DWDominik Wolfschläger

Dominik Wolfschläger

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Dominik Wolfschläger has a total of 62 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    WZL-XCore as an Open-Source Versatile Platform for Industrial xCT Data Visualization and Analysis

    by Ahmed Baraka, Dominik Wolfschläger, Robert H.SChmitt

    In industrial X-ray Computed Tomography (xCT), a wide range of data types, such as projection images, three-dimensional (3D) voxel volumes, sectional images, surface meshes, and parameter logs, are typically generated and used for various analytical tasks. Navigating between these data types often requires multiple software tools that are often closed source and thus limited in flexibility, extensibility, and reproducibility. This work presents WZL-XCore, an open-source, unified software platform, designed to streamline the visualization, analysis, and conversion of diverse xCT data types within a single environment. XCore supports the display of full or downsampled projection images, 3D voxel volumes, 2D sectional images in multiple orientations, and surface meshes. Core features include 3D reconstruction from projection images, histogram-based brightness correction, material segmentation, coordinate system definition, 2D slice extraction, and surface mesh generation from 3D volumes. Additionally, it enables intuitive access to metadata, including system conditions (e.g., temperature, pressure) and acquisition parameters. While XCore uses established algorithms, its strength lies in its data versatility, and extensibility, as new features can be easily integrated into the modular framework. The software has been successfully tested with data from two different xCT systems and demonstrates promising results in terms of speed, compatibility, and usability. WZL-XCore fills a practical gap for researchers and engineers seeking an adaptable and open-source tool for xCT data exploration.

  • Open Access

    Compensating Projection Interpolation Artifacts in Sparse-View CT using a Two- Stage CNN with learnable Upscaling

    by Ammar Alsaffar, Faizan Ahmad, Ahmed Baraka, Steffen Kieß, Ct-Lab Ug, Jajnabalkya Guhathakurta, Dominik Wolfschläger, Robert H. Schmitt, Sven Simon

    X-ray Computed Tomography (CT) is a valuable tool for non-destructive testing, typically requiring thousands of projections to reconstruct high-quality images. For inline CT applications, however, scan time constraints necessitate reducing either the tube current or the number of projections. These limitations introduce significant noise and streak artifacts in reconstructed images. Building on existing approaches for artifact compensation, we propose a novel method to address missing projections through learned angular upscaling of sparse-view sinograms. Our approach modifies the standard U-Net architecture by integrating additional convolution and pixel-shuffle layers to recover missing data. During training, the upscaling kernel parameters are optimized to maximize alignment with ground-truth projections through three training phases. Even at an extreme sparsity factor of 20× fewer projections, our method demonstrates substantial improvement over interpolation-based upscaling deep learning techniques and achieves significant enhancement of sparse-view reconstructions for experimental results.

  • Open Access

    Improvement of Fine Structure Preservation in Denoising by Self-Supervised Learning Compared to Supervised Learning

    by Faizan Ahmad, Ahmed Baraka, HEITEC PTS GmbH, Matthias Fleßner, Ammar Alsaffar, Ct-Lab Ug, Jajnabalkya Guhathakurta, Guangpu Yang, Dominik Wolfschläger, Robert H. Schmitt, et al.

    Inline computed tomography (CT) enables rapid quality control but suffers from high noise due to short scan times. While deep learning offers powerful denoising capabilities, standard supervised models require clean reference data which is often unavailable in industrial settings and which tend to overfit training statistics, risking the suppression of anomalous features like defects. This paper investigates the generalization capabilities of self-supervised learning for preserving such unseen fine structures. We conduct a rigorous comparison between supervised (Noise2Clean) and self-supervised (Noise2Noise) denoising, utilizing the ReTWIN strategy to generate independent training pairs from single projection datasets. We derive a theoretical framework linking the gradient variance in Noise2Noise to implicit regularization that favors "flatter" minima, thereby enhancing generalization. Building on this, we propose Noise2Noise Edge-Enhanced (N2NEE), a novel method that modifies the training target with a spectral boost factor to amplify the gradient signal for spatially coherent high-frequency structures. Performance is evaluated via Modulation Transfer Function (MTF) analysis, simulation of artificial pores (1–7 voxels), and application to real-world aluminium casting scans. Quantitative analysis demonstrates that N2NEE achieves a spatial resolution (MTF50) of 14.518 lp/mm, nearly tripling the performance of supervised baselines (5.747 lp/mm). In controlled experiments, N2NEE successfully preserved 1-voxel pores that were obliterated by supervised models, while also retaining the geometric integrity of larger defects. Validation on industrial data confirmed that N2NEE significantly improves the contrast-to-noise ratio of natural porosity without generating artifacts. These results establish N2NEE as a robust, practical solution for inline CT metrology, eliminating the need for ground truth data while ensuring reliable defect detection.

  • Open Access

    A 3D Denoising Neural Network for Improved Surface Quality in Inline CT Metrology

    by University of Stuttgart, Faizan Ahmad, RWTH Aachen University, Ahmed Baraka, Steffen Kieß, Dominik Wolfschläger, Cesar Cardona Marin, Robert H. Schmitt, Sven Simon

    Inline computed tomography (CT) is becoming increasingly important for 100% inspection in production technology. Rapid scanning cycles, often limited to minutes, require a reduction in the number of X-ray projections, resulting in significantly reduced photon counts compared to laboratory-based systems. This reduction adversely impacts the peak signal-to-noise ratio (PSNR), increasing noise levels and compromising the accuracy of surface measurements essential for dimensional metrology. To address this challenge, we use neural network-based denoising techniques that enhance image quality without the need for clean reference data. Additionally, we introduce a novel surface quality assessment metric based on the Hausdorff distance, enabling real-time monitoring of surface accuracy during CT scans. Our approach uses a three-dimensional U-Net architecture and an innovative data augmentation method to optimize denoising performance. Experimental results demonstrate that the proposed methods significantly improve surface quality and PSNR in CT data within the time constraints necessary for real-time applications.

  • Open Access

    Distribution analysis in xCT data for identifying factors influencing uncertainty of repeated measurements

    by RWTH Aachen University, Lionel Kielhöfer, Dominik Wolfschläger, Robert H. Schmitt

    X-ray computed tomography (xCT) enables the measurement of inner and outer dimensional quantities by reconstructing the 3D model of an object. Due to limited understanding of the xCT acquisition and reconstruction processes modern guidelines typically estimate the measurement uncertainty using a standardized procedure based on repeated measurements and basic statistical analysis. In this work, we analyze voxel-wise distributions in the reconstructed volume and identifyclusters that reveal factors influencing measurement uncertainty in repeated measurements, with the eventual goal of reducing the number of CT scans required for accurate uncertainty estimation.

  • Open Access

    A Fast Metric Based on Marching Cubes and Hausdorff Distance for the Quality Assessment of 3D Volume Data for Computed Tomography Measurement Technology

    by RWTH Aachen University, Ahmed Baraka, University of Stuttgart, Faizan Ahmad, Kilian Geiger, Dominik Wolfschläger, Sven Simon, Robert H. Schmitt

    Inline X-ray Computed Tomography (xCT) offers a promising approach for the quality assurance and control of various workpieces during production. This is due to its capability to non-destructively inspect both internal and external structures. However, the typical duration of measurements, which extends to several hours, remains a limiting factor in practical applications. The sparse view xCT method, which limits the number of necessary projection images, can reduce this duration to a few minutes. Nonetheless, this reduction in time increases the overall measurement uncertainty, primarily due to streak artifacts. Therefore, the ability to efficiently quantify a quality measure sensitive to the number of projections captured during xCT measurement is crucial for determining the reliability of conducted measurements. This paper introduces a quality metric sensitive to streak artifacts, which uses a rapid surface determination algorithm known as marching cubes, followed by the computation of the Hausdorff distance between a reference surface and the extracted surface. An experimental study correlating the Hausdorff distance to the measurement uncertainty as a function of the utilized number of projections is conducted. The findings show that the Hausdorff distance increases for surfaces extracted from measurements taken with fewer projections. Additionally, by analyzing the correlation between the Hausdorff distance and the measurement uncertainty, quantified through the standard deviation of multiple extracted geometrical features from the measured test workpiece, a strong positive correlation is observed.

  • Open Access

    Reinforcement Learning Agent for Multi-Objective Online Process Parameter Optimization of Manufacturing Processes

    by Akshay Paranjape, Nahid Quader, Lars Uhlmann, Benjamin Berkels, Dominik Wolfschläger, Robert H. Schmitt, Thomas Bergs

    Optimizing manufacturing processes to reduce scrap and enhance process stability presents significant challenges, particularly when multiple conflicting objectives must be addressed concurrently. As the number of objectives increases, the complexity of the optimization task escalates. This difficulty is further intensified in online optimization scenarios, where optimal parameter settings must be delivered in real time within active production environments. In this work, we propose a reinforcement learning-based framework for the multi-objective optimization of manufacturing parameters, demonstrated through a case study on pinion gear manufacturing. The framework utilizes the Multi-Objective Maximum a Posteriori Optimization (MO-MPO) algorithm to train a reinforcement learning agent. A high-fidelity simulation of the pinion manufacturing process is constructed in Simufact, serving both data generation and validation purposes. The agent’s performance is assessed using a hold-out test set along with additional simulations of the physical process. To ensure the generalizability of the approach, further validation is performed using open-source manufacturing datasets and synthetically generated data. The results demonstrate the feasibility of the proposed method for real-time industrial deployment. Moreover, Pareto-optimality is verified via half-space analysis, emphasizing the framework’s effectiveness in managing trade-offs among competing objectives.


  • Open Access

    Generative AI in industrial machine vision: a review

    by Hans Aoyang Zhou, Dominik Wolfschläger, Constantinos Florides, Jonas Werheid, Hannes Behnen, Jan-Henrik Woltersmann, Tiago C. Pinto, Marco Kemmerling, Anas Abdelrazeq, Robert H. Schmitt

    Machine vision enhances automation, quality control, and operational efficiency in industrial applications by enabling machines to interpret and act on visual data. While traditional computer vision algorithms and approaches remain widely utilized, machine learning has become pivotal in current research activities. In particular, generative Artificial Intelligence (AI) demonstrates promising potential by improving pattern recognition capabilities, through data augmentation, increasing image resolution, and identifying anomalies for quality control. However, the application of generative AI in machine vision is still in its early stages due to challenges in data diversity, computational requirements, and the necessity for robust validation methods. A comprehensive literature review is essential to understand the current state of generative AI in industrial machine vision, focusing on recent advancements, applications, and research trends. Thus, a literature review based on the PRISMA guidelines was conducted, analyzing over 1,200 papers on generative AI in industrial machine vision. Our findings reveal various patterns in current research, with the primary use of generative AI being data augmentation, for machine vision tasks such as classification and object detection. Furthermore, we gather a collection of application challenges together with data requirements to enable a successful application of generative AI in industrial machine vision. This overview aims to provide researchers with insights into the different areas and applications within current research, highlighting significant advancements and identifying opportunities for future work.


  • Open Access

    A Comparative Study of Supervised and Self-Supervised Denoising Techniques for Defect Segmentation in Industrial CT Imaging

    by Fraunhofer Institute for Integrated Circuits (IIS), Virginia Florian, Leiden Univeristy, Jiayang Shi, Willem Jan Palestijn, Daniël M. Pelt, K. Joost Batenburg, Thomas Lang, University of Passau, Christoph Heinzl, et al.

    X-ray computed tomography (CT) is a powerful imaging tool for defect detection, segmentation and feature extraction in industrial applications as it enables non-destructive evaluation. The presence of artifacts and noise, however, imposes difficulties on the defect detection due to low contrast between defects and material. Different methods, the most recent ones based on deep learning, have been proposed to address both CT artifacts and noise. In this work, three state-of-the-art denoising techniques, namely BM3D, a supervised UNet and Noise2Inverse are compared with a novel approach based on a set of CNNs applied at different stages of the CT data acquisition pipeline. The comparison is done regarding the capabilities of the methods in terms of image quality enhancement as a preprocessing step in CT-based data analysis before performing defect segmentation.


  • Open Access

    Surface Quality Monitoring and Improvement for Dimensional Metrology in Inline CT by Denoising with Neural Networks and Fast Surface Quality Metric

    by University of Stuttgart, Faizan Ahmad, RWTH Aachen University, Ahmed Baraka, César Cardona-Marin, Steffen Kieß, Dominik Wolfschläger, Robert H. Schmitt, Sven Simon

    Inline computed tomography (CT) is becoming increasingly important for 100% inspection in production technology. However, the short machine cycle times—often just a few minutes—require either fewer X-ray projections or shorter detector exposure times, significantly reducing photon counts by one to two orders of magnitude compared to lab-based CT systems. This reduction leads to a decrease in the signal-to-noise ratio (SNR) by at least an order of magnitude, thereby increasing noise and diminishing the accuracy of surface measurements essential for metrology. To address this challenge, denoising methods based on neural networks have been used, outperforming traditional algorithms such as BM3D. In this work, we investigate the Noise2Noise method, which trains a neural network using pairs of noisy images, eliminating the need for clean ground truth data—typically unavailable in CT. Furthermore, we propose a fast surface quality metric based on the marching cubes algorithm and Hausdorff distance to enable realtime monitoring of voxel dataset quality during continuous CT scans, as required in inline CT. This metric demonstrates a strong correlation with measurement errors associated with surface quality degradation due to noise. Experimental results show that our proposed methods significantly enhance surface quality and SNR of full CT data volumes, achieving denoising within minutes, as required for inline CT applications.