Imaging Informatics
Full course description
Digital image analysis is one of the fastest growing applications in almost all fields. In automotive industry, self-driving cars will need to interpret images in real time to “see” the children playing next to the street. In public surveillance systems, image analysis will be able to recognize faces from cameras and match them to criminal databases. Satellite imagery will analyse real-time high-resolution satellite images to monitor and predict crop yields. And in the digitalization of industrial production (Industry 4.0), where robots will start replacing more and more skilled workers, image analysis will be needed to enable robots seeing and interpreting their environment.
Also in medicine, digital imaging solutions will continue revolutionizing diagnostic capabilities. In vivo imaging of patients in nuclear medicine departments will provide higher-resolved imaging data accompanied with chemical information to monitor therapy progression. Likewise, digital pathology systems based on high-resolution scans of microscopic slides will use deep learning algorithms to assist the pathologist in diagnostic decision-making. This is not restricted to the clinical environment. More and more smartphone apps related to health (such as the already existing app for detection of skin cancer using the smart phone camera) will make use of the information provided by the smart phone camera to monitor the health state of the user.
All of these imaging applications will have not only have a high social impact, but will also lead to the creation of new jobs that deal with image analysis. The intention of the course is therefore to prepare you to effectively and successfully analyze digital images, to prepare you for this job market.
Course objectives
After completing this course, you are able to:
- Understand the imaging technology and the characteristics of the image data
- Image formation;
- Image representation (pixels/voxels, bit-depths, resolution, colour-maps and colour-models, transparency, vector graphics);
- Image storage (file formats, compression).
- Develop a fundamental and theoretical understanding of the different algorithms used
- Logical and arithmetical operations;
- Simple geometric image manipulation (rotation, scaling);
- Brightness and contrast adjustments;
- Colour calibrations;
- Image filtering;
- Machine learning approaches (object classification).
- Image registration to overlay images (control-point based, intensity-based);
- Spatial statistical tests;
- 3D imaging data.
- Understand the task/information which needs to be extracted from the images
- Devise an appropriate image processing and analysis pipeline by considering legal and ethical issues in image acquisition and processing
- Protect privacy and guarantee anonymity of human subjects in image data
- Digital watermarking of images for copyright protection and authentication
- Develop hands-on image processing / analysis skills
- Improve collaboration and communication skills by working together on a presentation
Recommended reading
- Jähne, B. (2005). Digital Image Processing (6th ed.). Springer. https://doi.org/10.1007/3-540-27563-0
- Bivand, R.S., Pebesma, E. J., & Gomez-Rubio, V. (2013). Applied Spatial Data Analysis with R (2nd ed.). Springer. https://doi.org/10.1007/978-1-4614-7618-4
- B.D. Balluff