Realistic Image Synthesis of Imperfect Specimens using Generative Networks
Deniz Neufeld, Tobias Würfl, Roland Gruber, Tobias Schön, Andreas Maier · e-Journal of Nondestructive Testing · 2019
This work explores conditional Generative Adversarial Networks (cGANs) as a tool to create realistic appearing CT slice images with pre-defined imperfections for the verification of automated defect detection algorithms. We aim to create an effective and efficient technique to simulate defects in CT slice images by implementing a new method which can simulate realistic textures and shapes. The problem is stated as an image to image translation task, where a new image is generated based on a given semantic description of the desired realistic image. This semantic description is a material based segmentation of the image with additional circular segments indicating the rough size and position of the intended defect. Based upon related work on cGANs, a convolutional neural network architecture is introduced and applied to our task. This method was trained and evaluated using 2D slice images derived from industrial CT datasets of automotive pistons. Our method showed promising results, producing convincing images in under one minute of computation with image resolutions of 256 by 256 pixels.