Computer vision courses and concepts
Computer vision is the branch of AI that lets computers extract information from images and video: what objects a picture contains, where each one is, or what text it shows. It lets software act on what a camera or scanner captures without a person looking at it, for example reading a license plate to open a gate, checking products for defects on a production line, or turning a scanned page into editable text. Most current vision systems use deep learning, which learns visual patterns from large numbers of labeled example images instead of following hand-written rules. Learning it means understanding the main tasks, such as image classification, object detection, image segmentation and text recognition, and either training a model for one or using a ready-made service that performs it.
Computer vision courses
Use AI — ready-made vision services
Develop AI — build vision into software, in code
Building AI Agents with Multimodal Models
NVIDIA Deep Learning Institute
Community Computer Vision Course
Hugging Face
Computer Vision
Kaggle Learn
Computer Vision Fundamentals with Google Cloud
Google Skills
Deep Learning for Images with PyTorch
DataCamp
Extract insights from visual data on Azure
Microsoft Learn
Image Modeling with Keras
DataCamp
OpenCV Bootcamp
OpenCV University
Computer vision terms explained
Object detection, image segmentation and optical character recognition name specific tasks, which differ in what they return: object detection draws a box around each object it finds, image segmentation labels every pixel to give each object's exact outline, and optical character recognition turns the text in an image into text a computer can search and edit.
Use AI covers using AI tools and services, for visual tasks and others; Develop AI covers building AI systems in code, including training vision models and building applications that use them.