Go to JKU Homepage
Institute of Computational Perception
What's that?

Institutes, schools, other departments, and programs create their own web content and menus.

To help you better navigate the site, see here where you are at the moment.

Digital Image Processing

Student projects in digital image processing

The main goal of digital image processing is to extract useful information about the objects contained in an images from an input image of potentially low quality. The steps necessary to this end (restoration, geometry correction, enhancement, segmentation, feature extraction, classification) are therefore of major interest for us at CP. Additionally we are very interested in image copyright protection (digital image watermarking)

These student projects can be started any time (including holidays) and can span over semester boundaries.

Contact for these topics: Josef Scharinger

Remark: I am open for new proposals – if you are interested in image processing topics just contact me! 

Concrete topics I am interested in:

  • Region-based stereo matching, opens a file
  • Conveyor belt speed measurement, opens a file
  • Building a hyperspectral camera, opens a file
  • Model Inversion and Poisoning Attacks for Medical Images
  • Atmospheric Turbulence Mitigation from Images
  • Image Restoration from Thermal Images (Image Denoising, Image SuperResolution, Image DeRaining)
  • Evaluation of "State-of-the-Art Computer Vision Algorithms for 3D Box and Pallet Detection in Point Cloud Data" (Cooperation with Dr. Simon Vogl)
  • Image Completion
  • Semantic segmentation of images
  • Digital image watermarking 
  • Content based image retrieval
  • Silhouette extraction from videos of moving persons
  • Image retrieval for music-related images (band pictures, album covers, logos, ...)
  • Image features for 3D-Tracking in distance images
  • SLAM using ToF data, or IMU data, respectively (with or without GPS)
  • Setup and calibration of a stereo camera with HW-accelerated matching on an ARM platform
  • Single view 3D reconstruction via structure-from-motion