Root Identification in Minirhizotron Imagery with Multiple Instance Learning


In this paper, multiple instance learning (MIL) algorithms to automatically perform root detection and segmentation in minirhizotron imagery using only image-level labels are proposed. Root and soil characteristics vary from location to location, thus, supervised machine learning approaches that are trained with local data provide the best ability to identify and segment roots in minirhizotron imagery. However, labeling roots for training data (or otherwise) is an extremely tedious and time-consuming task. This paper aims to address this problem by labeling data at the image level (rather than the individual root or root pixel level) and train algorithms to perform individual root pixel level segmentation using MIL strategies. Three MIL methods (MI-ACE, miSVM, MIForests) were applied to root detection and compared to non-MIL approches. The results show that MIL methods improve root segmentation in challenging minirhizotron imagery and reduce the labeling burden. In our results, multiple instance support vector machine outperformed other methods. The multiple instance adaptive cosine coherence estimator algorithm was a close second with an added advantage that it learned an interpretable root signature which identified the traits used to distinguish roots from soil and did not require parameter selection.






G. Yu, A. Zare, H. Sheng, R. Matamala, J. Reyes-Cabrera, F. B. Fritschi and T.E. Juenger, “Root Identification in Minirhizotron Imagery with Multiple Instance Learning,” in Machine Vision and Applications, vol. 31, 2020.
title={Root Identification in Minirhizotron Imagery with Multiple Instance Learning},
author={Guohao Yu and Alina Zare and Hudanyun Sheng and Roser Matamala and Joel Reyes-Cabrera and Felix B. Fritschi and Thomas E. Juenger},  
journal = {Machine Vision and Applications},  
volume = {31},