Implementation of imaging system in OpenCV and CUDA

OData support
Dr. Szirmay-Kalos László
Department of Control Engineering and Information Technology

In my thesis work I implement an image reconstruction system that will analyze the state of zebrafish eggs for scientific purposes. The system’s objective is to determine whether or not the given egg is alive. In order to achieve this objective, image processing algorithms are used on pictures taken automatically. OpenCV library will be used to implement image processing tasks and the CUDA GPGPU language to implement high computing-intensive tasks. At the beginning of my thesis work I will describe the basics and specialties of the previously mentioned library and language. Then I will describe the algorithms used during image reconstruction. In the description of each algorithm I will explain their function, the modifications I made in them. The descriptions also contain the results which show whether or not the algorithm is suitable to categorize the eggs. At the end I summarize and evaluate the numerical results of the algorithms. I also explain how the decision module works, which decides the state of the given egg using the data provided by the algorithms.


Please sign in to download the files of this thesis.