-
[pdf]
[bibtex]@InProceedings{Hartley_2023_ICCV, author = {Hartley, Zane K. J. and Lind, Rob J. and Smith, Nicholas and Collison, Bob and French, Andrew P.}, title = {Unlocking Comparative Plant Scoring with Siamese Neural Networks and Pairwise Pseudo Labelling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops}, month = {October}, year = {2023}, pages = {678-684} }
Unlocking Comparative Plant Scoring with Siamese Neural Networks and Pairwise Pseudo Labelling
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.
Related Material