Skip to main content

Research Repository

Advanced Search

Towards Low-Cost Image-based Plant Phenotyping using Reduced-Parameter CNN.

Atanbori, John; Chen, Feng; French, Andrew P; Pridmore, Tony


John Atanbori

Feng Chen

Andrew P French

Tony Pridmore


© 2018. The copyright of this document resides with its authors. Segmentation is the core of most plant phenotyping applications. Current state-of-the-art plant phenotyping applications rely on deep Convolutional Neural Networks (CNNs). However, these networks have many layers and parameters, increasing training and test times. Phenotyping applications relying on these deep CNNs are also often difficult if not impossible to deploy on limited-resource devices. We present our work which investigates parameter reduction in deep neural networks, a first step to moving plant phenotyping applications in-field and on low-cost devices with limited resources. We re-architect four baseline deep neural networks (creating what we term "Lite CNNs") by reducing their parameters whilst making them deeper to avoid the problem of overfitting. We achieve state-of-the-art, comparable performance on our "Lite" CNNs versus the baselines. We also introduce a simple global hyper-parameter (alpha) that provides an efficient trade-off between parameter-size and accuracy.


Atanbori, J., Chen, F., French, A. P., & Pridmore, T. (2018, September). Towards Low-Cost Image-based Plant Phenotyping using Reduced-Parameter CNN. Paper presented at British Machine Vision Conference 2018, BMVC 2018, Northumbria University

Presentation Conference Type Conference Paper (unpublished)
Conference Name British Machine Vision Conference 2018, BMVC 2018
Conference Location Northumbria University
Start Date Sep 4, 2018
End Date Sep 6, 2018
Publication Date Jan 1, 2019
Deposit Date Nov 13, 2019
Public URL