Thesis supervisor: Gergő Bognár
Location of studies (in Hungarian): ELTE IK Numerikus Analízis Tanszék Abbreviation of location of studies: ELTE
Description of the research topic:
The research aims to investigate inverse problems in image processing by combining adaptive mathematical models and artificial intelligence concepts. Several image processing problems (e.g. adaptive filtering, reconstruction, super-resolution, medical imaging) can be modelled as an inverse problem, where the task is to estimate the input data and the parameters of the model from typically noise and distorted observations. The mathematical approaches of the problem include statistical methods (e.g. ML, EM, MAP), numerical optimization (e.g. variable projections), and variational models, among others. Additionally, data-driven artificial intelligence approaches (like model-based and generative neural networks) are also applicable. Note that inverse problems are typically ill-posed and challenging to handle, and they might require additional task-specific domain knowledge (e.g. priors) or regularization techniques. The research objective is to investigate mathematical methods (adaptive filter and transformations, statistical estimates, regulatization techniques) and artificial intelligence and machine learning approaches (primarily neural network architectures) related to inverse problems; algorithm development by the combination of them; development of model-based generative neural network architectures; and the application and validation of the proposed methods on real image processing problems.
Required language skills: angol Further requirements: Fundamental knowledge of mathematical modelling, numerical optimization, signal and image processing, and machine learning; programming and software development skills in Python and Matlab environments.
Number of students who can be accepted: 1
Deadline for application: 2024-05-31
2024. IV. 17. ODT ülés Az ODT következő ülésére 2024. június 14-én, pénteken 10.00 órakor kerül sor a Semmelweis Egyetem Szenátusi termében (Bp. Üllői út 26. I. emelet).
Login
