Nagoya University, Graduate School of Bioagricultural Sciences, Nagoya, 464-0814, Japan.
Analyst. 2019 Nov 7;144(21):6438-6446. doi: 10.1039/c9an01180c. Epub 2019 Oct 7.
From the viewpoint of combating illegal logging and examining wood properties, there is a contemporary demand for a wood species identification system. Several nondestructive automatic identification systems have been developed, but there is room for improvement to construct a highly reliable model. The present study proposes cognitive spectroscopy that combines near infrared hyperspectral imaging (NIR-HSI) with a deep convolutional neural network approach. We defined "cognitive spectroscopy" as a protocol that extracts features from complex spectroscopic data and presents the best results without human intervention. Overall, 120 samples representing 38 hardwood species were scanned using an NIR-HSI camera. A deep learning prediction model was built based on the principal component (PC) images obtained from the PC scores of hyperspectral images (wavelength range: 1000-2200 nm at approximately 6.2 nm interval). The results showed that the accuracy of wood species identification based on 6PC (PC1-PC6) images was 90.5%, which was considerably higher than the accuracy of 56.0% obtained with conventional visible images.
从打击非法采伐和检验木材性质的角度来看，当代社会对木材种类识别系统存在需求。已经开发出了几种非破坏性的自动识别系统，但仍有改进空间，以构建高度可靠的模型。本研究提出了认知光谱学，它将近红外高光谱成像（NIR-HSI）与深度卷积神经网络方法相结合。我们将“认知光谱学”定义为一种从复杂光谱数据中提取特征并呈现最佳结果而无需人工干预的协议。总体而言，使用 NIR-HSI 相机扫描了代表 38 种硬木的 120 个样本。基于从高光谱图像的主成分得分（波长范围：1000-2200nm，约 6.2nm 间隔）获得的主成分（PC）图像，构建了深度学习预测模型。结果表明，基于 6PC（PC1-PC6）图像的木材种类识别准确率为 90.5%，明显高于使用传统可见图像获得的 56.0%的准确率。
