国内8款常用植物识别软件的识别能力评价

doi:10.17520/biods.2019272

生物多样性 ›› 2020, Vol. 28 ›› Issue (4): 524-533. DOI: 10.17520/biods.2019272

国内8款常用植物识别软件的识别能力评价

许展慧¹,刘诗尧¹,赵莹¹,涂文琴¹,常诏峰¹,张恩涛¹,郭靖¹,郑迪¹,耿鋆¹,顾高营¹,郭淳鹏¹,郭璐璐¹,王静¹,徐春阳¹,彭钏¹,杨腾¹,崔梦琪¹,孙伟成¹,张剑坛¹,刘皓天¹,巴超群¹,王鹤琪¹,贾竞超¹,武金洲¹,肖翠²,马克平^2,^*()

1 中国科学院大学, 北京 100049
2 中国科学院植物研究所植被与环境变化国家重点实验室, 北京 100093

收稿日期:2019-09-01 接受日期:2020-01-21 出版日期:2020-04-20 发布日期:2020-06-15
通讯作者: 马克平
基金资助:
中国科学院战略性先导科技专项(XDA19050404)

Evaluation of the identification ability of eight commonly used plant identification application softwares in China

Zhanhui Xu¹,Shiyao Liu¹,Ying Zhao¹,Wenqin Tu¹,Zhaofeng Chang¹,Entao Zhang¹,Jing Guo¹,Di Zheng¹,Jun Geng¹,Gaoying Gu¹,Chunpeng Guo¹,Lulu Guo¹,Jing Wang¹,Chunyang Xu¹,Chuan Peng¹,Teng Yang¹,Mengqi Cui¹,Weicheng Sun¹,Jiantan Zhang¹,Haotian Liu¹,Chaoqun Ba¹,Heqi Wang¹,Jingchao Jia¹,Jinzhou Wu¹,Cui Xiao²,Keping Ma^2,^*()

1 University of Chinese Academy of Sciences, Beijing 100049
2 State Key Laboratory of Vegetation and Environmental Change, Institute of Botany, Chinese Academy of Sciences, Beijing 100093

Received:2019-09-01 Accepted:2020-01-21 Online:2020-04-20 Published:2020-06-15
Contact: Keping Ma

摘要/Abstract

摘要：

随着智能手机和人工智能技术的发展, 以手机app为载体的植物识别软件慢慢走进公众生活、科普活动和科研活动的各个方面。植物识别app的识别正确率是决定其使用价值和用户体验的关键因素。目前, 国内应用市场上有许多植物识别app, 它们的开发目的和应用范围各异, 软件本身的关注点、数据库来源、算法、硬件要求也存在很大差异。对于不同人群, 植物识别app有不同的意义, 如对于科研人员来说, 识别能力强的app是提高效率的一大工具; 对植物爱好者来说, 具一定准确率的识别app可以作为入门的工具。因此, 对各app的识别能力进行分析与评价显得尤为重要。本文选取了8款常用的app, 分别对400张已准确鉴定的植物图片进行识别, 其中干旱半干旱区、温带、热带和亚热带4个区各选取100张。这些图片共计122科164属340种, 涵盖了乔木、灌木、草本、草质藤本和木质藤本5种生长型, 包含23种国家级保护植物。种、属、科准确识别正确分别计4分、2分、1分, 以此标准对软件识别能力按总得分进行排序, 正确率得分由高到低依次为花帮主、百度识图、花伴侣、形色、花卉识别、植物识别、发现识花、微软识花。

关键词: 植物识别软件, 花帮主, 百度识图, 花伴侣, 形色, 花卉识别, 植物识别, 发现识花, 微软识花

Abstract

Smart phone and artificial intelligence technology development has led to various plant recognition softwares on mobile applications. These applications have gradually entered all aspects of public life, popular science activities, and scientific research activities. Presently, there are many plant recognition apps in China, which have varying development purposes and application scopes. Among these differences include variation in software concerns, database sources, algorithms, and hardware which could implicate large discrepancies between apps, making it important to analyze and evaluate the accuracy, scope of application and potential use of each software. In this paper, eight apps were selected to identify 400 accurately identified plant photos, 100 photos being chosen from arid and semi-arid zones, temperate zones, tropical zones, and subtropical zones, respectively. In total, these photos belong to 122 families, 164 genera and 340 species, covering five growth forms of trees, shrubs, herbs, herbaceous vines and woody vines, as well as 23 national protected plant species. Accurate identification of species, genera and families was scored 4, 2 and 1 points, respectively. The software recognition ability was sorted according to total scores, and the results are as follows: HuaBangZhu, Baidu-Shitu, HuaBanLv, XingSe, Huahui-Shibie, Zhiwu-Shibie, Faxian-Shihua, Flower Recognition.

Key words: Plant recognition software, HuaBangZhu, Baidu-Shitu, HuaBanLv, XingSe, Huahui-Shibie, Zhiwu-Shibie, Faxian-Shihua, Flower recognition

许展慧, 刘诗尧, 赵莹, 涂文琴, 常诏峰, 张恩涛, 郭靖, 郑迪, 耿鋆, 顾高营, 郭淳鹏, 郭璐璐, 王静, 徐春阳, 彭钏, 杨腾, 崔梦琪, 孙伟成, 张剑坛, 刘皓天, 巴超群, 王鹤琪, 贾竞超, 武金洲, 肖翠, 马克平 (2020) 国内8款常用植物识别软件的识别能力评价. 生物多样性, 28, 524-533. DOI: 10.17520/biods.2019272.

Zhanhui Xu, Shiyao Liu, Ying Zhao, Wenqin Tu, Zhaofeng Chang, Entao Zhang, Jing Guo, Di Zheng, Jun Geng, Gaoying Gu, Chunpeng Guo, Lulu Guo, Jing Wang, Chunyang Xu, Chuan Peng, Teng Yang, Mengqi Cui, Weicheng Sun, Jiantan Zhang, Haotian Liu, Chaoqun Ba, Heqi Wang, Jingchao Jia, Jinzhou Wu, Cui Xiao, Keping Ma (2020) Evaluation of the identification ability of eight commonly used plant identification application softwares in China. Biodiversity Science, 28, 524-533. DOI: 10.17520/biods.2019272.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://www.biodiversity-science.net/CN/10.17520/biods.2019272

https://www.biodiversity-science.net/CN/Y2020/V28/I4/524

图/表 5

图1 国内8款常用植物识别软件总得分排序

Fig. 1 Total score ranking of eight commonly used plant identification application softwares in China

图2 国内8款常用植物识别软件在气候区的得分排序

Fig. 2 Score ranking by climate zone of eight commonly used plant identification application softwares in China

图3 国内8款常用植物识别软件对于不同生长型的识别结果得分

Fig. 3 Score of identification result of eight commonly used plant identification application softwares in China for different growth forms

图4 国内8款常用植物识别软件对于不同生长型识别到种(a)、属(b)、科(c)的比例

Fig. 4 Identification results of eight commonly used plant identification application softwares in China for different growth forms (a) Ratio of species identified; (b) Ratio of genus identified; (c) Ratio of family identified.

图5 国内8款常用植物识别软件对国家级保护植物(共23张图片)的识别结果

Fig. 5 Identification results of eight commonly used plant identification application softwares in China for national protected plants (23 pictures in total)

参考文献 15

[1]	Cao XY, Sun WM, Zhu YX, Qian X, Li XY, Ye N (2018) Plant image recognition based on family priority strategy. Journal of Computer Application, 38(11), 195-199. (in Chinese with English abstract)
	[ 曹香滢, 孙卫民, 朱悠翔, 钱鑫, 李晓宇, 业宁 (2018) 基于科优先策略的植物图像识别. 计算机应用, 38(11), 195-199.]
[2]	Joly A, Bonnet P, Goeau H, Barbe J, Selmi S, Champ J, Kowalski SD, Affouard A, Carre J, Molino JF, Boujemaa N, Barthelemy D (2016) A look inside the Pl@ntNet experience. Multimedia Systems, 22, 751-766.
[3]	Kumar N, Belhumeur PN, Biswas A, Jacobs DW, Kress WJ, Lopez I, Soares JVB (2012) Leafsnap: A computer vision system for automatic plant species identification. In: European Conference on Computer Vision (eds Fitzgibbon A, Lazebnik S, Perona P, Sato Y, Schmid C), pp. 502-516. Springer-Verlag, Berlin.
[4]	Li M (2018) “flower partners”: A new medium of knowledge service in the era of artificial intelligence. Publishing Reference, (8), 23-24. (in Chinese)
	[ 李敏 (2018) “花伴侣”: 人工智能时代知识服务的新媒介. 出版参考, (8), 23-24.]
[5]	Li MT, Zhang JT, Lei YH (2017) Influence analysis of Chinese plant science popularization app based on user demand—A case study of “HuabanLv” App. Science and Technology Communication, 9(22), 211-213. (in Chinese)
	[ 李珉葶, 张健涛, 雷耀华 (2017) 基于用户需求的国内植物类科普app影响力分析——以花伴侣App为例. 科技传播, 9(22), 211-213.]
[6]	Vesely O, Vild O, Stastny J (2014) A novel approach for the increase in student’s learning motivation. In: DIVAI 2014: The 10th International Scientific Conference on Distance Learning in Applied Informatics, pp. 529-536. Wolters Kluwer, Sturovo.
[7]	Wang JX (2019) Research on the communication effect of “huajian” article on shape-color App based on “5W” communication mode. Audio-Visual, 142(2), 131-132. (in Chinese).
	[ 王加希 (2019) 基于“5W”传播模式对形色App“花间”文章传播效果的探究. 视听, 142(2), 131-132.]
[8]	Wang L, Hong ZB, Fang LM, Chen X, Wu C (2018) Plant leaf recognition technology based on image analysis. Journal of Zhejiang A & F University, 35, 900-907. (in Chinese with English abstract)
	[ 王礼, 洪祖兵, 方陆明, 陈珣, 吴超 (2018) 基于iOS系统的观赏植物识别. 浙江农林大学学报, 35, 900-907.]
[9]	Wang Z, He JY (2017) “HuaBanLv”: Put the encyclopedia of plants into pocket. Greening and Life, (10), 30-33. (in Chinese)
	[ 王桢, 何建勇 (2017) 花伴侣: 把“植物大百科”装进小口袋. 绿化与生活, (10), 30-33. ]
[10]	Yuan Y, Huang ZQ, Ding SF, Liu YJ, Feng ZJ (2018) Research on sampling method of plants based on big data analysis. Modern Agricultural Science and Technology, (3), 149-151. (in Chinese with English abstract)
	[ 袁银, 黄稚清, 丁释丰, 刘永金, 冯志坚 (2018) 基于大数据分析的植物标本取样方法研究. 现代农业科技, (3), 149-151.]
[11]	Zhang J, Chen SB, Chen B, Du YJ, Huang XL, Pan XB, Zhang Q (2013) Citizen science: Integrating scientific research, ecological conservation and public participation. Biodiversity Science, 21, 738-749. (in Chinese with English abstract) DOI URL
	[ 张健, 陈圣宾, 陈彬, 杜彦君, 黄晓磊, 潘绪斌, 张强 (2013) 公众科学: 整合科学研究、生态保护和公众参与. 生物多样性, 21, 738-749.] DOI URL
[12]	Zhang JJ, Guo JH, Wang ZZ, Wang PB, Wu XS (2017) “Campus Plants”, Design and development of the plant-recognize software—Take Donghu campus of Zhejiang Agricultural and Forestry University as an example. South Agricultural Machinery, 48(5), 80-81. (in Chinese)
	[ 张健捷, 郭建辉, 王志真, 王拼搏, 吴小双 (2017) “校园植物通”定位识别软件设计与研发——以浙江农林大学东湖校区为例. 南方农机, 48(5), 80-81.]
[13]	Zhang N, Liu WP (2011) Plant leaf recognition technology based on image analysis. Application Research of Computers, 28, 4001-4007. (in Chinese with English abstract)
	[ 张宁, 刘文萍 (2011) 基于图像分析的植物叶片识别技术综述. 计算机应用研究, 28, 4001-4007.]
[14]	Zhang YZ, Li BY (2016) Remote rapid recognition method for plants. Journal of Computer Applications, 36(S2), 206-209. (in Chinese with English abstract)
	[ 张玉琢, 李柏依 (2016) 植物远程快速识别的方法. 计算机应用, 36(S2), 206-209.]
[15]	Zhong GL, Wang Q, Li MR, Lu Y (2015) Know-It-All—A recognition system of leaves. Internet of Things Technologies, 5(12), 6-7. (in Chinese)
	[ 钟刚亮, 王强, 李梦如, 卢遥 (2015) 百叶通——植物叶片识别系统. 物联网技术, 5(12), 6-7.]

国内8款常用植物识别软件的识别能力评价

Evaluation of the identification ability of eight commonly used plant identification application softwares in China

RichHTML

PDF (PC)

补充材料

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 15

相关文章 1

编辑推荐

Metrics

本文评价