Unlocking Comparative Plant Scoring with Siamese Neural Networks and Pairwise Pseudo Labelling

Hartley, Zane K.J.; Lind, Rob J.; Smith, Nicholas; Collison, Bob; French, Andrew P.

Abstract

Phenotypic assessment of plants for herbicide discovery is a complex visual task and involves the comparison of a non-treated plant to those treated with herbicides to assign a phytotoxicity score. It is often subjective and difficult to quantify by human observers. Employing novel computer vision approaches using neural networks in order to be non-subjective and truly quantitative offers advantages for data quality, leading to improved decision making.In this paper we present a deep learning approach for comparative plant assessment using Siamese neural networks, an architecture that takes pairs of images as inputs, and we overcome the hurdles of data collection by proposing a novel pseudo-labelling approach for combining different pairs of input images. We demonstrate a high level of accuracy with this method, comparable to human scoring, and present a series of experiments grading Amaranthus retroflexus weeds using our trained model.

Citation

Hartley, Z. K., Lind, R. J., Smith, N., Collison, B., & French, A. P. (2023, October). Unlocking Comparative Plant Scoring with Siamese Neural Networks and Pairwise Pseudo Labelling. Presented at 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW), Paris, France

• Presentation Conference Type: Edited Proceedings
• Conference Name: 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
• Start Date: Oct 2, 2023
• End Date: Oct 6, 2023
• Acceptance Date: Oct 2, 2023
• Online Publication Date: Dec 25, 2023
• Publication Date: Dec 25, 2023
• Deposit Date: Feb 5, 2025
• Publicly Available Date: Apr 15, 2024
• Publisher: Institute of Electrical and Electronics Engineers
• Peer Reviewed: Peer Reviewed
• Pages: 678-684
• Series ISSN: 2473-9944
• Book Title: 2023 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
• ISBN: 979-8-3503-0745-0
• DOI: https://doi.org/10.1109/iccvw60793.2023.00075
• Public URL: https://nottingham-repository.worktribe.com/output/29539846
• Publisher URL: https://ieeexplore.ieee.org/document/10350460
• Other Repo URL: https://openaccess.thecvf.com/content/ICCV2023W/CVPPA/papers/Hartley_Unlocking_Comparative_Plant_Scoring_with_Siamese_Neural_Networks_and_Pairwise_ICCVW_2023_paper.pdf