Marco Filax

Bild von Marco Filax
Drittmittelbeschäftigte/-r

Dr.-Ing. Marco Filax

Faculty of Computer Science (FIN)
Chair of Software Engineering (CSE)
Universitätsplatz 2, 39106 Magdeburg, G29-402

Marco Filax received the B.Sc. degree and the M.Sc. degree in Computational Visualistics from the Otto von Guericke University, Magdeburg, Germany, in 2011 and 2013. His thesis dealt with the problem of separating overlapping fingerprints. His fields of research include but are not limited to pattern recognition, computer vision, machine learning, and pervasive cameras.

2024

Dissertation

Fine-grained open-world recognition identifying retail products in supermarkets

Filax, Marco; Ortmeier, Frank; Leich, Thomas

In: Magdeburg: Universitätsbibliothek, Dissertation Otto-von-Guericke-Universität Magdeburg, Fakultät für Informatik 2024, 1 Online-Ressource (vi, 183 Seiten, 17,69 MB) [Literaturverzeichnis: Seite 157-182][Literaturverzeichnis: Seite 157-182]

2023

Book chapter

On challenging aspects of reproducibility in deep anomaly detection

Kirchheim, Konstantin; Filax, Marco; Ortmeier, Frank

In: Reproducible Research in Pattern Recognition , 1st ed. 2023. - Cham : Springer Nature Switzerland ; Kerautret, Bertrand, S. 57-66 - (Lecture notes in computer science; volume 14068) [Workshop: Fourth International Workshop on Reproducible Research in Pattern Recognition, RRPR 2022, Montreal, Canada, August 21, 2022]

2022

Book chapter

PyTorch-OOD - a library for Out-of-Distribution Detection based on PyTorch

Kirchheim, Konstantin; Filax, Marco; Ortmeier, Frank

In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition workshops / IEEE/CVF Computer Vision and Pattern Recognition Conference , 2022 - Piscataway, NJ : IEEE, S. 4350-4359 [Konferenz: IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW, Orleans, LA, USA, 19-20 June 2022]

Multi-class hypersphere anomaly detection

Kirchheim, Konstantin; Filax, Marco; Ortmeier, Frank

In: 2022 26th International Conference on Pattern Recognition (ICPR) , 2022 - [Piscataway, NJ] : IEEE, insges. 7 S. [Konferenz: 26th International Conference on Pattern Recognition, ICPR, Montreal, QC, Canada, 21-25 August 2022]

Peer-reviewed journal article

Semi-automatic acquisition of datasets for retail recognition

Filax, Marco; Gonschorek, Tim; Ortmeier, Frank

In: Journal of WSCG - Plzen : [Verlag nicht ermittelbar], Bd. 30 (2022), Heft 1-2, S. 86-94 [Konferenz: 30. Jubilee International Conference on Computer Graphics, Visualization and Computer Vision 2022]

2021

Book chapter

On the influence of viewpoint change for metric learning

Filax, Marco; Ortmeier, Frank

In: IAPR International Conference on Machine Vision Applications (MVA) / International Conference on Machine Vision and Applications , 2021 - IEEE : IEEE, Artikel P2-5, insges. 4 S. [Konferenz: 17th International Conference on Machine Vision and Applications, MVA, Aichi, Japan, 25-27 July 2021]

Grocery recognition in the wild - a new mining strategy for metric learning

Filax, Marco; Gonschorek, Tim; Ortmeier, Frank

In: VISIGRAPP 2021 ; Volume 4: VISAPP , 2021 - [Sétubal] : SCITEPRESS - Science and Technology Publications, Lda. ; Farinella, Giovanni Maria, S. 498-505 [Konferenz: 16th International Conference on Computer Vision Theory and Applications, VISAPP, Online, 08.-10.02.2021]

2020

Book chapter

ENT endoscopic surgery and mixed reality - application development and integration

Gomes Ataide, Elmer Jeto; Fritzsche, Holger; Filax, Marco; Chittamuri, Dinesh; Potluri, Lakshmi Sampath; Friebe, Michael

In: Biomedical and clinical engineering for healthcare advancement - Hershey, PA: Medical Information Science Reference, 2020; Sriraam, N. . - 2020, S. 17-29

2019

Book chapter

Data for image recognition tasks - an efficient tool for fine-grained annotations

Filax, Marco; Gonschorek, Tim; Ortmeier, Frank

In: Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods. Volume 1 - [Setúbal] : SCITEPRESS - Science and Technology Publications, Lda. . - 2019, S. 900-907 [Konferenz: 8th International Conference on Pattern Recognition Applications and Methods,February 19-21, 2019, Prague, Czech Republic]

Integrating safety design artifacts into system development models using SafeDeML

Gonschorek, Tim; Bergt, Philipp; Filax, Marco; Ortmeier, Frank

In: Model-Based Safety and Assessment , 1st ed. 2019 - Cham : Springer ; Papadopoulos, Yiannis, S. 93-106 - ( Lecture Notes in Computer Science; volume 11842) [Symposium: 6th International Symposium, IMBSA 2019, Thessaloniki, Greece, October 1618, 2019]

SafeDeML: on integrating the safety design into the system model

Gonschorek, Tim; Bergt, Philipp; Filax, Marco; Ortmeier, Frank; Hoyningen-Hüne, Jan; Piper, Thorsten

In: Computer Safety, Reliability, and Security , 1st ed. 2019 - Cham : Springer, S. 271-285 - (Programming and Software Engineering; 11698) [Konferenz: 38th International Conference, SAFECOMP 2019, Turku, Finland, September 11-13, 2019]

2018

Abstract

Predictive tracking control of a camera - head mounted display system subject to communication Constraints

Kogel, Markus; Andonov, Petar; Filax, Marco; Ortmeier, Frank; Findeisen, Rolf

In: 2018 European Control Conference (ECC) , 2018 - Limassol, Cyprus ; European Control Conference (17.:2018), S. 1035-1041 [Konferenz: 2018 European Control Conference (ECC), June 12-15, 2018, Limassol, Cyprus]

A very first glance on the safety analysis of self-learning algorithms for autonomous cars

Gonschorek, Tim; Filax, Marco; Ortmeier, Frank

In: Archive ouverte HAL - Paris : Centre National de la Recherche Scientifique - 2018, Art. hal-01878562, insgesamt 2 S. [Konferenz: 37th International Conference on Computer Safety, Reliability, & Security, SAFECOMP2018, Vasteras, Sweden, September 19-21, 2018]

Book chapter

On the similarities of fingerprints and railroad tracks - using minutiae detection algorithms to digitize track plans

Klockmann, Maximilian; Filax, Marco; Ortmeier, Frank; Reib, Martin

In: 13th IAPR International Workshop on Document Analysis Systems , 2018 - Piscataway, NJ : IEEE, S. 311-316 [Workshop: 13th IAPR International Workshop on Document Analysis Systems, DAS 2018, Vienna, Austria, 24-27 April 2018]

Article in conference proceedings

VIOL: Viewpoint invariant object localizator viewpoint invariant planar features in man-made environments

Filax, Marco; Ortmeier, Frank

In: VISAPP / VISIGRAPP , 2018 - [Setúbal, Portugal] : SCITEPRESS - Science and Technology Publications, Lda., S. 581-588 [Konferenz: 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISIGRAPP 2018, Funchal, Madeira, Portugal, January 27-29, 2018]

2017

Book chapter

Building models we can rely on - requirements traceability for model-based verification techniques

Filax, Marco; Gonschorek, Tim; Ortmeier, Frank

In: Model-Based Safety and Assessment - Cham : Springer . - 2017, S. 3-18 - (Lecture Notes in Computer Science; 10437) [Symposium: 5th International Symposium, IMBSA 2017, Trento, Italy, September 11-13, 2017]

QuadSIFT: unwrapping planar quadrilaterals to enhance feature matching

Filax, Marco; Gonschorek, Tim; Ortmeier, Frank

In: WSCG 2017 - Plzen : Vaclav Skala - Union Agency, S. 7-16 [Konferenz: 25th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, WSCG 2017, Plzen, Czech Republic, May 29 - June 2, 2017]

Peer-reviewed journal article

Effiziente Sicherheitsnachweisführung mithilfe modellbasierter Systemanalyse

Bitsch, Friedemann; Filax, Marco; Gonschorek, Tim; Ortmeier, Frank; Schumacher, Rolf

In: Signal + Draht - Hamburg : DVV Media Group . - 2017, Heft 6

Article in conference proceedings

A verification environment for critical systems - integrating formal methods into the safety development life-cycle

Gonschorek, Tim; Filax, Marco; Ortmeier, Frank

In: ResearchGATE - Cambridge, Mass. : ResearchGATE Corp. . - 2017, insges. 1 S. [Symposium: 5th International Symposium on Model-Based Safety and Assessment, IMBSA2017, Trento, 11-13 September 2017]

2016

Book chapter

Correct formalization of requirement specifications - a V-model for building formal models

Filax, Marco; Gonschorek, Tim; Ortmeier, Frank

In: Reliability, Safety, and Security of Railway Systems. Modelling, Analysis, Verification, and Certification - Cham : Springer . - 2016, S. 106-122 - (Lecture Notes in Computer Science; 9707) [Kongress: 1st International Conference, RSSRail 2016, Paris, France, June 28-30, 2016]

Peer-reviewed journal article

Bringing formal methods on the rail - Modellbasierte Systemanalyse in der Sicherheitsnachweisführung

Filax, Marco; Gonschorek, Tim; Hebecker, Tanja; Lipaczewski, Michael; Madalinski, Agnes; Ortmeier, Frank; Fietze, Mario; Schumacher, Rolf

In: Der Eisenbahningenieur - Hamburg : DVV Media Group . - 2016, S. 24-27

2014

Book chapter

VECS - verification enviroment for critical systems - tool supported formal modeling an verification

Gonschorek, Tim; Filax, Marco; Lipaczewski, Michael; Ortmeier, Frank

In: IMBSA 2014: short & tutorial proceedings of the 4th international symposium on model based safety assessment - Magdeburg: Univ., S. 63-64

On traceability of informal specifications for model-based verification

Filax, Marco; Gonschorek, Tim; Lipaczewski, Michael; Ortmeier, Frank

In: IMBSA 2014: short & tutorial proceedings of the 4th international symposium on model based safety assessment - Magdeburg: Univ., S. 11-18

Bringing VECS to the World - challenges and accomplishments in teaching of formal model analysis

Lipaczewski, Michael; Filax, Marco; Ortmeier, Frank

In: European Conference on Software Engineering Education - ECSEE 2014: 27th and 28th November 2014, Seeon Monastery - Aachen: Shaker, S. 217-228Kongress: ECSEE 2014 27 (Seeon Monastery, Germany : 2014.11.27-28)

Completed projects

Fine-Grained Recognition of Retail Products
Duration: 01.01.2015 to 30.09.2024

Grocery recognition in supermarkets comprises several challenges as groceries embed small inter-class and intra-class variance. Small inter-class variance is given because different products share substantial visual similarities. Datasets typically contain real-world images and reference images, which induces intra-class variance. The visual appearances of products change over time, and their number continuously grows because designs are reworked or new products are published. Standard object classification methods are inapplicable at scale because models need to be fine-tuned continuously to relax these changing conditions.

In this project, we leverage the burden of requiring all classes to be known at training time using methods derived from face recognition techniques and meta-knowledge derived from additional sensor information. The setting is based on recognizing groceries in unknown supermarkets, e.g., without substantial infrastructural changes. The core idea is to extend face-recognition methods and fine-tune known architectures to distinguish the fine-grained visual differences of grocery products. The required training images are semi-automatically generated using sensor data acquired with modern smart glasses, e.g., the user’s trajectory and a model of the environment. Product candidates in real-world images are found using a sliding window approach, which uses the observation that products are arranged on shelves.

View project in the research portal

Real-time on-site reconnaissance and mission monitoring (EVOK) - Sub-project: Conception of a real-time capable on-site reconnaissance system
Duration: 01.02.2019 to 31.12.2022

In EVOK, a system for real-time situational awareness is to be developed that allows the creation of a 3D model of the environment during an ongoing operation. The current positions of the emergency services can also be displayed in this model. This is to be visualized in a way that is specifically tailored to each user group. In addition to special software algorithms, the corresponding hardware, including operational sensors, is also being developed and adapted. The latter should be so compact that they can be mounted both on autonomous reconnaissance systems and on the equipment of special forces.

The system developed in the project represents a technical innovation that is directly geared towards practical requirements. The requirements of real operations are incorporated into the development throughout the entire project. The visualization of the location and position of the emergency services can help to minimize hazards and make operations more efficient. This significantly increases the safety of the emergency services and the people affected.
This text was translated with DeepL on 28/11/2025

View project in the research portal

Development of technologies for intelligent, collaborative, interactive displays for outdoor use (i-Display)
Duration: 01.01.2019 to 30.04.2022

This project aims to develop a stele that a) can be used both indoors and outdoors, b) allows user interactions - in particular those that go beyond pure touch gestures - and c) can display context- and history-dependent information through networking and collaboration with other stelae.

In outdoor areas, the steles are exposed to strong fluctuations in temperature, humidity and air pressure (up to 50°C difference in one day). This requires particularly hardened IT and sensor technology. Due to the different lighting conditions to be expected, weather/context-dependent displays of information and interaction metaphors may be necessary.

There are conceptually diverse metaphors for user interaction - from speech and gestures to biometric signals. The steles face particular challenges here due to the weather conditions, the potentially large numbers of rapidly changing viewers and, of course, data protection.

Collaboration requires the steles to be able to exchange and correlate information with each other. For example, a shared image of the surroundings (e.g. where is which stele, who is standing where) must be created. Data protection plays an essential role, especially for the history-dependent display, as this often involves user-related data and at the same time it is not easy to decide who is currently interacting with the stele.
This text was translated with DeepL on 28/11/2025

View project in the research portal

ObViewSly 4.0 - Object extraction from 3D geoinformation mass data
Duration: 07.05.2019 to 30.04.2022

The aim of the "ObViewSly 4.0" project is to develop a new method for the semi-automatic, interactive derivation of 3D geodata products from aerial images.
The aim is to enable the user to quickly and easily derive 3D objects from mass data. Figures 1 to 3 show an illustrative example. According to preliminary market research, such a software system is not currently available. In addition, an automatic, area-based derivation of 3D geodata products should be achieved without the need for user interaction.

The market launch of this product is to take place in various stages, depending on the version status and usability. The following sub-goals are planned in this project:

  • Automated detection of buildings in textured 3D mesh data
  • Generation of textured 3D objects from 3D mesh data
  • Texture analyses for information extraction of vector objects
  • Aggregation of objects with external data sets (owner, use)
  • Usage analyses for urban areas
  • Socio-economic analyses
  • The objectives are defined in a logical sequence, but are not dependent on each other. The input data for the individual modules may, but need not, originate from a previous module.
    This text was translated with DeepL

    View project in the research portal

    STIMULATE research campus: Robotics research group
    Duration: 01.01.2015 to 31.12.2019

    The project aims to develop new methods for the thermal ablation of spinal tumors that go far beyond the current status of purely telemanipulating surgical robots. A central goal of the project is the development of a control and path planning algorithm for the optimal positioning of an ablation electrode by a robot in an autonomous intervention on the spine. The clinical and technical requirements are defined in close coordination with the project partners from research and industry. The approaches for optimal path planning for a robot are developed and investigated in a clinical laboratory environment. The main challenge is to compensate for and minimize possible systematic and non-systematic errors. Above all, the frequently occurring errors, such as in the registration of the robot relative to the patient and to the imaging devices (angoigraphy device and an external navigation system) or due to the compliance of the ablation electrodes and the patient's breathing, lead to a high degree of inaccuracy in electrode placement, which is to be reduced. As part of the project, a concept for online compensation of possible modeling and positioning errors is being developed in order to react to possible disturbances during an intervention. As a result, a higher accuracy of the ablation dosage, shorter treatment duration and reduced X-ray dose for the treating staff as well as for the patients will be made possible.
    This text was translated with DeepL on 28/11/2025

    View project in the research portal

    figaro-logo-dalle3Computer-aided visual perception is one of the fundamental problems in computer vision research. Often, approaches aim to predict the likeliest predefined labels. These typically have been determined during a dataset's acquisition.
    Decades of research were required to predict the likeliest (predefined) label with sufficient accuracy for everyday use. Although the currently available and often data-driven approaches work reasonably well, their ability to predict labels of objects is similar to that of a three-year-old child. These labels have a broad complexity, such as differentiating mammals (e.g., dogs or cats). Fine-grained objects (e.g., different dog breeds) pose new challenges because minute differences separate one object label from another. More research must be conducted with open datasets without obligating the closed dataset requirement (i.e., having a complete set of labels during the implementation).
    We refer to this category of problems as fine-grained recognition problems. This research investigates the current state of the art in fine-grained open-world recognition (i.e., retail product recognition) and aims to improve its accuracy. We research approaches for overcoming the shortage of fine-labeled datasets by exploiting metaknowledge of the environment and demonstrate how these approaches can be applied to acquire datasets at a significant scale. We also research different approaches for recognizing the identifier of fine-grained retail products in real-world scenarios. Moreover, we aim to reduce the number of manually required annotations during training.

    This topic is under ongoing research. For questions refer to Marco Filax.

    scatter_plot_web

    Last Modification: 30.04.2025 -
    Contact Person: Webmaster