top of page

High-throughput and accurate phenotyping for maize

Fast, simple and reliable access to phenotypic variables of interest.

 

We leverage AI systems to bring you the best possible measurements for hard-to-reach traits, usually only accessible via time-consuming and labor-intensive means.

They already trust us

Earbox benefits

Ear and grain data

ear data v4 Ear WEB.png

Place your cursor here

ear data v4 WEB.png

The data are produced at 2 scales:

  • ears

  • grains along the ear


For ears, all data are measured or calculated for each of the 6 images captured by the system. The 6 images can be considered as repetitions, and averaged to obtain values at the ear scale, and indices (e.g. standard deviation, etc.) concerning their stability around the ear.


For grains, it is possible to make averages according to their "level" (cohort number) from the base of the ear. You can also process grain data according to their position (cm) in relation to the base of the ear.

Data
Yield components

Access to yield components

yield components_final.png
yield components_final_focus.png

The EARBOX system has been build to fit into phenotyping pipelines of experimental stations, while speeding it, complementing it and scaling it to new heights:

  • More data : to increase the power of genotypic studies and most statistical analyses

  • Accurate data : to correctly characterise varieties, differences and similarities between them, biotic and abiotic stresses

  • Standardized data : to regroup, merge and treat large datasets from multi-site trials

Fast and Friendly

Developed with the French agronomic institute
(INRAE)

Acquisition time <30sec. (~26sec.)
 

Base on open source and affordable technologies
 

Flexible ear identification: by ear or by plot

Automatic check for duplicates and acquisition inconsistencies

Fast & friendly

Developed by scientists for scientists and professionals:

Our development methodology shows our rigor and our requirement to offer research a useful tool that can feed tomorrow's reflections and experiments. In this logic, the methodologies of phenotypic data extraction are presented in the method article (2022 - Plant Methods): Earbox, an open tool for high-throughput measurement of the spatial organization of maize ears and inference of novel traits .We scanned and trained a neural network on the widest possible phenotypic diversity, so that it would be able to segment maize kernels regardless of their appearance. We then developed an algorithm to extract in post-processing all the phenotypic data, which were all compared to manual data or via other machines.


This project was initiated in partnership with the INRAE of Montpellier (France) and more particularly the LEPSE (Laboratory of ecophysiology of plants under environmental stress) and the experimental station of Mauguio, with whom the EARBOX was defined, tested, validated and adopted.

Accurate and reliable data

Validation & accuracy

Specifications

6 ears version (for French market only)

Image cabine

  • 6 ears slot

  • Cameras: Pi Noir Camera V2 x2

  • 2 LED spectra: CRI 90 visible and infrared 940nm

Hardware

  • System: Raspberry PI x2

  • 2 stepper motors: rollers and door

  • 21" screen