农业工程2025，Vol.15Issue(9)：27-35,9.DOI:10.19998/j.cnki.2095-1795.202509305
基于SS-FusionNet的苍术与关苍术分类方法
Classification method for Atractylodes lancea(Thunb.)DC.and Atractylodes japonica Koidz.Ex Kitam.based on SS-FusionNet
摘要
Abstract
Atractylodes lancea(Thunb.)DC.and Atractylodes japonica Koidz.Ex Kitam.are highly similar in appearance,composi-tion,and other aspects.Traditional identification methods based on morphological or chemical indicators have low classification accur-acy under conditions of small sample sizes or non-destructive testing.A deep learning classification network called SS-FusionNet was proposed,which integrated spectral and image information for high-precision classification of Atractylodes lancea(Thunb.)DC.and Atractylodes japonica Koidz.Ex Kitam.slices under hyperspectral image and small sample conditions.Atractylodes lancea(Thunb.)DC.and Atractylodes japonica Koidz.Ex Kitam.slices sample data were collected by hyperspectral imaging system.An autoencoder net-work was pre-trained using unlabeled hyperspectral data to enable encoder module to extract image features from spectral data.Spectral features were deeply fused with image features,and classification was performed by combining upsampling convolution module.Exper-imental results showed that under small sample conditions,SS-FusionNet achieved a classification accuracy of 92.7%,which was 7.5 percentage points higher than 85.2%classification accuracy of support vector machines and 6.1 percentage points higher than 86.6%accur-acy of convolutional neural networks.A new ideas and methods was procided for in-depth identification research on traditional Chinese medicine species.关键词
高光谱图像/苍术/关苍术/图谱融合/自编码器/小样本分类/分类网络Key words
hyperspectral image/Atractylodes lancea(Thunb.)DC./Atractylodes japonica Koidz.Ex Kitam./spectral image fusion/autoencoder/small sample classification/classification network分类
农业科技引用本文复制引用
郭鹏飞,王飞云,陈月锋,韩亚芬,赵明杰,吕程序,赵博,姜含露..基于SS-FusionNet的苍术与关苍术分类方法[J].农业工程,2025,15(9):27-35,9.基金项目
中国机械工业集团有限公司科研项目(ZDZX2022-2) （ZDZX2022-2）
