Fluorescence microscopy is a widespread tool in biological research. It is the primary modality for bioimaging and empowers the study and analysis of multitudes of biological processes. It can be applied to fixed biosamples, that is samples with frozen biological features by mean of chemical linkers, or live biosamples providing useful insights on the spatio-temporal behavior of fluorescently stained biomarkers. Current fluorescent microscopy techniques use digital image sensors which are used to leverage quantitative studies instead qualitative outcomes. However, state-of-the-art techniques are not suitable for integration in small, contained and (semi-)autonomous systems. They remain costly, bulky and rather quantitatively inefficient methods for monitoring fluorescent biomarkers, which is not on par with the design constraints found in modern Lab-on-a-Chip or Point-of-Use systems requiring the use of miniaturized and integrated fluroscence microscopy. In this thesis, I summarize my research and engineering efforts in bringing an embedded image processing system capable of monitoring fluorescent biomarkers in cell cultures in a continuous and real-time manner. Three main areas related to the problem at hand were explored in the course of this work: simulation, segmentation algorithms and embedded image processing. n the area of simulation, a novel approach for generating synthetic fluorescent 2D images of cell cultures is presented. This approach is dichotomized in a first part focusing on the modeling and generation of synthetic populations of cells (i.e. cell cultures) at the level of single fluorescent biomarkers and in a second part simulating the imaging process occurring in a traditional digital fluorescent microscope to produce realistic images of the synthetic cell cultures. The objective of the proposed approach aims at providing synthetic data at will in order to test and validate image processing systems and algorithms. Various image segmentation algorithms are considered and compared for the purpose of segmenting fluorescent spots in microscopic images. The study presented in this thesis includes a novel image thresholding technique for spot extraction along with three well-known spot segmentation techniques. The comparison is undertaken on two aspects. The segmentation masks provided by the methods are used to extract further metrics related to the fluorescent signals in order to (i) evaluate how well the segmentation masks can provide data for classifying real fluorescent biological samples from negative control samples and (ii) quantitatively compare the segmentations masks based on simulated data from the previously stated simulation tool. Finally, the design of an embedded image processing system based on FPGA technologies is showcased. A semi-autonomous smart camera is conceived for the continuous monitoring of fluorescent biomarkers based on one of the segmentation methods incorporated in the previously stated comparison. Keeping the focus on the need for integration in fluorescence microscopy, the image processing core at the heart of the smart camera results from the use of a novel image processing suite; a suite of IP cores developed under the constraints dictated by the bioimaging needs of fluorescence microscopy for use in FPGA and SoC technologies. As a proof of concept, the smart camera is applied to the monitoring of the kinetics of the uptake of fluorescent silica nano-particles in cell cultures.