的230个波长中提取出了13个特征波长，两者相比，SPA能更有效地提高模型预测能力。预测生长发育后期苹果糖度的最佳模型为基于SPA的PLS模型，其预测集相关系数为0.945，均方根误差为0.628°Brix。【结论】高光谱图像技术可以用于生长发育后期苹果糖度的无损检测，该技术的应用将有助于指导苹果的种植和适时采收。 |
| 关键词: 高光谱成像技术 苹果糖度 无损检测 |
| DOI： |
| 分类号: |
| 基金项目:国家科技支撑计划项目（2015BAD19B03）；国家级大学生创新创业训练计划项目(201410712021) |
|
| Hyperspectral imaging based non-destructive prediction of soluble solids content in apples at late development period |
|
MENG Tianyuan,WANG Zhuanwei,CHI Qian,et al
|
| Abstract: |
| 【Objective】This study investigated the feasibility of using hyperspectral image technique to nondestructively predict soluble solids content (SSC) of apples at the late development period. 【Method】‘Fuji’ apples were used as samples to acquire hyperspectral images from 900 nm to 1 700 nm.Three prediction models,partial least squares (PLS),support vector machine (SVM) and extreme learning machine (ELM),were built.The effect of characteristic wavelength selection method of successive projections algorithm (SPA) and data compression method of principal component analysis (PCA) were compared according to model predication accuracy.【Result】Nine principal components were compressed by PCA and 13 characteristic wavelengths were selected by SPA from the full spectra (230 wavelengths).SPA improved the prediction performance effectively.The best model for SSC prediction of apples at late development period was SPA-PLS,whose correlation coefficient and root mean square error of prediction were 0.945 and 0.628 °Brix,respectively.【Conclusion】Hyperspectral imaging technique could be used as a noninvasive method for predicting SSC of apples at late development period.This technique is helpful to instruct apple planting and harvest timely. |
| Key words: hyperspectral imaging soluble solids content in apple non-destructive prediction |
