The seminars take place on the Montpellier Institut Agro/INRA Campus of La Gaillarde (2, place P. Viala Montpellier)

Thursday june 9, 2022 – Amphi 206

Valèrio Giuffrida

Edinburgh Napier University

Learning to Count Leaves of Plants

The collection of plant phenotyping traits has been done manually in the past, which is a tedious, error-prone, and time-consuming task. For this reason, image-based plant phenotyping is used to facilitate the measurement of plant traits with algorithms. However, the lack of robust software to extract reliable phenotyping traits from plant images has created a bottleneck.

In this presentation, I will showcase one of the plant image analysis problems that I have been working on for several years: the estimation of the total number of leaves in rosette plants. The leaf count is a sought-after plant trait, as it is related to the plant development stage, health, yield potential, and flowering time. In my work, I addressed the estimation of the number of leaves in an image as a global regression problem. In this context, the learning of the algorithm is relaxed to the prediction of a single number (the leaf count) and the collection of labelled datasets is easy enough to be also performed by non-experts.

I will show you an award-winning approach to leaf counting using a traditional machine learning approach. After that, I will introduce you to deep learning approaches and how they contributed to a more reliable and accurate leaf count prediction.

Contact : Tou-Cheu Xiong

Contacts IBIP :

Sabine Zimmermann (sabine.zimmermann@cnrs.fr)
Alexandre Martiniere (alexandre.martiniere@cnrs.fr)

Aude Coupel-Ledru (aude.coupel-ledru@inrae.fr)

Chantal Baracco (chantal.baracco@inrae.fr)