This course introduces students to the fundamental principles and practical techniques of computer vision. Topics include image filtering, feature extraction, edge detection, geometric transformations, object detection, segmentation, and 3D vision. Students will also explore modern deep learning-based approaches such as convolutional neural networks (CNNs), Vision Transformers (ViTs), object detection models (YOLO, SSD), and convolutional autoencoders (CAEs) for dimensionality reduction and denoising. Applications span image classification, depth estimation, and video analysis. Through hands-on labs and projects using Python and libraries like OpenCV, PyTorch, and Scikit-image, students will develop the skills to build, evaluate, and deploy computer vision systems.

Temps présentiel : 30 heures

Charge de travail étudiant : 70 heures

Méthode(s) d'évaluation : Examen final, Examen partiel, Travail personnel