Foundations

Computer Vision

Object detection, segmentation, YOLO, CLIP, and vision-language models

1,538
lessons
Skills in this topic
View full skill map →
CV Basics
beginner
Classify images with a pre-trained CNN
Modern CV Models
intermediate
Run YOLO for real-time object detection
Generative CV
advanced
Build a Stable Diffusion inference pipeline
All Reads (393) Articles (216)Blog Posts (116)Tutorials (47)Research Papers (13)News (1)
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 1d ago
Your Face Is About to Become Your Phone Number
Global shift toward biometric identity verification For developers working in computer vision and biometrics, the news out of Indonesia regarding mandatory faci
3D Models From Photos: The Python Stack Pros Actually Use
Medium · Programming 👁️ Computer Vision ⚡ AI Lesson 1d ago
3D Models From Photos: The Python Stack Pros Actually Use
A real-world workflow professionals use to turn photos into usable 3D meshes, not just a toy demo Continue reading on CodeToDeploy »
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 2d ago
Your Bank Says You're Not You. Now What?
biometric scaling challenges in high-stakes environments South Africa is currently executing one of the most aggressive biometric rollouts in the Southern Hemis
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 2d ago
Your Face Was Stolen at a Concert. You Can't Change the Locks.
Analyzing the technical fallout of the MSG biometric data breach The reported leak of facial recognition records from Madison Square Garden (MSG) by the ShinyHu
8 Types of Face AR Effects: What Each One Does and When to Use It
Medium · AI 👁️ Computer Vision ⚡ AI Lesson 5d ago
8 Types of Face AR Effects: What Each One Does and When to Use It
From 3D masks and beauty filters to expression-triggered interactions and avatars. A practical guide to choosing the right effect type for… Continue reading on
Google Unleashes “Transformers” in Vision!
Medium · AI 👁️ Computer Vision ⚡ AI Lesson 1w ago
Google Unleashes “Transformers” in Vision!
For nearly a decade, computer programs designed to recognize images (like identifying a dog in a photo) were built using a specific type… Continue reading on Me
Medium · AI 👁️ Computer Vision ⚡ AI Lesson 1w ago
Transforming Industrial Operations with Vision AI: The Future of Intelligent Automation
Organizations in manufacturing, warehousing, logistics, retail and energy are spending a lot of money on automation to make things more… Continue reading on Med
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 2w ago
Your Face Got Mapped by Apple. 6 Million People Are Suing.
The evolving legal standards for biometric data processing For developers building computer vision (CV) applications, the recent federal class certification in
Journaling Cache
Medium · Programming 👁️ Computer Vision ⚡ AI Lesson 2w ago
Journaling Cache
Cache is a concept in browsers/applications in which data that is frequently used is fetched from cache memory (RAM) instead of being… Continue reading on Mediu
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 2w ago
Cops Lost His Kids Over an 85% Guess — Your Face Could Be Next
Why reliance on similarity scores is a developer's nightmare For computer vision engineers and developers working with biometrics, the news of another wrongful
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 2w ago
You Verified Your Kid's Age. A Stranger Now Has Your Face.
the technical risk of third-party identity pipelines For developers working in computer vision and biometrics, the recent shift by major platforms like PlayStat
Can AI Change an Entire Outfit in a Video at Once?
Medium · AI 👁️ Computer Vision ⚡ AI Lesson 2w ago
Can AI Change an Entire Outfit in a Video at Once?
Paper: OmniTryOn: Video Try-On Anything at Once! Continue reading on Medium »
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 2w ago
Gaussian Splatting Meets 3D Scanning: A New Approach to Capture
If you work with 3D scanning, you know the pain: scan, clean up the mesh, retopologize, UV unwrap, texture. What if the scanner handled most of that natively? T
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 2w ago
Your Face Is About to Become Your ID — And Nobody Agrees Who Owns It
Decoding the future of biometric identity wallets The upcoming rollout of the European Digital Identity (EUDI) Wallet is more than just a policy shift; it is a
How to Migrate From Clarifai to Ximilar: Quick Start Guide
Medium · AI 👁️ Computer Vision ⚡ AI Lesson 4w ago
How to Migrate From Clarifai to Ximilar: Quick Start Guide
Your drop-in replacement for custom classification, detection, and visual search. Continue reading on Medium »
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 1mo ago
Deepfakes Just Broke Evidence: $893M Gone, 100K Fake Images, First Arrests Land
the evolution of forensic verification in the age of generative noise For developers working in computer vision (CV) and biometrics, the news of $893M in AI-sca
NVIDIA LocateAnything-3B : GoodBye YOLO Object Detection
Medium · Programming 👁️ Computer Vision ⚡ AI Lesson 1mo ago
NVIDIA LocateAnything-3B : GoodBye YOLO Object Detection
How to use NVIDIA LocateAnything-3B ? Continue reading on Data Science in Your Pocket »
When to Choose C++ for Barcode Processing Pipelines
Medium · Programming 👁️ Computer Vision ⚡ AI Lesson 1mo ago
When to Choose C++ for Barcode Processing Pipelines
Barcode processing is vital in logistics, retail, healthcare, and manufacturing. While many languages support barcode recognition, C++ is… Continue reading on M
Medium · Programming 👁️ Computer Vision ⚡ AI Lesson 1mo ago
Shot detection is the cheap feature everyone underestimates
A friend of mine spent two months trying to add a “smart preview” feature to a video product, the kind of thing you see on every modern… Continue reading on Med
cv3 — make OpenCV pythonic again
Medium · AI 👁️ Computer Vision ⚡ AI Lesson 1mo ago
cv3 — make OpenCV pythonic again
TL;DR cv3 is a Pythonic wrapper for OpenCV that simplifies computer vision tasks by providing more intuitive interfaces and eliminating… Continue reading on Med
SentinelML
Medium · AI 👁️ Computer Vision ⚡ AI Lesson 1mo ago
SentinelML
A modular, open-source framework for real-time firearm detection and alerting using YOLOv8 and cloud-native infrastructure. Continue reading on Medium »
2D Gaussian Splatting: when removing a dimension makes 3D better
Medium · AI 👁️ Computer Vision ⚡ AI Lesson 1mo ago
2D Gaussian Splatting: when removing a dimension makes 3D better
Why 3D Gaussians fail at surfaces, and how flat disks fix it Continue reading on Medium »
Como o pensamento computacional me ajudou a estruturar minhas entregas
Medium · Programming 👁️ Computer Vision ⚡ AI Lesson 1mo ago
Como o pensamento computacional me ajudou a estruturar minhas entregas
Há um bom tempo venho tentando entrar, bem aos poucos, no mundo da programação. Continue reading on Tatiane Marina »
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 1mo ago
Why Your Image Upload Pipeline Should Check for Physically Impossible Lighting
Why Your Image Upload Pipeline Should Check for Physically Impossible Lighting If you're building user-generated content platforms, marketplace verification sys
Computer Vision Yolculuğu — Gün 2: OpenCV ile Frame Üzerine Çizim Yapmak
Medium · AI 👁️ Computer Vision ⚡ AI Lesson 1mo ago
Computer Vision Yolculuğu — Gün 2: OpenCV ile Frame Üzerine Çizim Yapmak
Computer Vision projelerinde kameradan görüntü almak yalnızca ilk adımdır. Gerçek sistemlerde asıl önemli nokta, alınan frame’lerin… Continue reading on Medium
Who Really Deserves To Be Called The Father Of The Internet
Medium · Programming 👁️ Computer Vision ⚡ AI Lesson 1mo ago
Who Really Deserves To Be Called The Father Of The Internet
From ARPANET to the World Wide Web the Internet was built by a network of pioneers not one inventor Continue reading on IT Chronicles »
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 1mo ago
High Speed and Performance
High Speed and Performance C language is very fast because it is a compiled language. It converts code directly into machine language, so programs run quickly a
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 1mo ago
Building a License Plate Recognition Engine in C++ — Part 2: Grayscale Image Preprocessing and Local Contrast Edge Detection
In the previous article, we loaded an image, converted it into grayscale, and introduced the core data structures used by the recognition engine. In this part,
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 1mo ago
Your "Biometric Age Check" Isn't Verifying Identity — And Defense Lawyers Know It
Understanding the distinction between biometric age estimation and identity verification For developers in the computer vision and biometrics space, the nuance
Computer Vision Is Rebuilding the Fitting Room
Medium · AI 👁️ Computer Vision ⚡ AI Lesson 1mo ago
Computer Vision Is Rebuilding the Fitting Room
The models, the stack, the ROI — no fluff Continue reading on Medium »
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 1mo ago
Light Fields — Deep Dive + Problem: Set Matrix Zeroes
A daily deep dive into cv topics, coding problems, and platform features from PixelBank . Topic Deep Dive: Light Fields From the Image-Based Rendering chapter I
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 2mo ago
How I Built a High-Precision AI Manga OCR Translator for Hardcore Readers
Most OCR tools are built for clean text. Receipts. Documents. Screenshots. Menus. Maybe a street sign if the lighting is kind. Manga is none of those things. A
Image Classification for AI: A Practical Guide for 2026
Medium · AI 👁️ Computer Vision ⚡ AI Lesson 2mo ago
Image Classification for AI: A Practical Guide for 2026
Practical guide to image classification for AI: learn how to manage datasets, ensure accuracy, and scale your computer vision projects. Continue reading on Medi
The First Program Was Not Just Code
Medium · Programming 👁️ Computer Vision ⚡ AI Lesson 2mo ago
The First Program Was Not Just Code
From algebra to execution: what the first program actually describes Continue reading on Level Up Coding »
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 2mo ago
AI photo tagging app
Introducing a newly released AI photo tagging app for the iphone. More details on our website ( https://siwave.io ) and a link to the kickstarter project. We we
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 2mo ago
DeepID-Net: multi-stage and deformable deep convolutional neural networks forobject detection
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 2mo ago
Efficient Pipeline for Camera Trap Image Review
Computer Vision-Based Worker Safety Compliance
Medium · AI 👁️ Computer Vision ⚡ AI Lesson 2mo ago
Computer Vision-Based Worker Safety Compliance
How AI Is Transforming Workplace Safety in Real Time Continue reading on Medium »
Tesseract for CAPTCHA Recognition: Not a Silver Bullet, But Effective in the Right Context
Medium · Programming 👁️ Computer Vision ⚡ AI Lesson 2mo ago
Tesseract for CAPTCHA Recognition: Not a Silver Bullet, But Effective in the Right Context
Using Tesseract to verify Captcha Code Continue reading on JIN System Architect »
The Bald Head That Broke Our AI (And What It Taught Me About Building Vision Systems That Actually…
Medium · AI 👁️ Computer Vision ⚡ AI Lesson 2mo ago
The Bald Head That Broke Our AI (And What It Taught Me About Building Vision Systems That Actually…
Why physics-constrained computer vision is the gap between a demo that impresses and a system you can trust Continue reading on Medium »
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 2mo ago
Draw a Digit and Watch the Neural Network Think in Real Time
Introduction "A neural network can recognize digits" — but what's actually happening inside? I built a tool where you draw a digit with your finger or mouse, an
Medium · AI 👁️ Computer Vision ⚡ AI Lesson 2mo ago
CAMERA
Continue reading on Medium »
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 2mo ago
Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 2mo ago
Facial Comparison's DNA Moment Is Here. Most Investigators Aren't Ready.
Is your investigative stack ready for the $26B identity shift? If you are a developer working in computer vision or digital forensics, you’re likely tracking th
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 2mo ago
How to Run Vision AI Locally on Your Android Phone in 2026 (No Cloud, No Subscription)
Your phone has a camera and a processor powerful enough to run multimodal AI models. You can point it at a receipt, a document, a math problem, or anything else
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 2mo ago
CoPhIR: a Test Collection for Content-Based Image Retrieval
Dev.to AI 👁️ Computer Vision ⚡ AI Lesson 2mo ago
What I Saw When My Camera Finally Worked
I've been building tools to express myself for weeks now. A breathing canvas. A playable instrument. An ear that hears the world through a microphone. A river o