Deep learning increases the availability of organism photographs taken by citizens in citizen science programs.
Deep learning increases the availability of organism photographs taken by citizens in citizen science programs.
复制标题
DOI：
10.1038/s41598-022-05163-5
复制
发表时间：
2022-01-24
影响因子：
4.6
通讯作者：
Okatani T
中科院分区：
文献类型：
--
作者：
Suzuki-Ohno Y;Westfechtel T;Yokoyama J;Ohno K;Nakashizuka T;Kawata M;Okatani T
使用生物体照片的公民科学计划已经变得流行，但有两个问题与照片有关。一个问题是照片质量低。在户外拍摄的照片中识别物种是很费力的，因为它们是焦点，部分不可见的，或者在不同的照明条件下。另一个是非专家很难识别物种。生物通常具有种间相似性和种内变异，这阻碍了非专家的物种鉴定。深度学习解决了这些问题，并增加了生物体照片的可用性。我们训练了一个深度卷积神经网络Xception，使用市民拍摄的各种质量的蜜蜂照片来识别蜜蜂物种。这些蜜蜂属于2个蜜蜂种和10个熊蜂种，具有种间相似性和种内变异。我们研究了生物学家和深度学习对物种识别的准确性。Xception的物种识别准确率（83.4%）远高于生物学家（53.7%）。当我们分组蜜蜂照片的不同颜色所产生的种内变异，除了物种，物种识别的准确性提高到84.7%。与深度学习和专家的合作将提高物种识别的可靠性及其在科学研究中的应用。
Citizen science programs using organism photographs have become popular, but there are two problems related to photographs. One problem is the low quality of photographs. It is laborious to identify species in photographs taken outdoors because they are out of focus, partially invisible, or under different lighting conditions. The other is difficulty for non-experts to identify species. Organisms usually have interspecific similarity and intraspecific variation, which hinder species identification by non-experts. Deep learning solves these problems and increases the availability of organism photographs. We trained a deep convolutional neural network, Xception, to identify bee species using various quality of bee photographs that were taken by citizens. These bees belonged to two honey bee species and 10 bumble bee species with interspecific similarity and intraspecific variation. We investigated the accuracy of species identification by biologists and deep learning. The accuracy of species identification by Xception (83.4%) was much higher than that of biologists (53.7%). When we grouped bee photographs by different colors resulting from intraspecific variation in addition to species, the accuracy of species identification by Xception increased to 84.7%. The collaboration with deep learning and experts will increase the reliability of species identification and their use for scientific researches.
登录
查看更多内容
来自Argus眼的公民的生物多样性数据挖掘：Lepomis acrochirus acrochirus rafinesque的第一个非法介绍记录，基于Twitter信息，在日本1819年。
影响因子：
1.3
作者：
Miyazaki Y;Teramura A;Senou H
通讯作者：
Senou H
影响因子：
4.8
作者：
Conn, Paul B.;McClintock, Brett T.;Boveng, Peter L.
通讯作者：
Boveng, Peter L.
影响因子：
3.7
作者：
Falk, Steven;Foster, Gemma;Smith, Barbara
通讯作者：
Smith, Barbara
影响因子：
3.3
作者：
PLOWRIGHT, RC;OWEN, RE
通讯作者：
OWEN, RE
影响因子：
4.6
作者：
Austen GE;Bindemann M;Griffiths RA;Roberts DL
通讯作者：
Roberts DL