Blog
Learn computer vision by running it — explainers, interactive demos, runnable Python & C++, and honest benchmarks, organized by topic.
Every score in computer vision, from the confusion matrix to FID — the equations, the intuition, and runnable code.
Fundamentals
Camera Models, End to End: Pinhole, Lens Distortion, Calibration & PnP — with OpenCV
How a 3-D point becomes a pixel and back again: the pinhole model and intrinsic matrix K, the extrinsics R|t, Brown–Conrady lens distortion (a corner can move 62 px), Zhang calibration to sub-pixel reprojection error, and solvePnP recovering a 68-px-off pose to ~0. The math, three interactive labs, and runnable OpenCV in Python and C++.
Image processing, computer vision, and computer graphics: one picture, three directions of the arrow
Three fields, one shared object — the digital image. Graphics turns a model into an image (forward), vision turns an image into a model (inverse), and image processing turns an image into a better image. Worked on a single red-ball scene, with a 1957→2026 timeline of how they split apart and re-merged.
How 2D Convolution Works on Images: Kernels, Filters, and the Math, Interactively
2D convolution is the operation behind blur, sharpening, edge detection — and every CNN. Slide a kernel, multiply, sum: see it happen step by step in an interactive demo, apply real kernels to a live image, and get the math plus runnable OpenCV in Python and C++.
From Photons to Pixels: Image Formation and Color Spaces, with OpenCV in Python and C++
How a camera turns light into an array of numbers — projection, sampling, quantization, the Bayer sensor — and the color spaces (RGB/BGR, grayscale, HSV, YCrCb, Lab) you convert between every day. The equations, plus runnable OpenCV in both Python and C++.
Models & Detection
Evaluation
Classification Metrics, From the Ground Up: Precision, Recall, F1, ROC and AUC
The confusion matrix and everything that falls out of it — precision, recall, F1, specificity, the precision/recall trade-off, PR and ROC curves, and AUC — built on one running toy example (a backyard cat-cam), with the equations, the intuition, and scikit-learn.
Image Generation Metrics: FID, IS, KID, LPIPS, and CLIPScore
How do you score images with no ground truth? You compare distributions and use learned perceptual models — Inception Score, Fréchet Inception Distance, KID, LPIPS, and CLIPScore for prompt fidelity — on one running cat-generator example, with the equations, the catches, and torchmetrics.
Multiclass and Multilabel Metrics: Micro, Macro, Weighted, and the Difference That Matters
How precision/recall/F1 scale past two classes — one-vs-rest, and the micro/macro/weighted averaging that decides whether rare classes count. Plus multilabel-specific metrics: subset accuracy, Hamming loss, and top-k — all on one running shelter-camera example, with scikit-learn.
Object Detection Metrics: IoU, AP, and the mAP Everyone Quotes
How detection is scored — IoU to decide a hit, greedy matching into TP/FP/FN, per-class Average Precision as the area under the precision–recall curve, and the COCO mAP@[.5:.95] you see in every paper — all on one running parking-lot example, with torchmetrics.
Object Tracking Metrics: MOTA, MOTP, IDF1, and HOTA
Tracking adds identity over time, so its metrics score two things at once — detecting objects and keeping their IDs consistent. MOTA, MOTP, ID switches, IDF1, and the modern HOTA that balances detection against association — on one running door-cam example, with the equations and motmetrics.
Segmentation Metrics: IoU, Dice, mIoU, and Panoptic Quality
Scoring masks instead of boxes — pixel IoU/Jaccard and the Dice coefficient (and why they're related), mIoU for semantic segmentation, mask-AP for instance segmentation, and Panoptic Quality for the unified task — on one running cat-mask example, with the equations and code.
