Machine Vision
Introduces symbolic description of environments from images, image formation, analysis, binary processing, filtering, and robotics applications.
Search titles, authors, subjects and dates from across the DARE African Knowledge Repository.
12 resources found in Science, Technology & Innovation.
Scoped to Science, Technology & Innovation · Search all DARE
Introduces symbolic description of environments from images, image formation, analysis, binary processing, filtering, and robotics applications.
Covers computer vision, computer graphics, geometric deep learning, 3D scene representation, reconstruction, and self-supervised training.
Covers feature extraction, biological object recognition, Bayesian decision theory, clustering, and image processing for machine vision.
Brief workshop introducing machine vision, data wrangling, reinforcement learning, and hands-on algorithm training.
Studies representations, contours, level sets, deformation fields, manifold fitting, Markov random fields, EM, and clustering for image analysis.
Covers geometry, deep multi-view methods, differentiable rendering, generative modeling, representation learning, and vision for embodied agents.
Introductory deep learning course with applications to computer vision, NLP, biology, and TensorFlow practice.
Practical introduction to deep neural networks, CNNs, transformers, generative LLMs, and text-to-image models.
Covers supervised learning, regularization, SVMs, VC theory, boosting, feature selection, and vision/text/bioinformatics applications.
Tutorial on optimization strategies for diffusion models in image and video generation including architecture, hardware efficiency, and inference.
Covers digital signal and image processing, filtering, feature extraction, modeling, and biomedical applications.
Introduces knowledge representation, problem solving, and learning methods of artificial intelligence.