دورية أكاديمية
أعرض في EDS

Identifying and extracting bark key features of 42 tree species using convolutional neural networks and class activation mapping.

التفاصيل البيبلوغرافية
العنوان: Identifying and extracting bark key features of 42 tree species using convolutional neural networks and class activation mapping.
المؤلفون: Kim TK; Department of Agriculture, Forestry and Bioresources, Seoul National University, Seoul, 08826, Republic of Korea., Hong J; Department of Agriculture, Forestry and Bioresources, Seoul National University, Seoul, 08826, Republic of Korea., Ryu D; Interdisciplinary Program in Agricultural and Forest Meteorology, Seoul National University, Seoul, 08826, Republic of Korea., Kim S; Department of Agriculture, Forestry and Bioresources, Seoul National University, Seoul, 08826, Republic of Korea., Byeon SY; Department of Agriculture, Forestry and Bioresources, Seoul National University, Seoul, 08826, Republic of Korea., Huh W; Department of Agriculture, Forestry and Bioresources, Seoul National University, Seoul, 08826, Republic of Korea., Kim K; Department of Agriculture, Forestry and Bioresources, Seoul National University, Seoul, 08826, Republic of Korea., Baek GH; Department of Forest Sciences, Seoul National University, Seoul, 08826, Republic of Korea., Kim HS; Department of Agriculture, Forestry and Bioresources, Seoul National University, Seoul, 08826, Republic of Korea. cameroncrazies@snu.ac.kr.; Department of Forest Sciences, Seoul National University, Seoul, 08826, Republic of Korea. cameroncrazies@snu.ac.kr.; Interdisciplinary Program in Agricultural and Forest Meteorology, Seoul National University, Seoul, 08826, Republic of Korea. cameroncrazies@snu.ac.kr.; National Center for Agrometeorology, Seoul, 08826, Republic of Korea. cameroncrazies@snu.ac.kr.; Research Institute of Agricultural and Life Sciences, Seoul National University, Seoul, 08826, Republic of Korea. cameroncrazies@snu.ac.kr.
المصدر: Scientific reports [Sci Rep] 2022 Mar 19; Vol. 12 (1), pp. 4772. Date of Electronic Publication: 2022 Mar 19.
نوع المنشور: Journal Article; Research Support, Non-U.S. Gov't
اللغة: English
بيانات الدورية: Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: MEDLINE
أسماء مطبوعة: Original Publication: London : Nature Publishing Group, copyright 2011-
مواضيع طبية MeSH: Plant Bark* , Trees*, Algorithms ; Humans ; Neural Networks, Computer ; Vision, Ocular
مستخلص: The significance of automatic plant identification has already been recognized by academia and industry. There were several attempts to utilize leaves and flowers for identification; however, bark also could be beneficial, especially for trees, due to its consistency throughout the seasons and its easy accessibility, even in high crown conditions. Previous studies regarding bark identification have mostly contributed quantitatively to increasing classification accuracy. However, ever since computer vision algorithms surpassed the identification ability of humans, an open question arises as to how machines successfully interpret and unravel the complicated patterns of barks. Here, we trained two convolutional neural networks (CNNs) with distinct architectures using a large-scale bark image dataset and applied class activation mapping (CAM) aggregation to investigate diagnostic keys for identifying each species. CNNs could identify the barks of 42 species with > 90% accuracy, and the overall accuracies showed a small difference between the two models. Diagnostic keys matched with salient shapes, which were also easily recognized by human eyes, and were typified as blisters, horizontal and vertical stripes, lenticels of various shapes, and vertical crevices and clefts. The two models exhibited disparate quality in the diagnostic features: the old and less complex model showed more general and well-matching patterns, while the better-performing model with much deeper layers indicated local patterns less relevant to barks. CNNs were also capable of predicting untrained species by 41.98% and 48.67% within the correct genus and family, respectively. Our methodologies and findings are potentially applicable to identify and visualize crucial traits of other plant organs.
(© 2022. The Author(s).)
References: Nature. 2015 May 28;521(7553):436-44. (PMID: 26017442)
Plant Methods. 2019 Jul 23;15:77. (PMID: 31367223)
Nature. 2010 Sep 9;467(7312):154-5. (PMID: 20829777)
New Phytol. 2014 Jan;201(2):486-497. (PMID: 24117609)
Proc Natl Acad Sci U S A. 2016 Mar 22;113(12):3305-10. (PMID: 26951664)
Proc Natl Acad Sci U S A. 2018 Jun 19;115(25):E5716-E5725. (PMID: 29871948)
Sci Rep. 2020 Feb 11;10(1):2322. (PMID: 32047172)
تواريخ الأحداث: Date Created: 20220320 Date Completed: 20220504 Latest Revision: 20220504
رمز التحديث: 20221213
مُعرف محوري في PubMed: PMC8934343
DOI: 10.1038/s41598-022-08571-9
PMID: 35306532
قاعدة البيانات: MEDLINE
الوصف
تدمد:2045-2322
DOI:10.1038/s41598-022-08571-9