© Alumni-Büro Universität Siegen

In a dark room with black walls and ceilings, an array of small green LEDs illuminates a tiny biological specimen. The pattern of the array changes. And changes again. Each time it changes, a picture is taken. Prof. Dr. Onofre Martorell from the University of the Balearic Islands, Mallorca, explains: “By using artificial intelligence—or, more precisely, machine learning algorithms—we are able to automatically combine the data from the various images taken with different illumination patterns and produce a single super-resolution image that reveals the specimen’s fine structures, which would otherwise be invisible.” A mathematician by training, Martorell specializes in the algorithmic merging of images. In 2022, while pursuing his Ph.D. under Prof. Dr. Antoni Buades at the University of the Balearic Islands in Mallorca, he was looking for an internship abroad. A colleague in Mallorca introduced him to Prof. Dr. Michael Möller, Professor of Computer Vision in the Department of Computer Science and Electrical Engineering at the University of Siegen. Martorell and Möller got along extremely well right from the start. Not only did they both earn their doctoral degrees in applied mathematics—giving them a theoretical background—but they also share a passion for image processing and reconstruction, where they algorithmically combine and enhance images taken with consumer-grade cameras or reconstruct images that cannot be captured directly. Their collaboration has continued actively since Prof. Martorell’s initial visit, and when Möller received funding for the research unit Learning to Sense (L2S)—selected in a special call as one of only eight AI-related research units by the German Research Foundation—the opportunity arose to expand their research focus to include an experimental component. Enter Prof. Ivo Ihrke’s group, which works on Computational Sensorics & Communications Engineering at the University of Siegen’s Center for Sensor Systems (ZESS).

The LEDs change their pattern again, and now, on a computer screen connected to the experimental setup, an abstract image appears in incredibly high resolution, revealing intricate details. Onofre’s collaboration partner from the research unit, Dr. John Meshreki, takes a closer look at what he explains is a cross-section of a mushroom. Meshreki, a physicist by training, currently works as part of the “Learning to Sense” research unit within Prof. Ihrke’s group and is the lead researcher behind the Fourier Ptychography Microscopy (FPM) setup being used here, which provides Möller and Martorell with real-world images to work with. FPM is an advanced microscopy technique that is unique in that it does not alter the specimen’s properties—unlike traditional staining methods, such as fluorescence microscopy. Instead, it images the specimen using the phase of light, allowing for the study of biological samples in their natural state. This holds tremendous potential for the healthcare industry, for example, in digital pathology. With the help of this computational imaging technique, doctors can potentially detect even small tumors or, in the long run, study cancer cells—without the need to alter the specimen or use expensive microscope lenses.

When Prof. Martorell isn’t working with his colleagues from Siegen, he currently serves as an assistant professor, teaching undergraduate courses and conducting research in his main area of expertise, which involves merging images taken at different exposure times—a technique known as bracketing. The resulting image features distinct details and colors across the entire range—from the darkest to the brightest parts of the scene. Thus, it is called high dynamic range (HDR). The presence of moving objects in the scene and small dots known as noise, which typically appear in dark images, make this task very challenging. Continuous improvements are highly desirable, as both cell phone cameras and image processing software like Adobe Photoshop make extensive use of this technique.

Although high-quality images are ubiquitous, the process from the initial capture to the polished-looking picture we take for granted on our screens is lengthy and involves a great deal of mathematics. Möller and Martorell are both working to further improve this process and are publishing their results together. The FPM project is currently working toward a publication in a high-impact journal and a joint technical paper, “Kissing to Find a Match: Efficient Low-Rank Permutation Representation, co-authored by Martorell and Möller among others, was accepted at the Neural Information Processing Systems (NeurIPS) conference 2023, the most prestigious international machine learning conference.

Dr. Martorell’s research stay at the University of Siegen in the first half of 2025 is supported by our research alumni grant “Return for Research,” funded by the Alumni Association for Electrical Engineering and Computer Science at the University of Siegen.

This article was written by Onofre Martorell and Jan Söhlke.