Automatic image segmentation is one of the central problems in the area of computer vision. It is commonly employed in many tasks such as locating objects in satellite images (roads, forests, etc.), traffic control systems, face recognition, etc. But, in particular it plays an important role in biomedical imaging, with various different applications, one of them dealing with Segmentation of Living Cells. In this thesis, we use three different segmentation techniques, namely, region growing segmentation technique, watershed segmentation and texture segmentation to accurately extract the shapes of membranes and nuclei from the inverted microscopy images, taken throughout the monolayer formation of BGM-70 (Baby Grevit Monkey) cell culture. This strategy is a prerequisite for an accurate quantitative analysis of cell shape and morphogenesis during organogenesis and is the basis for an integrated understanding of biological processes. The segmentation of cellular structures is achieved by first normalizing the microscopic images by performing CLAHE operation followed by de-noising by morphological opening and filling of the holes and then applying segmentation algorithm for cell shape r