Automatic processing of microscopic images allows (compared to manual processing by human operator) a better and more efficient acquisition of a large amount of information stored in the captured images. When working with time-lapse images, we need to segment cells from the background, to determine their exact boundaries and monitor their movements. These results can be very helpful to biologists and other scientists in their research. The project deals with images of somatic cells acquired by a phase-contrast microscope. The project aims to reduce the influence of artifacts present in these images and improve methods for processing such images. Another objective of the project is to create an application that will process such images and obtain information about the behavior and movement of cells.