Free and open-source software for object detection, size, and colour determination for use in plant phenotyping

Plant Methods · 4 authors, 3 centres

AI SUMMARY

FIDELITY 100%

This summary was generated by AI from a single paper. It has not been reviewed by a clinician and is not clinical advice. Verify against the source before acting on it.

AGENT 01 · STRUCTURED SUMMARY

TRACE TO SOURCE

“

TL;DR

The study provides free Python scripts for plant phenotyping, demonstrating their ability to accurately predict lycopene content in tomatoes and chlorophyll content in basil leaves using image analysis.

Full summary

779 CHARS

The paper presents a set of free, open-source Python scripts for plant phenotyping, including background and colour correction, object detection, and size and colour measurement. The scripts were validated using two examples: predicting lycopene content in tomatoes and chlorophyll content in basil leaves. Tomatoes were imaged under four lighting conditions with three cameras, showing colour correction reduced error. All cameras could predict lycopene, but only the DSLR camera accurately predicted content outside the training set. Basil chlorophyll was accurately predicted with a DSLR camera in a lightbox, but validation showed underprediction for out-of-sample leaves, highlighting the need for comprehensive training data. The method is fast, cheap, and non-destructive.

STUDY TYPE

other

SPECIALTY

research methods

SUMMARISED BY

AI pipeline

FIDELITY CHECK

100% · A

ORIGINAL PAPER

PMC10647133

Free and open-source software for object detection, size, and colour determination for use in plant phenotyping

Plant Methods

READ THE FULL PAPER

ABSTRACT

Abstract Background Object detection, size determination, and colour detection of images are tools commonly used in plant science. Key examples of this include identification of ripening stages of fruit such as tomatoes and the determination of chlorophyll content as an indicator of plant health. While methods exist for determining these important phenotypes, they often require proprietary software or require coding knowledge to adapt existing code. Results We provide a set of free and open-source Python scripts that, without any adaptation, are able to perform background correction and colour correction on images using a ColourChecker chart. Further scripts identify objects, use an object of known size to calibrate for size, and extract the average colour of objects in RGB, Lab, and YUV colour spaces. We use two examples to demonstrate the use of these scripts. We show the consistency of these scripts by imaging in four different lighting conditions, and then we use two examples to show how the scripts can be used. In the first example, we estimate the lycopene content in tomatoes ( Solanum lycopersicum ) var. Tiny Tim using fruit images and an exponential model to predict lycopene content. We demonstrate that three different cameras (a DSLR camera and two separate mobile phones) are all able to model lycopene content. The models that predict lycopene or chlorophyll need to be adjusted depending on the camera used. In the second example, we estimate the chlorophyll content of basil ( Ocimum basilicum ) using leaf images and an exponential model to predict chlorophyll content. Conclusion A fast, cheap, non-destructive, and inexpensive method is provided for the determination of the size and colour of plant materials using a rig consisting of a lightbox, camera, and colour checker card and using free and open-source scripts that run in Python 3.8. This method accurately predicted the lycopene content in tomato fruit and the chlorophyll content in basil leaves. Supplementary Information The online version contains supplementary material available at 10.1186/s13007-023-01103-0. Keywords: Colour, Chlorophyll, Lycopene, FOSS, Object detection, Open-source

CITATION EXPORT

Harry Charles Wright, Frederick Antonio Lawrence, Anthony John Ryan et al.. Free and open-source software for object detection, size, and colour determination for use in plant phenotyping. Plant Methods. (2023). https://doi.org/10.1186/s13007-023-01103-0

AUTHORS

4 · 3 CENTRES

Harry Charles Wright, Frederick Antonio Lawrence, Anthony John Ryan, Duncan Drummond Cameron

1Department of Chemistry, The University of Sheffield, Sheffield, S3 7HF UK
2Department of Chemistry, Imperial College London, London, SW7 2AZ UK
3Department of Earth and Environmental Sciences and Manchester Institute of Biotechnology, The University of Manchester, John Garside Building, Manchester, M1 7DN UK