文献类型：期刊文献

英文题名：Opening the black box: explainable deep-learning classification of wood microscopic image of endangered tree species

作者：Zheng, Chang[1,2] Liu, Shoujia[1,2] Wang, Jiajun[1,2,4] Lu, Yang[1,2] Ma, Lingyu[1,2] Jiao, Lichao[1,2] Guo, Juan[1,2] Yin, Yafang[1,2] He, Tuo[1,2,3]

第一作者：Zheng, Chang

通信作者：He, T[1];He, T[2];He, T[3]

机构：[1]Chinese Acad Forestry, Res Inst Wood Ind, Dept Wood Anat & Utilizat, Beijing 100091, Peoples R China;[2]Chinese Acad Forestry, Wood Collect, Beijing 100091, Peoples R China;[3]Natl Forestry & Grassland Adm, Wildlife Conservat Monitoring Ctr, Beijing 100714, Peoples R China;[4]Natl Ctr Archaeol, Beijing 100013, Peoples R China

年份：2024

卷号：20

期号：1

外文期刊名：PLANT METHODS

收录：;Scopus(收录号：2-s2.0-85191329546);WOS:【SCI-EXPANDED(收录号:WOS:001207792100002)】；

基金：We would like to thank Alex C. Wiedenhoeft of Center for Wood Anatomy Research, USDA Forest Service, Forest Products Laboratory for his help with data support.

语种：英文

外文关键词：Computer vision; Deep learning; Feature visualization; Image classification; Wood identification

摘要：Background Traditional method of wood species identification involves the use of hand lens by wood anatomists, which is a time-consuming method that usually identifies only at the genetic level. Computer vision method can achieve "species" level identification but cannot provide an explanation on what features are used for the identification. Thus, in this study, we used computer vision methods coupled with deep learning to reveal interspecific differences between closely related tree species.Result A total of 850 images were collected from the cross and tangential sections of 15 wood species. These images were used to construct a deep-learning model to discriminate wood species, and a classification accuracy of 99.3% was obtained. The key features between species in machine identification were targeted by feature visualization methods, mainly the axial parenchyma arrangements and vessel in cross section and the wood ray in tangential section. Moreover, the degree of importance of the vessels of different tree species in the cross-section images was determined by the manual feature labeling method. The results showed that vessels play an important role in the identification of Dalbergia, Pterocarpus, Swartzia, Carapa, and Cedrela, but exhibited limited resolutions on discriminating Swietenia species.Conclusion The research results provide a computer-assisted tool for identifying endangered tree species in laboratory scenarios, which can be used to combat illegal logging and related trade and contribute to the implementation of CITES convention and the conservation of global biodiversity.