Understanding Odor Descriptors through Advanced NLP Models and Semantic Scores

Explainable Predictive Maintenance: Forecasting and Anomaly Detection of Diagnostic Trouble Codes for Truck Fleet Management

Attention Artifact! Misalignment and artifact detection using deep learning and augmentation


Image2Tikz: Neural Network-Based TikZ Code Generation

Work description
This thesis aims to develop Image2Tikz, a tool that uses neural networks to transform images into TikZ code by segmenting objects, estimating distances between them, and then translating this information into TikZ. Starting with simple TikZ images and progressing to more complex, hand-drawn versions, the tool will be refined to handle increasing noise levels and complexities. The performance will be evaluated by comparing the generated TikZ code against the original images.

The following questions should be considered:

  • How can neural networks be effectively trained for tikz object segmentation and distance estimation in images?
  • What techniques can be used to translate segmented objects and their relative distances into TikZ code?
  • How does the introduction of noise and complexity in images affect the tool’s accuracy and reliability?
  • What strategies can improve the tool’s performance on more complex, hand-drawn images?


Candidates should have a strong foundation in machine learning, particularly in neural networks, with practical experience in Python and familiarity with PyTorch. Skills in image processing and an understanding of LaTeX, especially TikZ, are desirable. The ability to work independently and creatively solve problems is essential.

Please include your transcript of record with your application.

Deep Learning-Driven Approaches for Optimizing Accuracy and Inference Speed in Compact Segmentation Models on Edge Devices

Automatic detection of Bronchoscopes on x-ray images

Scamming Scammers using Large Language Models

This Master Thesis is a cooperation with the Chair of Applied Cryptography.

Work description
In the digital age, scam emails have become a serious threat. These fraudulent emails aim to steal sensitive information or cause financial damage. This thesis aims to better understand the problem of scam emails and develop effective solutions to reduce their success. We will address several aspects, including the vulnerability of email addresses to scammers, the differentiation of scam emails from other dubious messages, the automation of responses through Large Language Models (LLMs), the detection of the usage of LLMs by the scammers, and the evaluation of the economic damage to the scammers based on the data obtained. We aim to strengthen the security of digital communication and help minimize the risks for users and organizations.

The following questions should be considered:

  • How can an email address be made vulnerable to scammers?
  • How can emails from scammers be distinguished from other dubious emails?
  • How can LLM responses be automated and customized?
  • How quickly do scammers recognize automated responses?
  • How can we accurately assess the extent of the economic harm caused by the scammer using our collected data?


Prerequisites for this task include good knowledge of Deep Learning and IT Security, familiarity with Python and PyTorch, and the capability to work independently.

For your application, please send your transcript of record.

Towards Automated Learning-based Image Quality Prediction of Cone-Beam CT Reconstructions from few Scout Images for Metal Artifact Avoidance

AI-based Pavement Recognition System for Vehicle Road Infrastructure

Synthetic data creation of defect images for CNN training using GAN

Master Thesis in Cooperation with Infineon Technologies AG

External Supervision:
Weichselbaumer Christoph (BE R UPE TEST) (

Working Tittle:
Synthetic data creation of defect images for CNN training using GAN

Research Question:
Can the use of Generative Adversarial Networks (GANs) for generating synthetic data of particles and scratches on a transparent background improve the accuracy of Convolutional Neural Networks (CNNs) in defect detection?

The proposed Master’s thesis aims to address the challenge of providing ground truth for model training in AI use-cases, specifically in the context of detecting defects in products. Currently, the process of manual review and labeling of images for CNN [1] training is highly time-consuming and costly, and the most critical and relevant defects are often the least present in real data due to the design of products to minimize such defects. Moreover, data shifts in production can also affect the training of models.
To overcome these challenges, the proposed Master’s thesis will focus on the use of Generative Adversarial Networks (GANs) [2],[3], [4] to generate synthetic data for the minority classes for CNN training. The goal of the thesis is to create one or more GANs that are capable of generating defect images of particles and scratches on a transparent background, and to evaluate the performance of these generated images by measuring their classification accuracy using an existing CNN [5].

The proposed research will involve two sub-targets:
1. Developing GANs capable of generating defect images of particles and scratches on a transparent background.
2. Creating GANs capable of image-to-image translation to generate defect images of particles and scratches.
The focus of the research will be on generating defect images on a transparent background, with image-to-image translation considered an optional target depending on the progress of the research.

The approach to using GANs involves using existing defect image datasets for training, and then generating synthetic images to fill gaps in the real data. The GANs will be trained to generate synthetic images of particles and scratches on a transparent background, and these images will be combined with a “golden die” background to create an enhanced dataset for CNN training.
The suggested topic has the potential to significantly reduce the time and cost associated with manual review and labeling of images for CNN training, and to provide a more diverse and relevant dataset for model training. The proposed approach can also be applied to other defect types, such as stains and chipping, to further enhance the dataset for CNN training.

[1]. O’Shea, Keiron, and Ryan Nash. “An introduction to convolutional neural networks.” arXiv preprint arXiv:1511.08458 (2015).
[2]. Ali, Safinah, Daniella DiPaola, and Cynthia Breazeal. “What are GANs? introducing generative adversarial networks to middle school students.” Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 35. No. 17. 2021.
[3]. Figueira, Alvaro, and Bruno Vaz. “Survey on synthetic data generation, evaluation methods and GANs.” Mathematics 10.15 (2022): 2733.
[4]. Eilertsen, Gabriel, et al. “Ensembles of GANs for synthetic training data generation.” arXiv preprint arXiv:2104.11797 (2021).
[5]. Buda, Mateusz, Atsuto Maki, and Maciej A. Mazurowski. “A systematic study of the class imbalance problem in convolutional neural networks.” Neural networks 106 (2018): 249-259.