Warning
This page is located in archive. Go to the latest version of this course pages. Go the latest version of this page.

Semestral work

The task is to implement a simple image processing algorithm with medical imaging applications. It should take you about 20 hours, so it should not be completely trivial. You can either choose your own task or pick one from the list below. In either case, it needs to be approved by the instructor beforehand. The implementation needs to be yours, written from scratch. You are not allowed to use any existing code, or trivial modifications thereof. Such attempts will be considered a plagiarism and will result in a failure from the course. Library functions may be used for common tasks (e.g. reading or displaying image, solving systems of linear equations etc.). If in doubt, check with the instructor. The required output of the project should be the implementation itself and a short report (a few pages), describing the task in the context of the state of the art methods, the method and its implementation and how to use it, and the experimental resuls.

Project ideas:

Already reserved topics are crossed-out.

  • active contour segmentation based on edge terms
  • active contour segmentation based on intensity (Chan-Vese)
  • gradient vector flow segmentation
  • level set segmentation (2D is enough)
  • segmentation with active shape and appearance models (synthetic data is sufficient)
  • finding superpixels (e.g. SLIC)
  • superpixel segmentation (superpixels can be found using an existing library)
  • normalized cut segmentation
  • GraphCut segmentation - implement the optimization yourself
  • random walker segmentation
  • texture classification using wavelet descriptors
  • texture classification using textons
  • U-net segmentation - study the dependence on parameters and architecture
  • anatomically constrained neural networks - test a simplified case on synthetic data
  • cell nuclei detection using simplified Al-Kofahi's method
  • cell nuclei detection using simplified deep regression
  • implement Frangi's vesselness, generalize and optimize parameters
  • deep regression based retina vessel segmentation (e.g. IOSTAR dataset)
courses/bam33zmo/tutorials/semestralwork.txt · Last modified: 2020/11/23 12:54 by kybicjan