孟庆龙,尚静,杨雪,张艳.基于BP网络的苹果硬度高光谱无损检测[J].包装工程,2020,41(15):14-18.
MENG Qing-long,SHANG Jing,YANG Xue,ZHANG Yan.Nondestructive Detection for Hyperspectral Imaging of Apple Firmness Based on BP Network[J].Packaging Engineering,2020,41(15):14-18. |
| 基于BP网络的苹果硬度高光谱无损检测 |
| Nondestructive Detection for Hyperspectral Imaging of Apple Firmness Based on BP Network |
| 投稿时间：2020-01-12 修订日期：2020-08-10 |
| DOI：10.19554/j.cnki.1001-3563.2020.15.003 |
| 中文关键词: 高光谱成像 苹果 硬度 数据降维 无损检测 |
| 英文关键词: hyperspectral imaging apples firmness data mining nondestructive detection |
| 基金项目:国家自然科学基金（61505036）；贵州省科技计划（黔科合基础[2020]1Y270）；贵州省普通高等学校工程研究中心项目（黔教合KY字[2016]017）；贵阳市科学技术局-贵阳学院科技专项资金（GYU-KYZ〔2019~2020〕PT05-02）；大学生创新创业训练计划（20195200353） |
|
| 摘要点击次数: |
| 全文下载次数: |
| 中文摘要: |
| 目的 为了实现基于高光谱成像以及误差反向传播（BP）网络模型的苹果硬度快速无损检测。方法 利用高光谱成像采集系统采集采后“富士”苹果的高光谱图像，然后提取整个苹果样本区域的平均反射光谱；利用连续投影算法（SPA）和竞争性自适应重加权算法（CARS）实现对标准正态变换预处理后光谱数据的降维；研究基于全光谱以及特征光谱的预测苹果硬度BP网络模型。结果 采用SPA和CARS分别从256个全光谱中提取了18个和16个特征波长，明显提升了预测模型的运行效率，且SPA+BP网络模型具有相对较好的苹果硬度预测能力（rp=0.728，RPm=0.282 kg/cm2）。结论 研究表明基于高光谱成像技术和BP网络建立的预测模型可快速无损预测苹果的硬度。 |
| 英文摘要: |
| The work aims to realize rapid nondestructive detection of firmness of apples based on hyperspectral imaging technology and error back propagation (BP) network. The hyperspectral imaging acquisition system was used to acquire the hyperspectral images of postharvest 'Fuji' apples, and then the average reflectance spectra in the whole region of apple samples was extracted. The successive projection algorithm (SPA) and competitive adaptive reweighted sampling (CARS) method were used to conduct data mining of spectral data preprocessed by the standard normal variation. A BP network model for predicting firmness of apples based on full spectra and characteristic spectra was studied. The results showed that, 18 and 16 characteristic wavelengths were extracted by SPA and CARS from 256 full wavelengths, which obviously improved the working efficiency of prediction model. Moreover, SPA+BP network model had a relatively good prediction ability for firmness of apples (rp=0.728, RPm=0.282 kg/cm2). This study indicates that the prediction model based on hyperspectral imaging technology and BP network can be applied in the rapid nondestructive prediction of firmness of apples. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
渝公网安备 50010702501716号