Teaching computers to see.
Computer vision allows building the systems that make sense of what cameras record — counting, checking, sorting, reading and understanding, without a person watching the screen.
What can Computer Vision do?
Telling what a picture shows
The software looks at a whole picture and gives it a name.
Some people call this: image classification Read this
Finding things in a picture
The software draws a box around each thing it finds and names it.
Some people call this: object detection Read this
Tracing the exact shape of things
Instead of a rough box, the software marks the exact outline of each thing.
Some people call this: image segmentation Read this
Working out how big something is
The software measures real sizes and distances from pictures, not just what is in them.
Some people call this: photogrammetry Read this
Recognising faces and people
The software compares a face in a picture to faces it already has on file.
Some people call this: facial recognition Read this
Reading text from pictures
The software finds writing in a picture and turns it into text you can search.
Some people call this: optical character recognition Read this
Understanding video
The software watches a moving picture and follows what happens over time.
Some people call this: video analysis Read this
Asking questions about pictures
You ask a question about a picture in ordinary words, and the software answers in ordinary words.
Some people call this: vision and language Read this
Who you'd be working with
I'm Louis Ryan. I've been building computer vision systems for thirteen years, long enough to have developed a feel for the full picture: the camera, the lighting, the mount, and the software that ties it all together.
I spent most of my career in industrial inspection — building systems used by medical device manufacturers to check for defects, measure components to tight tolerances, and inspect stents for breaks. In aerospace, the same systems verified wiring harnesses and checked for contamination after cleaning. I hold six patents on computer vision from that period.
The last product I worked on before going independent was a vision inspection and measurement system that a customer could train themselves — on their own products, on their own faults. It is currently installed and running in over 20,000 locations worldwide. Products I have worked on have been used in medical device plants, aerospace, pharmaceutical laboratories, and by a biological crop protection company to count beneficial insects and mites in production samples.
I work on my own, from Portlaoise. You deal with the person writing the code, not an account manager.
AI estimate
Answer five questions, about two minutes. You’ll get a ballpark price and a timescale by email. No obligation.