Image Processing

Mathematical Models and Image Analysis Algorithms for Industry

The department »Image Processing« develops mathematical models and image analysis algorithms and converts them into software suitable for industrial use, primarily in production. The application areas include in particular sophisticated surface inspection and analysis of microstructures. We have been developing and distributing software for 2D and 3D image analysis for over 15 years and develop both new methods and domain-specific machine learning algorithms.

In recent years, one focus in machine learning has been on image processing for production and industry. Methods such as  »Deep Learning« require a high number of annotated data, for example of the defects to be found in a production plant. Now, however, in a well-functioning manufacturing plant, there are many images of defect-free products, but only a few of products with defects. We therefore often use hybrids of the »classical« parameterizable methods (filters, morphology, edge detectors) and machine learning. In addition to solutions for production, we also offer »typical« machine learning solutions for image processing. These are often projects in which very large amounts of image data are processed manually and this process is to be automated by software.

Another focus is microstructure analysis. The microstructure of modern materials significantly determines their macroscopic material properties. We develop algorithms for characterization and stochastic modeling of such microstructures based on image data, e.g. from CT, FIB-REM, SEM.

Our products serve the deeper understanding of the complex geometry and structure-property relationships in materials and thus open up new possibilities such as optimization of material properties by virtual material design. Based on the parameters obtained from image data, stochastic geometry models are fitted to the real microstructures, which reflect the geometric structure relationships well and thus simplify or enable numerical simulations in the first place.

The latest research field in image processing is virtual inspection planning. Here, the complete, physically correct simulation of inspection systems is planned. The objective is a software infrastructure that simulates the complete inspection environment. This includes not only the properties of the inspection piece but also the properties of all hardware components (illumination, camera, optics, etc.).

Fields of Activity

In close collaboration with partners from industry and research, the department realizes custom solutions in the field of image and signal processing in the areas listed below:

 

Surface and Material Characterization

We develop algorithms and software for the spatial analysis of material structures using 2D and 3D images.

 

Quality Assurance and Optimization

Here we focus on the development of efficient and innovative image-based complete solutions for automated quality assurance.

 

Virtual Inspection Planning

Online inspection systems have proven themselves in many production environments. But what happens when the components are complicated? How can your testing be automated? Answers are provided by virtual inspection planning.

 

Industrial Image Learning

Main emphasis is Machine Learning in Image Processing for Production and Industry.

 

Condition Monitoring and Predictive Maintenance

In cooperation with other departments, we support the efficient maintenance of production facilities.

 

Quantum Image Processing

In the context of our focus on »Quantum Image Processing« we investigate to what extent quantum computers (QC) can solve classical image processing problems.