Rzanny Michael, Mäder Patrick, Deggelmann Alice, Chen Minqian, Wäldchen Jana
1Department of Biogeochemical Integration, Max Planck Institute for Biogeochemistry, Hans-Knöll-Str. 10, Jena, Germany.
2Software Engineering for Safety-Critical Systems Group, Technische Universität Ilmenau, Ehrenbergstr. 20, 98693 Ilmenau, Germany.
Plant Methods. 2019 Jul 23;15:77. doi: 10.1186/s13007-019-0462-4. eCollection 2019.
Deep learning algorithms for automated plant identification need large quantities of precisely labelled images in order to produce reliable classification results. Here, we explore what kind of perspectives and their combinations contain more characteristic information and therefore allow for higher identification accuracy.
We developed an image-capturing scheme to create observations of flowering plants. Each observation comprises five in-situ images of the same individual from predefined perspectives (entire plant, flower frontal- and lateral view, leaf top- and back side view). We collected a completely balanced dataset comprising 100 observations for each of 101 species with an emphasis on groups of conspecific and visually similar species including twelve Poaceae species. We used this dataset to train convolutional neural networks and determine the prediction accuracy for each single perspective and their combinations via score level fusion. Top-1 accuracies ranged between 77% (entire plant) and 97% (fusion of all perspectives) when averaged across species. Flower frontal view achieved the highest accuracy (88%). Fusing flower frontal, flower lateral and leaf top views yields the most reasonable compromise with respect to acquisition effort and accuracy (96%). The perspective achieving the highest accuracy was species dependent.
We argue that image databases of herbaceous plants would benefit from multi organ observations, comprising at least the front and lateral perspective of flowers and the leaf top view.
用于植物自动识别的深度学习算法需要大量精确标注的图像才能产生可靠的分类结果。在此，我们探讨何种视角及其组合包含更多特征信息，从而实现更高的识别准确率。
我们开发了一种图像采集方案来创建开花植物的观测数据。每次观测包括从预定义视角（整株植物、花朵正视图和侧视图、叶片顶面和背面视图）对同一植株拍摄的五张原位图像。我们收集了一个完全平衡的数据集，包含101个物种中每个物种的100次观测数据，重点关注同物种和视觉上相似的物种组，包括12种禾本科植物。我们使用该数据集训练卷积神经网络，并通过分数级融合确定每个单一视角及其组合的预测准确率。跨物种平均时，top-1准确率在77%（整株植物）至97%（所有视角融合）之间。花朵正视图的准确率最高（88%）。融合花朵正视图、花朵侧视图和叶片顶视图在采集工作量和准确率方面达到了最合理的折衷（96%）。准确率最高的视角因物种而异。
我们认为草本植物的图像数据库将受益于多器官观测，至少包括花朵的正面和侧面视角以及叶片顶视图。
