Advanced Image Processing and AI
Full course description
“A picture is worth a thousand words”. Most of us humans are much more efficient in conveying ideas and messages through pictures than through words. For a computer, this is not such an easy task. Tasks like face recognition have been worked on for more than 50 years, but became only recently available on mobile devices. A computer will require a multitude of steps before it can crap the essence of a picture. The high-resolution imaging modalities used in the field of Molecular Imaging and Engineering inevitably require automated analysis methods. In recent years these have become increasingly sophisticated, requiring expert knowledge to implement successfully.
This course will build on the fundaments laid out in the Imaging Informatics course and bring imaging processing to a next level. Although the professional context of this course is geared towards the applications offered during the programme, the methods presented are used for a wide range of modern-day image recognition, classification tasks, among others. Their fundamental aspects serve a much broader perspective, given the wide social impact that automated image recognition has on the society now and in the decades to come.
Course objectives
After completing this course, you are able to:
- Explain basic mathematical concepts such as complex numbers, derivatives & integrals, geometric series, trigonometric & exponential functions and apply them to Fourier sums, Fourier 2D and 3D transforms, Parseval’s theorem and (bandpass) filters.
- Design & practice computational image processing implementations, including applying and developing MATLAB code for image processing.
- Use image-processing techniques such as Noise filtering, Wiener filtering, inverse filtering, geometric transformations and grey value interpolation.
- Calculate the Nyquist-frequency and predict how to prevent aliasing
- Solve problems in multi-modal imaging and to segment image data by feature recognition both via neural network training techniques as well as through more traditional morphological image processing techniques.
- Consider ethical issues in image processing and communicate related considerations to an audience of specialists and non-specialists.
Recommended reading
- Anton, H., & Rorres, C. (2013). Elementary Linear Algebra: Applications Version (10th ed.). Wiley.
- Neuhauser, C., & Roper, M. L. (2018). Calculus for Biology and Medicine (4th ed.). Pearson.
- Bodine, E. N., Lenhart, S., & Gross, L. J. (2014). Mathematics for the Life Sciences. Princeton University Press.
- 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
- Gonzalez, R.C., & Woods, R.E. (2018). Digital Image Processing (4th ed.). Pearson.
- Gonzalez, R.C., Woods, R.E., & Eddins, S.L. (2020). Digital Image Processing using MATLAB (3rd ed.). Pearson.
- Forsyth, D.A., & Ponce, J. (2012). Computer Vision: A Modern Approach (2nd ed.). Pearson
- S.P.M. van Nuffel