Image segmentation plays a crucial role in computer vision and image processing with important applications such as scene understanding, medical image analysis etc, a field with a rich history of exploration. In this context, the prevalent success of deep learning model has driven the creation of innovative image segmentation techniques. It conducts a comparative analysis of various architectural paradigms, including U-Net, DenseNet, AlexNet, CoatNet, and VGG19. Through meticulous experimentation conducted in Python, the study aims to ascertain the efficacy of these architectures, striving to identify the most promising approach. The outcomes and implications drawn from the results pave the way for future avenues of research and development.
Medicalimage segmentation, deeplearning, semantic segmentation, u-net, alexnet, vgg19, Coatnet, densenet