PRMI: A Dataset of Minirhizotron Images for Diverse Plant Root Studies

Weihuang Xu, Guohao Yu, Yiming Cui, Romain Gloaguen, Alina Zare, Jason Bonnette, Joel Reyes-Cabrera, Ashish B Rajurkar, Diane Rowland, Roser Matamala, Julie D. Jastrow, Thomas Juenger, Felix Fritschi

Keywords: dataset, plant root, root system architecture, minirhizotron images, segmentation, weakly-supervised learning, transfer learning

TL;DR: We introduce a large-scale dataset of plant root minirhizotron images with manual annotations to fill the gap of the lack of public sizeable MR image dataset and ntroduce the computer vision community to this problem domain.

Abstract: Understanding a plant's root system characteristics is crucial for a variety of plant science problem domains including sustainability and climate adaptation. Minirhizotron (MR) technology is a widely-used approach for phenotyping root systems non-destructively by capturing root imagery over time. Precisely segmenting roots from the soil in MR imagery is a critical step in studying root system traits features. In this paper, we introduce a large-scale dataset of plant root images captured by MR technology. In total, there are more than 72K RGB root images across six different species including cotton, papaya, peanut, sesame, sunflower, and switchgrass in the dataset. The images span a variety of conditions including varied root age, root structures, soil types, and depths in the soil. All of the images have been annotated with weak image-level labels indicating whether each image contains roots or not. The image-level labels can be used to support weakly supervised learning in plant root segmentation tasks. In addition, 63K images have been manually annotated to generate pixel-level binary masks indicating whether each pixel corresponds to root or not. These pixel-level binary masks can be used as ground truth for supervised learning in semantic segmentation tasks. By introducing this dataset, we aim to facilitate the automatic segmentation of roots and the research of in vivo root system characteristics with deep learning and other image analysis algorithms.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/prmi-a-dataset-of-minirhizotron-images-for/code)