Root Identification in Minirhizotron Imagery with Multiple Instance Learning
Authors:
- Guohao YuGYGuohao Yu
- Alina ZareAZAlina Zare
- Hudanyun ShengHSHudanyun Sheng
- Roser MatamalaRMRoser Matamala
- Joel Reyes-CabreraJRJoel Reyes-Cabrera
- Felix B. FritschiFFFelix B. Fritschi
- Thomas E. JuengerTJThomas E. Juenger
Preprint
Abstract
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 (multiple instance adaptive cosine coherence estimator, multiple instance support vector machine, multiple instance learning with randomized trees) 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.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Overcoming small minirhizotron datasets using transfer learningComputers and Electronics in Agriculture, 2020
- SegRoot: A high throughput segmentation method for root image analysisComputers and Electronics in Agriculture, 2019
- Generalized Dictionaries for Multiple Instance LearningInternational Journal of Computer Vision, 2015
- Fine root biomass and turnover of two fast-growing poplar genotypes in a short-rotation coppice culturePlant and Soil, 2013
- Variation in root architecture among switchgrass cultivars impacts root decomposition ratesSoil Biology and Biochemistry, 2013
- Random set framework for multiple instance learningInformation Sciences, 2011
- MIForests: Multiple-Instance Learning with Randomized Trees2010
- Rapid automated detection of roots in minirhizotron imagesMachine Vision and Applications, 2008
- Detecting and Measuring Fine Roots in Minirhizotron Images Using Matched Filtering and Local Entropy ThresholdingMachine Vision and Applications, 2006
- Solving the multiple instance problem with axis-parallel rectanglesArtificial Intelligence, 1997