UTILE-Gen (UTILE-Gen)
Keywords: deeplearning, machinelearning, synthetic, data, generator, domainrandomization, label, mask, image, electronmiscroscopy, electronmicroscope,TEM,SEM
A versatile, agnostic, and configurable tool was developed to generate instance-segmented imaging datasets of nanoparticles. The synthetic generator tool employs domain randomization to expand the image/mask pairs dataset for training supervised deep learning models. The approach eliminates tedious manual annotation and allows the training of high-performance models for microscopy image analysis based on convolutional neural networks.
Publications
UTILE-Gen: Automated Image Analysis in Nanoscience Using Synthetic Dataset Generator and Deep Learning
Colliard-Granero A, Jitsev J, Eikerling M, Malek K, Eslamibidgoli M - ACS Nanoscience Au - 2023
Helmholtz Imaging Projects
2021: UTILE - Autonomous Image Analysis to Accelerate the Discovery and Integration of Energy Materials
