基于计算机视觉和嗅觉的菠菜叶绿素含量检测方法研究

发布时间：2018-02-10 14:32

本文关键词： 菠菜计算机视觉电子鼻融合技术人工神经网络叶绿素　出处：《现代食品科技》2017年05期 　论文类型：期刊论文

【摘要】：以叶绿素含量为评价菠菜新鲜度的参考指标,开发菠菜采后品质无损检测方法。采用计算机视觉和电子鼻分别获取储藏期内菠菜的图像和气味信息。分别提取视觉、嗅觉信息的主成分作为模型的输入,以叶绿素含量的化学检测值作为模型的输出,采用误差反向传播神经网络建立菠菜叶绿素的定量预测模型。试验显示,以视觉信息为输入量的模型测试结果:训练集和测试集的均方根误差(RMSE)分别为0.1978 mg/g和0.2147 mg/g,相关系数(R)分别为0.8457和0.7995。以电子鼻信息为输入量的模型测试结果:训练、测试集的RMSE分别为0.3119 mg/g和0.3032 mg/g,R分别为0.7013和0.6905。以视觉和嗅觉融合信息为输入量的模型测试结果:训练、测试集的RMSE分别为0.1759 mg/g和0.2121 mg/g,R分别为0.8888和0.8736,精度比两个单一技术均有所提高。研究表明,利用计算机视觉和电子鼻技术预测菠菜叶绿素含量的方法是可行的,采用融合技术有助于提升模型的预测精度。
[Abstract]:Using chlorophyll content as the reference index to evaluate the freshness of spinach, a nondestructive testing method of spinach quality after harvest was developed. The images and smell information of spinach during storage period were obtained by computer vision and electronic nose, respectively. The principal component of olfactory information was used as the input of the model, the chemical detection value of chlorophyll content was taken as the output of the model, and the quantitative prediction model of spinach chlorophyll was established by using the error back-propagation neural network. The RMSE of training set and test set were 0.1978 mg/g and 0.2147 mg / g, the correlation coefficient was 0.8457 and 0.7995 respectively. The RMSE of the test set was 0.3119 mg/g and 0.3032 mg / g / g, respectively 0.7013 and 0.6905.The model test results with visual and olfactory fusion information as input: training, The RMSE of the test set was 0.1759 mg/g and 0.2121 mg / g / g, respectively, which were 0.8888 and 0.8736, respectively, which were higher than those of two single techniques. The results showed that the method of predicting chlorophyll content in spinach by computer vision and electronic nose was feasible. The fusion technique is helpful to improve the prediction accuracy of the model.
【作者单位】：江苏大学食品与生物工程学院;
【基金】：江苏省重点研发计划(现代农业)项目(BE2015308) 江苏省高校自然科学研究重大项目(14KJA550001) 江苏高校优势学科建设工程资助项目国家自然基金项目(31671932) 江苏省第四期“333工程”资助项目(BRA2015320)
【分类号】：S636.1;TP391.41

【相似文献】