Technical framework of advanced volumetric sub-μ-CT wood imaging integrated with adaptable deep-learning-based wood species classification: initial evaluation on softwood and hardwood data

What is it about?

The presented work discusses the development of an automated deep learning system that classifies 3D volumetric CT scans of wood samples and its assessment with a conceptual hardwood-softwood dataset. We conducted tests to evaluate the systems performance with respect to training data splitting strategies and input data alterations. The goal of this automated pipeline is to improve the accuracy and efficiency of wood identification, potentially enabling the full automatization of wood identification. The results demonstrate the system's potential for real-world use, highlighting its ability to handle volumetric data automatically.

Featured Image