News

Written by Prathmesh Madhu Contribution Inspired from the pioneer work of Max Imdahl , our work focuses on generating image composition canvas (ICC) diagrams based on two central themes: (a) detection of action regions and action lines of an artwork (b) pose-based segmentation of for...

GitHub decided to backup several open-source software projects in the artic in the GitHub Archive Project. It's a great pleasure to announce that five of the lab's software projects made it to the list of projects archived there: CONRAD is an open-source framework for computed tomography allowin...

Today a BR film crew came to the lab and shot a feature for the "Abendschau" about our work on handwriting imitation . We demonstrated in detail how one's handwriting can automatically be synthesized. It was broadcast on BR Fernsehen Monday 20th of July in the "Abendschau" and can now be watched...

It's a great pleasure to announce that our Lecture Notes in Deep Learning created a lot of positive feedback. They are to large degrees automatically generated. Yet, we just got the news that a new column "FAU Lecture Notes" was established in Towards Data Science, a Medium publication with more th...

BaCaTeC will fund a joint project between Jokerst Bioimaging Lab at UCSD and PRL with 9.000 EUR. In the collaboration, we want to develop an algorithm to automatically detect wounds from non-invasive ultrasound and photoacoustic images.

Multi-modal (Audio, Text, Visual) Emotion Recognition Grant Awardee: Ronak Kosti Grant Duration: July-2020 to June-2021 Project Description We recognize people's emotions from their facial expressions, body posture, behavior and social interaction with other people. It is an essential ability wh...

Written by Prathmesh Madhu Contribution This work exploits style transfer in combination with transfer learning to recognize characters in art historical images. Our approach focuses on recognizing two central characters in the "Annunciation of the Lord" scene from Art history, Mary and Gabri...

You think handwriting is unique and cannot be imitated? We show the contrary in our work. To the best of our knowledge, it is the first paper that synthesizes realistic Western cursive handwriting by mimicking the actual temporal writing process. Our method works nearly fully automatic, e.g. no manual cutting out of characters, and is able to render full lines instead of glyphs/words as in other works.

The German Research Council (DFG) funds our Project Grant "Deep Animal Linguistic Analysis (DALA) - Decoding Animal Communication using Bioacoustics and Machine Learning"! In total, FAU will receive 260.000 EUR for 24 months in the first project phase. The total project volume is 400.000 EUR. ...

It is a great pleasure to announce that colleagues at the Pattern Recognition Lab won several awards on this year's virtual Bildverarbeitung für die Medizin 2020 conference: Best Scientific Paper 1st Place: Alexander Preuhs Deep Autofocus with Cone-Beam CT Consistency ConstraintPRS Video Best...