# Understanding Computer Vision: From Pixels to Object Detection
Introduction Computer vision is a field of artificial intelligence that enables computers to process and understand images and videos. It can be use…
Testing & QA
⚑ Report a ProblemLatest Testing & QA news from Tech News
All topics
agents
ai
api
architecture
automation
backend
beginners
career
claude
cybersecurity
devchallenge
devops
discuss
javascript
llm
machinelearning
mcp
node
opensource
performance
productivity
programming
python
security
showdev
softwareengineering
testing
tutorial
typescript
webdev
Building a Photo-Based Card Grader: Computer Vision Where the LLM Doesn't Pick the Score
Trading-card grading looks like an image-classification problem until you try to build it. A grade is driven by several physical properties at once:…
"You Got a Labeled Dataset. Here's How to Actually Verify It's Trustworthy."
Worked example: Suppose you're spot-checking a batch of vehicle bounding boxes against a small gold-standard subset. One box overlaps its reference…
Choosing Video Frames by Content Instead of by a Clock
Code: Megapixel99/video-timeline The usual way to hand a video to a language model is to pull a handful of screenshots and let it reason over them.…
Resolving Algorithm Output Inconsistencies When Porting Computer Vision from Python OpenCV to Niche Frameworks
Introduction Porting computer vision algorithms across frameworks—such as from Python with OpenCV to a niche image processing platform—inevitably ex…
The Critic Panel: Teaching an AI Pipeline to Check Its Own Work
Every critic in the main video-generation service's pipeline started with the same structural limit: it graded one picture. Is this frame composed c…
Three Phases of AI B-Roll: From Manual Beats to Vision-Authored Cutaways
B-roll is what makes a UGC testimonial feel edited rather than generated. The presenter talks to camera; cutaways show the product in hand, the labe…
Can AI Remember What It Sees?
So, I have been asking myself this question for quite a while, Can AI actually remember what it sees? and tell a user later that "I saw X at place Y…
Why scrolling screenshots fall apart on video feeds
I maintain a small Android app that stitches a scrolling screen into one long image. It worked well until people started pointing it at social feeds…
The Matte Learns Only Inside the Band
A bad cutout rarely announces itself as a bad cutout. The car lands on a new backdrop, the paint looks clean, then a thin piece is gone. An antenna.…
Android Computer Vision for Robot Navigation
Android Computer Vision for Robot Navigation Introduction Navigation requires a robot to understand its surroundings. Cameras can provide useful vis…
Segmentation Is Not the Finish Line
A car can be cut out cleanly and still look pasted on. The outline is right. The tires touch the ground. The mirrors have no halo. The giveaway is l…
CarSegNet v2: One Lot Photo to a Showroom Composite
A buyer does not open a listing and ask what the mask IoU was. They look at the mirror stalk, the antenna, the gaps between wheel spokes, the glass,…
The Model Is the Easy Part: What a Real-Time Computer Vision Product Actually Takes
I used to think computer vision was a model problem. It is a pipeline problem, and the model is the easy part. Here is the pattern I keep seeing. A…
Testing Face Embedding Nearest Neighbor Search with OpenCV SFace
Testing Face Embedding Nearest Neighbor Search with OpenCV SFace Hello, everyone. Face recognition can sound like a big topic, but technically it ca…
Vision Language Models — When AI Learns to See and Talk (Part 3 of 3)
Originally published on my blog . Cross-posted here with a canonical link. This is Part 3 of a 3-part series on the transformer revolution in vision…
Don't Buy It, Build It: Crafting an Open-Source, Edge-Computing AI Dashcam
Preface Every day, thousands of creative ideas sit completely dormant on workshop shelves around the world. A high-performance microprocessor sits i…
The SDXL VAE overflow that decoded black images in fp16
TL;DR: The SDXL VAE decoder pushes activations past 65504, the max value fp16 can hold, so the last decode step overflows to inf and you get a fully…
Winograd convolutions cost us 2 mAP and we didn't notice for a month
TL;DR: We turned on Winograd convolution to shave latency off a pedestrian detector running on a Cortex-A53, got a clean 18% speedup, and silently l…
Image Reconstruction Using Deep Learning: A Complete Guide
A comprehensive guide covering history, techniques, datasets, algorithms, tools, real-world applications, and final year project ideas for image rec…
An AI Module Smaller Than a Smartphone Photo. Are We Underestimating the Computer We Carry Every Day?
The Idea and the Main Engineering Challenges Recently, I released a new offline AI feature for my Android application as a separate module. The enti…
Our event-camera detector lost 6 mAP to a badly chosen accumulation window
TL;DR: We spent three weeks chasing a 6 mAP regression in an event-camera object detector. The model was fine. The bug was the accumulation window w…
QAT vs PTQ on our edge vision model: 6 months of A/B data
TL;DR: We ran post-training quantisation (PTQ) and quantisation-aware training (QAT) side by side on the same defect-classification model deployed o…
How I Built a Drone-Based Crack Detection Pipeline on AWS
I needed to build a pipeline that takes drone footage of infrastructure (bridges, facades, roads), detects surface defects like cracks and corrosion…
I Replaced My $500 GPU with a $75 Raspberry Pi: How Gemma 4 Makes Computer Vision 10x Cheaper
This is a submission for the Gemma 4 Challenge: Write About Gemma 4 I Replaced My $500 GPU with a $75 Raspberry Pi: How Gemma 4 Makes Computer Visio…