Development of a system for the automated identification of herbarium specimens with high accuracy.

Development of a system for the automated identification of herbarium specimens with high accuracy.
复制标题

DOI:
10.1038/s41598-022-11450-y
复制
发表时间:
2022-05-16
期刊:
影响因子:
4.6
通讯作者:
Akihiro T
Akihiro T
中科院分区:
综合性期刊3区
文献类型:
--
作者:
Shirai M;Takano A;Kurosawa T;Inoue M;Tagane S;Tanimoto T;Koganeyama T;Sato H;Terasawa T;Horie T;Mandai I;Akihiro T

文献摘要

参考文献

相似文献

植物标本室的标本是装在纸上的干燥植物。它们被有限数量的研究人员使用,例如植物分类学家,作为形态和分布信息的来源。最近,数字化植物标本馆标本已开始用于综合研究,以解决更广泛的问题。然而,一些标本被错误识别,如果使用,就有得出错误结论的风险。在这项研究中,我们成功地开发了一种利用图像识别系统对分类单元名称进行高精度识别的系统。利用日本192科2171个植物分类群(2064种,9个亚种,88个变种,10个形态)的500,554个标本图像,建立了一个准确率为96.4%的系统。我们澄清了人工智能在哪里寻找决策,以及哪些类群被错误识别。由于该系统可应用于世界范围内的数字化图像,因此它对选择和纠正错误识别的植物标本馆标本非常有用。
Herbarium specimens are dried plants mounted onto paper. They are used by a limited number of researchers, such as plant taxonomists, as a source of information on morphology and distribution. Recently, digitised herbarium specimens have begun to be used in comprehensive research to address broader issues. However, some specimens have been misidentified, and if used, there is a risk of drawing incorrect conclusions. In this study, we successfully developed a system for identifying taxon names with high accuracy using an image recognition system. We developed a system with an accuracy of 96.4% using 500,554 specimen images of 2171 plant taxa (2064 species, 9 subspecies, 88 varieties, and 10 forms in 192 families) that grow in Japan. We clarified where the artificial intelligence is looking to make decisions, and which taxa is being misidentified. As the system can be applied to digitalised images worldwide, it is useful for selecting and correcting misidentified herbarium specimens.
DOI: 10.3732/apps.1600108
发表时间: 2017-01
影响因子: 3.6
作者:
Rudin SM;Murray DW;Whitfeld TJ
通讯作者: Whitfeld TJ
DOI: 10.1186/s12862-017-1014-z
发表时间: 2017-08-11
影响因子: 3.4
作者:
Carranza-Rojas J;Goeau H;Bonnet P;Mata-Montero E;Joly A
通讯作者: Joly A
DOI: 10.1016/j.patcog.2017.05.015
发表时间: 2017-11-01
影响因子: 8
作者:
Lee, Sue Han;Chan, Chee Seng;Remagnino, Paolo
通讯作者: Remagnino, Paolo
DOI: 10.1016/j.compag.2020.105593
发表时间: 2020-08-01
影响因子: 8.3
作者:
Espejo-Garcia, Borja;Mylonas, Nikolaos;Fountas, Spyros
通讯作者: Fountas, Spyros
DOI: 10.1007/978-3-319-76445-0_9
发表时间: 2018-01-01
期刊: MULTIMEDIA TOOLS AND APPLICATIONS FOR ENVIRONMENTAL & BIODIVERSITY INFORMATICS
影响因子: --
作者:
Carranza-Rojas, Jose;Joly, Alexis;Bonnet, Pierre
通讯作者: Bonnet, Pierre