Wu Na, Zhang Yu, Na Risu, Mi Chunxiao, Zhu Susu, He Yong, Zhang Chu
College of Biosystems Engineering and Food Science, Zhejiang University 866 Yuhangtang Road Hangzhou 310058 China
State Key Laboratory of Modern Optical Instrumentation, Zhejiang University Hangzhou 310058 China.
RSC Adv. 2019 Apr 25;9(22):12635-12644. doi: 10.1039/c8ra10335f. eCollection 2019 Apr 17.
Variety identification of seeds is critical for assessing variety purity and ensuring crop yield. In this paper, a novel method based on hyperspectral imaging (HSI) and deep convolutional neural network (DCNN) was proposed to discriminate the varieties of oat seeds. The representation ability of DCNN was also investigated. The hyperspectral images with a spectral range of 874-1734 nm were primarily processed by principal component analysis (PCA) for exploratory visual distinguishing. Then a DCNN trained in an end-to-end manner was developed. The deep spectral features automatically learnt by DCNN were extracted and combined with traditional classifiers (logistic regression (LR), support vector machine with RBF kernel (RBF_SVM) and linear kernel (LINEAR_SVM)) to construct discriminant models. Contrast models were built based on the traditional classifiers using full wavelengths and optimal wavelengths selected by the second derivative (2nd derivative) method. The comparison results showed that all DCNN-based models outperformed the contrast models. DCNN trained in an end-to-end manner achieved the highest accuracy of 99.19% on the testing set, which was finally employed to visualize the variety classification. The results demonstrated that the deep spectral features with outstanding representation ability enabled HSI together with DCNN to be a reliable tool for rapid and accurate variety identification, which would help to develop an on-line system for quality detection of oat seeds as well as other grain seeds.
种子品种鉴定对于评估品种纯度和确保作物产量至关重要。本文提出了一种基于高光谱成像（HSI）和深度卷积神经网络（DCNN）的新方法来鉴别燕麦种子品种。同时还研究了DCNN的表征能力。对光谱范围为874 - 1734 nm的高光谱图像主要通过主成分分析（PCA）进行处理，以进行探索性视觉区分。然后开发了一种以端到端方式训练的DCNN。提取DCNN自动学习的深度光谱特征，并将其与传统分类器（逻辑回归（LR）、带径向基核的支持向量机（RBF_SVM）和线性核支持向量机（LINEAR_SVM））相结合，构建判别模型。基于传统分类器，使用全波长和通过二阶导数（二阶导数）方法选择的最佳波长构建对比模型。比较结果表明，所有基于DCNN的模型均优于对比模型。以端到端方式训练的DCNN在测试集上达到了最高准确率99.19%，最终用于可视化品种分类。结果表明，具有出色表征能力的深度光谱特征使HSI与DCNN成为快速准确品种鉴定的可靠工具，这将有助于开发燕麦种子以及其他谷物种子质量检测的在线系统。
