Image processing and computer vision
Tutorial series: every part of a topic, in order.
by MLHub Labs · 6 parts · about 109 min · beginner
How computers see, from the first pixel: cameras, colour, OpenCV, filters, edges, masks and video, with three small projects to build on a laptop …
by MLHub Labs · 13 parts · about 308 min · intermediate
How machines see: convolutions, the classic architectures, transfer learning, detection and segmentation.
Learn how OpenCV turns raw brightness changes into edges, how edges become contours, and how contours let you measure, count …
MLHub Deep Learning Organization
7 hours ago • 20 min read
Build a small labeled dataset from scratch, train a YOLOv8 model with the ultralytics library, evaluate it with real detection …
MLHub Deep Learning Organization
15 hours ago • 27 min read
A complete, runnable walkthrough of loading a pretrained ResNet18, replacing its head, fine-tuning it in two phases on an image-folder …
MLHub Deep Learning Organization
2 days, 6 hours ago • 29 min read
Learn how image filters work by sliding a small grid of numbers over every pixel, and see how box, Gaussian, …
MLHub Deep Learning Organization
2 days, 14 hours ago • 21 min read
Learn how OpenCV represents pictures as NumPy arrays, and master the three basic moves every computer vision script starts with: …
MLHub Deep Learning Organization
3 days, 15 hours ago • 18 min read
A practical guide to opening up convolutional networks with saliency maps and Grad-CAM, so you can see which pixels actually …
MLHub Deep Learning Organization
4 days, 7 hours ago • 24 min read
A pixel is just three numbers until you decide what they mean. This part explains RGB, greyscale and HSV from …
MLHub Deep Learning Organization
5 days, 15 hours ago • 15 min read
How vision models learn useful representations from unlabeled images alone, through contrastive learning (SimCLR, MoCo, BYOL) and masked image modeling …
MLHub Deep Learning Organization
6 days, 15 hours ago • 22 min read
How the transformer architecture, originally built for text, was adapted to see images by treating them as sequences of patches, …
MLHub Deep Learning Organization
1 week ago • 24 min read
How neural networks learn to label every pixel in an image, and the difference between painting a scene by category …
MLHub Deep Learning Organization
1 week, 1 day ago • 24 min read
How detectors go from a grid of pixels to a list of labelled boxes: the idea of anchors, how YOLO …
MLHub Deep Learning Organization
1 week, 2 days ago • 27 min read
Before OpenCV ever touches a photo, light has already been bent by a lens, counted by a sensor and rounded …
MLHub Deep Learning Organization
1 week, 4 days ago • 20 min read
• 4 min read
• 6 min read
• 5 min read
• 6 min read
3 weeks, 4 days ago • 17 min read
0 likes • 120 views • 1 comment
4 days, 14 hours ago • 6 min read
0 likes • 65 views • 0 comments
5 days, 15 hours ago • 15 min read
0 likes • 60 views • 0 comments
Get the latest AI insights and tutorials delivered to your inbox.
Your feedback has been received and we'll review it soon.
