该数据集包含 5,539 张作物和杂草幼苗的图像。如上图所示，图像分为 12 个类别。这些类别代表丹麦农业中的常见植物物种。每个类都包含显示植物不同生长阶段的 rgb 图像。图像大小各异，均为 png 格式。

The V1 version of this dataset was used in the Plant Seedling Classification playground competition here on Kaggle. This is the V2 version. Some samples in V1 contained multiple plants. The dataset’s creators have now removed those samples.

Citation

Paper: A Public Image Database for Benchmark of Plant Seedling Classification Algorithms

https://arxiv.org/abs/1711.05458

Acknowledgements

Many thanks to the Computer Vision and Signal Processing Group, Department of Engineering – Aarhus University, for making this dataset publicly available.

https://vision.eng.au.dk/plant-seedlings-dataset/

Inspiration

• Use this dataset to build a model to classify crop and weed seedlings.

• Start a school or university project to create a dataset of crop and weed seedling images in a local farming community. Then create a weed detection model based on your dataset. Deploy your model as a web app so farmers can use it.

• Can a ground based weed detector be built using an Arduino? This video may give you some ideas: https://www.youtube.com/watch?v=O_Q1WKCtWiA

Header photo by Francesco Gallarotti on Unsplash.