Chenouf, AmiraMerzkane, OumaymaChibani, Meriem2023-11-272023-11-272023http://dspace.univ-oeb.dz:4000/handle/123456789/17063Semantic segmentation is a fundamental task in computer vision that involves assigning a specific label to each pixel in an image, itenables machines to understand the scene and extract meaningful information. In this project, we explore the application of the U-Net architecture for semantic segmentation, aiming to develop an efficient and accurate system for pixel labeling. This project contributes to the field of semantic segmentation by investigating the application of the U-Net architecture. We demonstrate the effectiveness of the U-Net model in accurately segmenting images at the pixel level. The integration of deep learning techniques and the U-Net architecture holds great promise for advancing the field of computer vision and unlocking new possibilities in image understanding and analysis. The findings of this research open avenues for further advancements in semantic segmentation techniques by bridging the gap between theory and practical applications.enOther