基于高光谱图像及深度特征的大米蛋白质含量预测模型

Prediction model of rice protein content based on hyperspectral image and deep feature

为了充分挖掘高光谱图像的光谱信息和图像信息,实现大米中蛋白质含量的无损检测,该文提出一种堆叠自动编码器(stacked auto-encoder,SAE)提取高光谱图像深度特征的方法,在高温(45℃)高湿(95%相对湿度)条件下对市售大米进行放置处理,以6组不同放置时间(0,24,48,72,96和120 h)共420个大米样本(每组70个)为对象,利用可见光/近红外高光谱成像仪采集高光谱图像(400~1 000 nm,共478个波段),采用阈值分割法获取样本高光谱图像掩膜,分别提取掩膜后高光谱图像感兴趣区域(region of interest,ROI)的平均光谱信息和图像信息。应用多项式平滑(savitzky-golay,SG)对获取的光谱曲线进行预处理,利用SAE提取光谱深度特征,采用支持向量机回归(support vector regression,SVR)建立预测模型,结果表明训练集决定系数RC^2、训练集均方根误差RMSEC、预测集决定系数RP^2和预测集均方根误差RMSEP分别为0.976 2、0.068 6 g/(100 g)、0.939 2和0.115 3 g/(100 g)。将图像尺寸统一为28像素×28像素的灰度图并扁平化处理,利用SAE提取图像深度特征,结果表明RC^2、RMSEC、RP^2和RMSEP分别为0.915 4、0.051 0 g/(100 g)、0.821 0和0.111 8 g/(100 g)。进一步融合光谱信息和图像信息,结果表明RC^2、RMSEC、RP^2和RMSEP分别为0.971 0、0.077 2 g/(100 g)、0.964 4和0.085 1 g/(100 g),相较于光谱信息,RP^2提升幅度2.68%;相较于图像信息,RP^2提升幅度17.47%。研究表明,充分挖掘大米样本高光谱图像中的光谱信息和图像信息并进行融合,利用SAE提取光谱-图像融合深度特征,可有效提高模型的预测精度,为大米蛋白质含量无损检测提供了理论依据,具有良好的应用前景。

In order to fully explore useful spectral and image information of hyperspectral images,a method of extracting the deep feature of hyperspectral images based on stacked auto-encoder(SAE)was investigated in this study,then the extracted deep feature was used to establish support vector regression(SVR)model to realize non-destructive detection of protein content in rice.Firstly,420 rice samples(70 in each group)were placed in 6 groups at different storage time(0,24,48,72,96 and 120 h)under the condition of high temperature(45℃)and high humidity(95%relative humidity).Secondly,the hyperspectral images(400-1 000 nm)of 6 group rice samples with different protein content were collected by the hyperspectral image acquisition system.After hyperspectral images collection,the Kjeldahl method for determination of nitrogen was used to detect the protein content of rice samples.According to the chemical detection results,the protein content of the rice samples decreased from 7.78 to 7.62 g/(100 g)with the increase of storage time.Thirdly,in order to separate samples from background,the threshold segmentation method was used to obtain the sample mask in ENVI software,then the mask was applied to the hyperspectral image containing only rice samples.The rice sample area was chosen as region of interest(ROI),and the average spectral data and image information of ROI was extracted respectively.Finally,SAE was used to extract deep feature of spectral data,image information and fusion data.1)For spectral information,savitzky-golay(SG)was used to pre-process the obtained spectral data,and SAE was used to extract the deep feature,then SVR was used to establish the prediction model,and grid search method was used to optimize the kernel parameter g and penalty factor c in SVR.The results showed that the optimal scale of SAE was 478-400-290-70,and R^2C(determinant coefficient of calibration set),R^2P(determinant coefficient of prediction set),RMSEC(root mean square error of calibration set),RMSEP(root mean square error of prediction set)using deep feature extracted by SAE were 0.976 2,0.939 2,0.068 6 g/(100 g),0.115 3 g/(100 g),respectively.2)For image information,the RGB images in each band were extracted first,the size was 100 pixels×100 pixels.There was much redundant information in the original images,so we unified them to the gray images with 28 pixels×28 pixels,then flattened and converted them to one-dimensional column vector,after deep feature extraction by SAE on the vector,the prediction results of the model built with SVR showed that the optimal scale of SAE was 784-700-480-30,and R^2C,R^2P,RMSEC,RMSEP modeled using deep feature extracted by SAE were 0.915 4,0.821 0,0.051 0 g/(100 g),0.111 8 g/(100 g),respectively.3)For the fusion data of spectral data and image information,the initial dimension was 1 262,the fusion data combined all the redundant information of spectral and image,so dimension reduction becomes critical.After feature extraction by SAE,the dimension was reduced to the low level and the efficiency of network training was improved.The optimal scale of SAE was 1262-550-450-30,and R^2C,R^2P,RMSEC,RMSEP of the model build with deep feature extracted by SAE were 0.971 0,0.964 4,0.077 2 g/(100 g),0.085 1 g/(100 g),respectively.Compared with using spectral data or image information alone,the prediction effect of the model build with the fusion data was improved obviously.To summarize,the method in the paper fully fused the spectral data and image information of hyperspectral image,and then deep feature extracted by SAE improved the prediction accuracy of the model established by SVR effectively,which provides a theoretical basis for non-destructive detection of protein content in rice.