Computer vision 101: Navigational Introduction to AI for Image Processing

This Zenodo record contains the slides for the 1-hour seminar “Computer Vision 101: A Navigational Introduction to AI for Image Processing”, given by Dr. Vladimir Pimonov at the Institut Lumière Matière (Université Claude Bernard Lyon 1) on 12 December 2025 (Salle de séminaires Lippmann), invited by Abdul Rahman Allouche. The presentation is aimed at researchers and students without a computer-science background who want a clear entry point into modern AI. It introduces deep learning-especially computer vision-as a practical tool for research, combining a short historical perspective on neural networks, an intuition-driven explanation of why these models work, and a guided overview of core vision tasks (classification, object detection, and segmentation). The talk also includes research-oriented examples and a hands-on orientation on how to start with Python and Jupyter in a realistic, beginner-friendly way, with the goal of helping participants build both conceptual understanding and a practical roadmap for applying computer vision in their own projects. A support materials blog post “Computer Vision 101” complements the slides by providing a written recap of the historical timeline and collecting the learning resources shared in the seminar (Python setup, PyTorch vs TensorFlow/Keras notes, and links to beginner-friendly and advanced online courses).