iPattern

Hochschule Niederrhein. Your way.

iPattern - Institute of Pattern Recognition

Pattern recognition issues arise frequently in practical applications, e.g. in materials testing, medical diagnosis, evaluation of video and audio data, or information retrieval from large data sets. The institute's name iPattern is derived from the English term "Pattern Recognition".

We see ourselves as a partner of industry and commerce, advising on problems in the field of pattern recognition and developing solutions for them. This can take the form of direct contract research as well as publicly funded projects. Furthermore, we also develop and investigate self-selected problems in pattern recognition and publish the results as scientific reports and/or as open-source software.

Head of the institute

Digital signal processing and pattern recognition
iPattern at VISIGRAPP 2023

The iPattern Institute was represented with four contributions at VISIGRAPP 2023 in Lisbon and was nominated for the Best Poster Award.

Voice control for a wet room on the train

On behalf of Siemens Mobility GmbH, Prof. Hirsch and M.Sc. Neumann have developed a voice control system for a wet room in a train.

AI for monitoring tunnel mouths

Sponsored by the German Federal Ministry of Digital Affairs and Transport, Prof. Pohle-Fröhlich is researching with external partners how tunnel…

Students from Krefeld present at ICPRAI conference in Paris

Computer science students Willy Fritzsche, Nils Schuch and Marco Russinski have presented the results of a project on 3D city modeling at the iPattern…

"Best Poster Award" at IVAPP 2022

At this year's IVAPP conference, an iPattern paper received a distinction.

iPattern at VISAPP 2022

iPatterns was represented at the International Conference on Computer Vision and Applications (VISAPP) with a contribution in the context of the…

At the Institute for Pattern Recognition, we research and develop methods that enable a computer to perceive information like a human being. Depending on the type of data investigated, different areas of application arise:

  • Audio signal processing: recognition of speech and speakers
  • Image analysis: Recognition of objects in images
  • Search and prediction: information retrieval from large data sets
  • 3D modeling: generating models by combining data sources

For each of these application areas, we have experts in our team who can advise you on a specific problem and develop a solution.

Audio signal processing

In this area, we deal with methods for the reduction of noise, as well as for the recognition of the content and the speaker from a disturbed speech signal. We use these methods for automatic speech recognition to build concrete applications, e.g. to simplify the operation of vending machines or to query information with the help of a speech dialog system.

Expert:

Digital signal processing and pattern recognition

Image analysis

In this area we deal with methods for image enhancement, image classification, medical image processing, as well as person tracking in video data. Furthermore, the OpenSource software "Gamera" is developed in our institute, which can be used to create automatic document recognition systems.

Experts:

Computer science, graphic data processing
Mathematics and computer science

Search & Predict

In this area, we deal with information retrieval and data mining methods for finding relevant information in large, possibly also unstructured data sets. This also includes the estimation of future behavior (prediction) based on collected data from the past. We use these methods e.g. in special web applications, in recommender systems, or in systems for decision support.

Experts:

Computer Science Library Officer
Mathematics and computer science

3D modeling

In this area, we reconstruct realistic models from geodata. The foundation courses are, for example, aerial photographs or point clouds obtained by means of laser scanners or photogrammetric methods. Software is being developed at the institute that automatically calculates virtual 3D city models from these data for cadastral and simulation purposes.

Experts:

Mathematics and computer science
Computer science, graphic data processing

Publicly funded projects

TUNUKI
Monitoring of tunnel mouths using artificial intelligence (09/2022 - 08/2023), sponsored by the German Federal Ministry of Digital Affairs and Transport (mFund innovation initiative).

Translingo
Digital speech therapy for people who want to regain their speech after a stroke (aphasics) (09/2021 - 08/2024), funded by the German Federal Ministry of Education and Research(link to project homepage)

KiRaPol.5G
Artificial Intelligence for Radar Systems to Support Police Surveillance in Public Places and Stations (01/2022 - 06/2024), sponsored by the Ministry of Economic Affairs, Industry, Climate Protection and Energy of the State of North Rhine-Westphalia (link to project homepage)

MLPCO
Using Machine Learning to Predict Crop Output of Small scale farmers, (01/2021 - 11/2021), funded by the German Federal Ministry of Education and Research.

KlaRa
Development of Algorithms for Object Classification with Radar Signals, (09/2020 - 12/2022), sponsored by the "Central Innovation Program for SMEs" (ZIM)

plsm
User-oriented design of public spaces using sensor technology (04/2018 - 03/2021), funded by the "European Regional Development Fund (ERDF)" ( link to project homepage)

FahrRad
A sensor-based bicycle assistance system esp. for elderly cyclists (05/2017 - 05/2020), sponsored by the "European Regional Development Fund (ERDF)" (link to project homepage)

Smart Home Voice Control
Development of a voice-operated interface for home automation (11/2016 - 10/2019), funded by the "Central Innovation Program for SMEs" (ZIM).

Contract research and development

Voice control of a wet cell
Voice control system of a wet cell in a train for Siemens Mobility GmbH (2022)

Evaluation of Point Clouds
Algorithm for the detection of particle trajectories in point clouds from Time Projection Chambers for Universidade de Santiago de Compostela (2022)

Symmetry Scores
Software to compute symmetry scores of graphical elements for Intelligent Design Automated in Closter, USA (2020)

MRI evaluation
Software for semi-automatic muscle segmentation in MRI images for the "German Aerospace Center" in Cologne, Germany (2019)

Textured 3D city model
Area-wide 3D city model from laser scan data and cadastral floor plans for the city of Dortmund (2019)

Quality control
Automatic detection of solder joint defects for modus hightec-electronics in Willich (2017)

Cost estimation
Forecasting method for repair costs for AUTOonline in Neuss (2014)

 

Free research projects

Insect monitoring
Automatic long-term insect monitoring using dynamic vision sensors to record biodiversity through the use of AI.

3D City Model
Fully automated generation of virtual 3D city models using a combination of different data sources.
More info: Online model of Krefeld, Germany.

Gamera
Python framework for creating automatic document recognition systems.
Further information: Homepage of the open-source software

Wealth Distribution
Statistical method for estimating wealth distribution from incomplete data.
More info: Technical report & R code

Trajectory Detection
Automatictrajectory detection in point clouds.
More info: Open source software & demo

 

Peer Reviewed

Other publications

Audio signal processing: H.G. Hirsch

Digital signal processing and pattern recognition

Image analysis: R. Pohle-Fröhlich

Computer science, graphic data processing

Statistical methods: C. Dalitz

Mathematics and computer science

Search technologies: K. Weidenhaupt

Computer Science Library Officer

Virtual 3D Models: S. Goebbels

Mathematics and computer science

Manager

Digital signal processing and pattern recognition