文献类型：期刊文献

中文题名：基于卷积神经网络的近红外光谱与数字图像特征信息融合木材树种识别

英文题名：Wood Species Identification through Fusion of NIR Spectroscopy and Digital Image Features Information Using Convolutional Neural Networks

作者：潘玺[1] 李康[1] 杨忠[1]

第一作者：潘玺

机构：[1]中国林业科学研究院木材工业研究所,北京100091

年份：2024

卷号：60

期号：12

起止页码：136-145

中文期刊名：林业科学

外文期刊名：Scientia Silvae Sinicae

收录：CSTPCD;;EI(收录号：20250217650533);Scopus;北大核心:【北大核心2023】；CSCD:【CSCD2023_2024】；

基金：国家自然科学基金面上项目“基于可见光-近红外光谱与数字图像特征信息融合技术的木材识别研究”(31770766);中央级公益性科研院所基本科研业务费专项资金重点项目“人造板施胶均匀性快速检测新技术研究”(CAFYBB2021ZJ001)。

语种：中文

中文关键词：木材树种识别;卷积神经网络;近红外光谱;图像;特征提取与融合

外文关键词：wood species identification;convolutional neural network(CNN);near-infrared spectroscopy;image;feature extraction and fusion

分类号：S781.1

摘要：【目的】基于卷积神经网络自动提取,探究融合木材近红外光谱与数字图像特征信息准确识别木材树种的可行性。【方法】以樟科10种木材标本为例,使用手持式近红外光谱仪和便携式扫描仪采集木材标本横切面近红外光谱和图像。创新引入递归图方法,将手持式近红外光谱仪采集的一维短波长近红外光谱转换为二维图像,促进卷积神经网络从近红外光谱数据中提取判别性更强的特征,实现近红外光谱与图像在二维尺度上的融合。构建结构简单的双分支卷积神经网络模型,自动提取、融合近红外光谱与图像特征识别木材树种。【结果】与直接使用一维近红外光谱的建模方法相比,近红外光谱递归图结合卷积神经网络模型的识别性能提升1.79%~14%;与使用近红外光谱或图像单一特征识别相比,双分支卷积神经网络模型自动提取、融合近红外光谱与图像特征,对10种木材的识别性能至少提高3%,模型准确率、精度和召回率均大于99%。【结论】一维短波长近红外光谱递归图转换能够促进卷积神经网络从近红外光谱数据中提取判别性更强的特征,提高模型识别性能。双分支卷积神经网络能够充分提取并有效融合木材近红外光谱与图像特征,一定程度上可克服使用单一特征识别木材树种的不足,提高木材树种识别效果。
【Objective】The feasibility of accurately identifying wood species by integrating near infrared spectroscopy(NIR)and digital image feature information,automatically extracted based on convolutional neural networks(CNN),is investigated.【Method】10 wood specimens from the Lauraceae family were used as examples.NIR spectra and digital images from the transverse surfaces of specimens were collected using a handheld NIR spectrometer and portable scanner.The recurrence plot(RP)method was innovatively employed to encode one-dimensional(1D)NIR spectra as two-dimensional(2D)images.This not only enabled the CNN model to extract more robust discriminative features from the handheld NIR spectrometer’s shorter-wavelength NIR spectra,but also facilitated the fusion of NIR spectra and images.A simple two branch CNN(TB-CNN)model was developed to automatically extract and fuse NIR spectral and digital image features for wood species identification.【Result】Compared to different modeling methods that utilize 1D NIR spectra directly,integrating 2D RP of NIR spectra with CNN resulted in a performance improvement ranging from 1.79% to 14%.Furthermore,when compared with the results obtained using a single feature from either NIR spectra or digital image,the TB-CNN method showed a significant increase in identification rates of at least 3%.Notably,the accuracy,precision and recall values all surpassed 99%.【Conclusion】The conversion of 1D shortwavelength NIR spectra into RP enhances the ability of CNN model to extract more discriminative features from the NIR spectral data,improving model performance in species identification.The TB-CNN model effectively extracts and integrates wood NIR spectra and digital image features,addressing the limitations of using a single feature type for wood species identification and improving overall identification accuracy.