采集我国东北和非东北10个产地、4个品种共计1000份单粒大米样本在波长950～1700 nm区间的高光谱图像,按照单粒大米轮廓提取感兴趣区域并计算平均光谱,采用主成分分析从样本集光谱矩阵提取累计贡献率大于99％的第一、二主成分,根据载荷矩阵系数最大值筛选与第一、二主成分相关性最强的特征波长1396.67 nm和1467.38 nm.针对两组特征波长图像进行主成分分析,分别选取前三维主成分,共计可得2×3组训练样本集.结果表明:基于AlexNet卷积神经网络训练建立6组东北/非东北大米产地高光谱快速判别模型,均有较高的识别准确率,其中基于1467.38 nm波长的第三主成分图像建立的东北/非东北大米产地判别模型的性能最佳,其识别准确率可达99.5％.

大米的品质受到基因遗传、气候、土壤等影响,不同产地的大米品质不同,为了鉴别大 米的产地,应用德国Bruker VERTEX 70傅里叶红外光谱仪采集4个不同产地大米的傅里叶红外光谱,分别经过矢量归一化、一阶导数+13点平滑、一阶导数+13点平滑+矢量归一化、一阶导数+13点平滑+减去一条直线预处理后,建立偏最小二乘判别模型(Partial Least-squares Discrimination Analysis,PLS-DA).结果 表明:经过一阶导数+13点平滑+矢量归一化+PES-DA处理后的模型识别率为92.29％,该模型对吉林、江苏、辽宁、浙江这4个产地的识别率分别为93.77％、91.24％、100％、75％.为了提高模型的识别率,对全光谱数据进行主成分分析(Principal Component Analysis,PCA)特征提取,建立不同成分特征的K近邻(K Nearest Neighbor,KNN)模型,结果表明:选取PCA前7成分特征作为KNN模型的输入,得到PCA-KNN模型识别率为94.27％,该模型对吉林、江苏、辽宁、浙江这4个产地的识别率分别为94.44％、94.12％、93.75％、93.33％.实验结果表明,利用傅里叶红外光谱技术对大米产地溯源具有一定的可行性.

Hyperspectral images of rice from northeast/non-northeast regions were collected, and spectral images at characteristic wavelengths were screened. The clustering combination of image features and pattern recognition method was established to quickly and accurately identify northeast/non-northeast rice origin. Northeast rice is mainly japonica rice, and the typical northeastern rice varieties include long-grain, round-grain, rice flower and Xiaoding rice. Considering the practicability and applicability of rice origin identification model, samples of 10 origins and 4 varieties above were collected to form the original sample set. Among them, there are five northeastern origins, including Heilongjiang (1) , Jilin (2) , Liaoning (2) , and five non-northeastern origins, including Hebei (1), Zhejiang (1) , Jiangsu (2) and Anhui (1). 100 samples were selected randomly from each producing area. Hyperspectral images of 100 x 10 rice samples were collected using SisuCHEMA hyperspectral imaging system (Specim, Finland)in the range of 900 similar to 1700 nm. Extracting the average spectra of a single rice sample by selecting the region of interest according to the rice contour, Kennard-Stone method was used to divide training set and test set according to the ratio of 4 1. Eight characteristic wavelengths were screened by Successive Projections Algorithm ( SPA): 1 460. 30, 1 400. 20, 1 424. 92, 945. 98, 1 315. 62, 1 220. 87, 1 705. 91, 942. 53 nm. The eight models were built respectively by HOG features extracted from single characteristic wavelength Image and SVM to identify the rice origin whether it was from northeast or nonnortheast China. The recognition accuracy was as follows : 85. 5% , 77. 5% , 76. 5% , 73. 5% , 71% , 68. 5% , 67% , 65. 5%. In view of the low recognition rate of single model, a strategy of establishing model cluster based on single characteristic wavelength image model to synthetically discriminate rice origin was proposed. According to the recognition rate of single model from high to low, the cluster models were established by respectively combining three, five and seven the signal models above. While the probability of the sample judged to be true predicted by the conjunctive model is greater than 50% , the sample will be judged to be true, otherwise it will be false. The experimental results showed that the recognition rate of the test set samples can reach 90. 5% by combining the model sets of 1 460. 30, 1 400. 20, 1 424. 92, 945. 98, 1 315. 62, 1 220. 87 and 1 705. 91 nm bands. This study shows that hyperspectral technology combined with the strategy of conjunctive model consensus can provide feasible and effective methods to establish a robust and wide applicability model to recognize the rice origin (northeast/non-northeast) rapidly.

利用高光谱成像技术对不同品种的花生进行快速无损分类.选取五种不同品种的花生,分别为东北小花生、富硒黑皮花生、花育36号、鲁花01号、鲁花09号,每种15颗,共75颗花生作为样本,采集400nm-1000nm波长范围内的高光谱图像,随机将6个特征波段(416nm、518nm、572nm、633nm、746nm、928nm)下的450个样本图像以2∶1的比例分成训练集和测试集,建立基于深度学习的卷积神经网络模型.实验中所采用的网络模型为具有22层深度网络的GoogleNet模型,其中将dropout_ratio修改为0.6,训练集最终准确率为96％,测试集平均准确率为93.3％,每种花生的识别率均在90％及以上.最后与传统光谱处理方法PLS-DA进行对比,发现基于深度学习模型的识别率明显优于PLS-DA,结果表明,利用深度学习方法对花生快速无损分类具有可行性.

鉴于市场上东北大米掺伪和假冒现象频发,本研究将近红外光谱技术与PLS-DA判别法相结合用于东北大米产地快速溯源.实验共收集75份大米样本(52份东北产地大米,23份非东北产地大米),按照4∶1的比例随机划分得到训练集样本60份和测试集15份.为消除品种、颗粒形态等对近红外光谱和产地鉴别的影响,实验比较多种光谱预处理方法,并根据相关系数值确定了矢量归一化为首选的预处理方法;将矢量归一化预处理后的光谱按照吸收峰分4个区间分别建立东北大米产地PLS-DA模型,其中4 000～5 500cm-1谱区建立产地溯源模型,训练集准确率可达93.33％,测试集准确率为86.67％.实验结果表明,近红外光谱与PLS-DA法结合在东北大米产地快速溯源技术领域有着光明的应用前景.