Towards User-independent 2D / 3D Object Classification of Complex Life Science Images

We develop novel machine vision & mathematical morphology algorithms to analyze complex multi-modal Life Science images.

Project Scope:

Development of 2D/3D image segmentation & classification algorithms for (semi-)automated analysis of complex cellular structures in plants & liver images from Electron Micrographs (EM).

Project Plan:

  1. Develop & benchmark different 2D / 3D algorithms to segment, classify and quantify specific organells in sectional EMs:

    • Liver cells: vesicles, mitochondria, red blood cells, ER
    • Plant cells: thylakoid membrane, chloroplasts, yeast sections

  2. Develop a graphical user interface that bests supports

    • The training phase (object classification)
    • Post-corrections of non- & erroneously classified objects

Kind of Work

30% Theory, 70% Software Engineering


Solid knowledge of Matlab and C++, Good knowledge of Image Processing

Time & Effort

Master’s Thesis, 1-2 People