Cognitive spectroscopy for wood species identification: near infrared hyperspectral imaging combined with convolutional neural networks

文献信息

发布日期 2019-10-02

DOI 10.1039/C9AN01180C

影响因子 4.616

作者

Hideaki Kanayama, Te Ma, Satoru Tsuchikawa, Tetsuya Inagaki

查看原文

摘要

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.

期刊推荐

Pure and Applied Chemistry

Proceedings of the National Academy of Sciences of the United States of America

Journal of Catalysis

Kinetics and Catalysis

Journal of Physics and Chemistry of Solids

Israel Journal of Chemistry

Science

European Journal of Wood and Wood Products

Organic Preparations and Procedures International

Helvetica Chimica Acta

来源期刊

Analyst

CiteScore: 7.8

自引率: 5.6%

年发文量: 653

Analyst publishes analytical and bioanalytical research that reports premier fundamental discoveries and inventions, and the applications of those discoveries, unconfined by traditional discipline barriers.

Cognitive spectroscopy for wood species identification: near infrared hyperspectral imaging combined with convolutional neural networks

文献信息

期刊推荐

相关文献

Quantitative analysis of 14N quadrupolar coupling using 1H detected 14N solid-state NMR

Back cover

Electrical conductivity and oxygen diffusion behaviour of the (La0.8Sr0.2)0.95CrxFe1−xO3−δ (x = 0.3, 0.5 and 0.7) A-site deficient perovskites

Transition metal cations on the move: simultaneous operando X-ray absorption spectroscopy and X-ray diffraction investigations during Li uptake and release of a NiFe2O4/CNT composite

Excitation of singlet–triplet coherences in pairs of nearly-equivalent spins

Band alignment in quantum wells from automatically tuned DFT+U

A magnetic resonance and electrochemical study of the role of polymer mobility in supporting hydrogen transport in perfluorosulfonic acid membranes

Bismuth oxysulfide film electrodes with giant incident photon-to-current conversion efficiency: the dynamics of properties with deposition time

Bile acid derivative-based catanionic mixtures: versatile tools for superficial charge modulation of supramolecular lamellae and nanotubes

Tuning the magnetic properties of beryllium chains

您可能还喜欢

6-氯-2H-1,4-苯并噁嗪-3(4H)-酮(CAS号：7652-29-1)应用于哪些行业？

活性氧化铝(CAS号：1302-74-5)应用于哪些行业？

什么是硅胶(CAS号：112926-00-8)？

二乙基甲基一氢硅烷(CAS号：760-32-7)的主要用途是什么？

在合成中是否有N-花生四烯酰基甘氨酸(CAS号：179113-91-8)的替代品？

在合成中是否有1-(4-甲氧基苯基)丙烷-1,2-二酮(CAS号：10557-27-4)的替代品？

N-(4-氨基-1-苄基-3-羟基-5-苯基戊基)-3-甲基-2-(2-氧代四氢嘧啶-1-基)-丁酰胺 5-氧代吡咯烷-2-甲酸(CAS号：192726-06-0)通常如何合成？

(S)-2-氨基-3-喹啉-2-丙酸(CAS号：161513-46-8)的市场或研究趋势如何？

核黄素磷酸钠(CAS号：130-40-5)安全吗？

盐酸丙胺卡因杂质A(EP) 标准品(CAS号：19281-31-3)通常如何合成？

来源期刊

Analyst

推荐化合物

Atrial natriuretic factor (5-27)

(2-Bromopyridin-3-yl)methanamine

2-(4-Chlorophenyl)-4-(dimethylamino)-2-(2-(dimethylamino)ethyl)butanenitrile

(2-Bromo-5-chlorophenyl)boronic acid

1,3,6,8-Tetramethyl-9H-carbazole

推荐供应商