Improved image recognition via Synthetic Plants using 3D Modelling with Stochastic Variations

¹ School of Science, Edith Cowan University, 270 Joondalup Drive, Joondalup, Australia
² Department of Primary Industry Resource Development, South Perth, Australia

^* Corresponding author: d.cook@ecu.edu.au

Abstract

This research extends previous plant modelling using L-systems by means of a novel arrangement comprising synthetic plants and a refined global wheat dataset in combination with a synthetic inference application. The study demonstrates an application with direct recognition of real plant stereotypes, and augmentation via a plant-wide stochastic growth variation structure. The study showed that the automatic annotation and counting of wheat heads using the Global Wheat dataset images provides a time and cost saving over traditional manual approaches and neural networks. This study introduces a novel synthetic inference application using a plant-wide stochastic variation system, resulting in improved structural dataset hierarchy. The research demonstrates a significantly improved L-system that can more effectively and more accurately define and distinguish wheat crop characteristics.