Reflectance images of effective wavelengths from hyperspectral imaging for identification of Fusarium head blight-infected wheat kernels combined with a residual attention convolution neural network
文献类型：期刊论文
| 作者 | Weng, Shizhuang1; Han, Kaixuan1; Chu, Zhaojie1; Zhu, Gongqin1; Liu, Cunchuan1; Zhu, Zede2; Zhang, Zixi1; Zheng, Ling1; Huang, Linsheng1 |
| 刊名 | COMPUTERS AND ELECTRONICS IN AGRICULTURE
 |
| 出版日期 | 2021-11-01 |
| 卷号 | 190 |
| 关键词 | Hyperspectral imaging Wheat diseases Variable selection Feature fusion Deep learning |
| ISSN号 | 0168-1699 |
| DOI | 10.1016/j.compag.2021.106483 |
| 通讯作者 | Weng, Shizhuang(weng_1989@126.com) |
| 英文摘要 | Identification of the Fusarium head blight (FHB) infection degree of wheat kernels is important to customise the reasonable use of wheat kernels and ensure food safety. In this study, an FHB infection degree identification method using hyperspectral imaging (HSI) and deep learning networks was proposed. Firstly, the reflectance spectra of healthy and mildly, moderately and severely FHB-infected wheat kernels were extracted from HSI images, and five effective wavelengths (EWs) of the spectra were selected by random frog. Secondly, the reflectance images (RIs) of different combinations of the EWs were screened using LeNet-5, and a residual attention convolution neural network (RACNN), which was constructed by increasing width and depth and adding channel attention and residual modules, was adopted to recognise various FHB infection degrees in wheat kernels. Optimal recognition performance was achieved by RACNN and RIs of 940 nm and 678 nm with a classification accuracy of 100%, 98.60% and 98.13% for the calibration, validation and prediction sets, respectively. Meanwhile, class activation maps revealed that the RACNN could effectively extract the distinctive features of the different classes of kernels. The images of only two wavelengths can be quickly acquired and processed, and the simultaneous recognition of multiple targets is easily realised. Overall, the proposed method enables the rapid, accurate and massive analysis of the FHB infection degree of wheat kernels. |
| WOS关键词 | DAMAGED KERNELS ; DEOXYNIVALENOL |
| WOS研究方向 | Agriculture ; Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000710643300004 |
| 出版者 | ELSEVIER SCI LTD |
| 源URL | [http://ir.hfcas.ac.cn:8080/handle/334002/125813]  |
| 专题 | 中国科学院合肥物质科学研究院 |
| 通讯作者 | Weng, Shizhuang |
| 作者单位 | 1.Anhui Univ, Natl Engn Res Ctr Agroecol Big Data Anal & Applic, 111 Jiulong Rd, Hefei, Peoples R China 2.Chinese Acad Sci, Hefei Inst Phys Sci, 350 Shushanhu Rd, Hefei 230031, Peoples R China |
| 推荐引用方式 GB/T 7714 | Weng, Shizhuang,Han, Kaixuan,Chu, Zhaojie,et al. Reflectance images of effective wavelengths from hyperspectral imaging for identification of Fusarium head blight-infected wheat kernels combined with a residual attention convolution neural network[J]. COMPUTERS AND ELECTRONICS IN AGRICULTURE,2021,190. |
| APA | Weng, Shizhuang.,Han, Kaixuan.,Chu, Zhaojie.,Zhu, Gongqin.,Liu, Cunchuan.,...&Huang, Linsheng.(2021).Reflectance images of effective wavelengths from hyperspectral imaging for identification of Fusarium head blight-infected wheat kernels combined with a residual attention convolution neural network.COMPUTERS AND ELECTRONICS IN AGRICULTURE,190. |
| MLA | Weng, Shizhuang,et al."Reflectance images of effective wavelengths from hyperspectral imaging for identification of Fusarium head blight-infected wheat kernels combined with a residual attention convolution neural network".COMPUTERS AND ELECTRONICS IN AGRICULTURE 190(2021). |
入库方式： OAI收割
来源：合肥物质科学研究院
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。