文献类型：期刊文献

英文题名：How to discriminate wood of CITES-listed tree species from their look-alikes: using an attention mechanism with the ResNet model on an enhanced macroscopic image dataset

作者：Liu, Shoujia[1,2] Zheng, Chang[1,2] Wang, Jiajun[1,2,3] Lu, Yang[1,2] Yao, Jie[4] Zou, Zhiyuan[4] Yin, Yafang[1,2] He, Tuo[1,2,5]

第一作者：Liu, Shoujia

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, Peoples R China;[2]Chinese Acad Forestry, Wood Collect, Beijing, Peoples R China;[3]Natl Ctr Archaeol, Beijing, Peoples R China;[4]Beijing Informat Sci & Technol Univ, Beijing, Peoples R China;[5]Natl Forestry & Grassland Adm, Wildlife Conservat Monitoring Ctr, Beijing, Peoples R China

年份：2024

卷号：15

外文期刊名：FRONTIERS IN PLANT SCIENCE

收录：;Scopus(收录号：2-s2.0-85198332906);WOS:【SCI-EXPANDED(收录号:WOS:001266105500001)】；

基金：We would like to thank Alex C. Wiedenhoeft, Center for Wood Anatomy Research, USDA Forest Service, Forest Products Laboratory, for providing wood specimens used to collect images and giving good suggestions on experiment design. We wish to acknowledge the assistance of Prof. Xiaomei Jiang in participating in the discussion. We also express our gratitude to Dr. Jie Wang, Miss. Jiabao Chen, and Mr. Yupei Wei for their help with the figures in this paper, and Dr. Yu Sun for his contributions to image collection.

语种：英文

外文关键词：wood identification; CITES; convolutional neural network; attention mechanism; data enhancement; macroscopic images

摘要：Introduction Global illegal trade in timbers is a major cause of the loss of tree species diversity. The Convention on International Trade in Endangered Species of Wild Fauna and Flora (CITES) has been developed to combat the illegal international timber trade. Its implementation relies on accurate wood identification techniques for field screening. However, meeting the demand for timber field screening at the species level using the traditional wood identification method depending on wood anatomy is complicated, time-consuming, and challenging for enforcement officials who did not major in wood science.Methods This study constructed a CITES-28 macroscopic image dataset, including 9,437 original images of 279 xylarium wood specimens from 14 CITES-listed commonly traded tree species and 14 look-alike species. We evaluated a suitable wood image preprocessing method and developed a highly effective computer vision classification model, SE-ResNet, on the enhanced image dataset. The model incorporated attention mechanism modules [squeeze-and-excitation networks (SENet)] into a convolutional neural network (ResNet) to identify 28 wood species.Results The results showed that the SE-ResNet model achieved a remarkable 99.65% accuracy. Additionally, image cropping and rotation were proven effective image preprocessing methods for data enhancement. This study also conducted real-world identification using images of new specimens from the timber market to test the model and achieved 82.3% accuracy.Conclusion This study presents a convolutional neural network model coupled with the SENet module to discriminate CITES-listed species with their look-alikes and investigates a standard guideline for enhancing wood transverse image data, providing a practical computer vision method tool to protect endangered tree species and highlighting its substantial potential for CITES implementation.