Six Main Tasks in Image Processing

Six Main Tasks in Image Processing

P. Kollmannsberger (HHU Düsseldorf), C. Lerche (FZ Jülich), T.-O. Buchholz (Friedrich Miescher Institute), Carsten Rother (Heidelberg University), Dagmar Kainmüller (Max Delbrück Center), Deborah Schmidt (Max Delbrück Center), Ullrich Köthe (Heidelberg University)

In this series of seminars, six key image processing tasks will be discussed, following a typical workflow in the image processing pipeline. Images are not always captured by a camera. Often, they must be tediously reconstructed from a series of projections or other non-image types of acquisitions. Different reconstruction algorithms allow for better image quality or can focus on specific properties of the objects under observation. Noise can be introduced at many steps in the image acquisition process. Denoising is therefore an essential step in most image processing workflows. Tracking individual objects over multiple time steps is a difficult task, but allows for the observation of temporal dynamics. Segmentation refers to the assignment of each pixel in an image to a specific category. In semantic segmentation, all pixels belonging to a cat are labeled "cat", and all pixels belonging to trees are labeled "tree". In instance segmentation, each pixel is additionally assigned to an object instance, making it possible to distinguish multiple cats and trees in an image. The visualization of otherwise difficult-to-interpret data, such as reconstructed 3D(+T) objects or high-dimensional image data, is essential for understanding the results. Finally, interpreting the results of AI-based image analysis algorithms is important: Why was a particular decision made? What structures in the images were responsible? What can AI tell us about the underlying problem?

This lecture series is held by imaging experts invited by the organizing schools and Helmholtz Imaging. The course consists of presentations and interactive discussions. It covers different imaging techniques in life sciences and soft matter. For an in-depth understanding of the subject, we recommend attending all lectures. Registration is mandatory for participation. Places are limited and in the case of overbooking, priority will be given to fellows (members) of the three schools. Participants demonstrating an attendance record of more than 70% can receive a certificate of participation.

04.05. P. Kollmannsberger (HHU), Six Main Tasks in Image Processing: an Overview
25.05. C. Lerche (FZJ), Tomographic Methods in Medical Imaging
T.-O. Buchholz (FMI), Restoring Noisy Microscopy Images
15.06. C. Rother (HCI), Tracking of Objects: from One to Many
29.06. D. Kainmüller (MDC), Machine Learning for Image Segmentation
06.07. D. Schmidt (MDC), Visualization
27.07. U. Köthe (IWR), Explainable Machine Learning

All lectures take place from 2:00 pm to 3:30 pm CET!

Contact for registration:
Further details and up-to-date information in case of changes:

Following the lecture series, there will be short workshops on image processing to complement the theoretical and methodological content of the lectures. The aim will be to provide on hands-on experience. The exact date, content, and registration link for the workshop will be announced in the lecture series.

Most of the IHRS BioSoft courses are open to all interested colleagues. If you participate in more than 75% of a course, you can receive a Certificate of Participation. To register for our newsletter, send us a short email with your name, your institute, and your position.

@ Aachen, Bonn, Cologne, Düsseldorf, and Jülich

Last Modified: 27.04.2023