Computer Vision · London

Computer Vision Development Agency

Award-winning computer vision agency working across object recognition, face recognition, OCR, quality control, movement tracking, measurement from images, pattern detection and more, with each model built as its own project.

Every step, with engineers who have built vision systems

Most companies cannot tell in advance whether a vision model will be accurate enough on their own images. We have delivered more than 50 projects, and we guide you through every stage of this one.

  1. A free first call

    We start with a free call to look at the images or video you have, what you need read from them and how accurate that has to be. You leave with our view of whether a vision model can do it, and we will say plainly when it cannot.

  2. Costs, savings and payback

    Before anything is built and before you commit any money, you get a written breakdown of what the work will cost, what it should save you and how long it takes to pay for itself. The scope is fixed and so is the price.

  3. Built in agreed stages

    We agree the stages of the build with you before we start, beginning with a model trained on your own images so you can see how well it performs early. You pay for each stage once it is finished and working.

  4. Support once it is live

    We stay on hand after launch to retrain the model as your images change, fix anything that breaks and extend it to new checks. All code and intellectual property belongs to you on payment, so continued support is not a condition of keeping it.

Computer vision projects we have delivered

Each of these started with a judgement someone was making by eye, and ended with a model making it consistently at scale.

  • Vehicle imaging platform

    A company producing vehicle photography at scale needed every image to look consistent, at a volume where no team could check each one by eye. Over a multi-year engagement, CodeLeap built the capture apps and computer vision pipeline that standardise, enhance and quality-check every shot automatically.

    Read more
  • Medical test scanning app

    Colour-change screening tests are read by eye, which makes the result subjective and hard to track over time. CodeLeap built a computer vision algorithm that reads the test objectively from a photograph taken on a phone, together with the apps around it.

    Read more
  • Automated vehicle video generation

    A company working in automotive imaging wanted a branded promotional video for every vehicle listing, at a volume no editing team could reach. CodeLeap built the video system end to end, and it has run in production since, producing listing videos with no human editing step.

    Read more

What our clients are saying

Real reviews from clients we have delivered for, on Clutch and elsewhere.

  • They are incredibly diligent in the quality of work they produce, and go above and beyond when it comes to solving issues faced within the project, and to ensure we meet strict project deadlines. You never feel like you are one of many clients, and they ensure they are always there to help with any need you have, no matter how big or small.
    Amelia Parmiter Marketing Manager, Marble
  • The enthusiasm, understanding of our mission, and passion from the first few minutes of the call were the deciding factors in choosing CodeLeap. Within 3 months of our app launching, we had over 1,500 downloads, appeared in leading publications from Forbes, The Metro, Marie Claire, Women's Fitness and many more, and started raising further investment.
    Charlie CEO, Becon
  • CodeLeap made me feel like my options were limitless in terms of what could be achieved, which was critical to me as we were creating something very unique. I'm glad I chose Codeleap over a large corporation as the personable approach resulted in a smooth and pleasant experience.
    James CEO, Bearable
  • Working with CodeLeap was a very good experience from both a professional and personal point of view. These people know what they are doing and are both efficient and clever and made a good partner. I wouldn't hesitate to recommend CodeLeap.
    John CEO, Neurometrics-Diab
  • CodeLeap adds so much value and goes above and beyond what I expected. CodeLeap's team is very flexible with all the different requests we've put in front of them. They've also been great with the whole business side of things, and being able to forecast for this industry is really helpful. Overall, I'm completely satisfied with their work — they've been incredibly helpful.
    Johanne CEO, Cherry

Awards & partnerships

Our partners, and independent rankings from Clutch, The Manifest, SME News and the National Digital Awards.

Flexible, transparent pricing

  • Feasibility study

    Can it be done

    • One to two weeks at a fixed price
    • Your own images and video assessed
    • A model tested on a sample of them
    • Accuracy you can expect, stated in writing
    • A costed recommendation on whether to build
  • Vision model build

    One task, built and live

    • One vision task built end to end
    • A model trained on your own material
    • Built into the software you already run
    • Fixed scope and price agreed before building
    • Handover, documentation and a month of support
  • Vision platform

    Several models, running at scale

    • Several vision tasks across one connected system
    • Capture apps and processing pipelines where needed
    • Retraining as your images and products change
    • Delivered in phases, each one live first
    • A named team for the full engagement

Any questions? We're here to answer

Everything you might want to know before starting a project with us.

  • A single vision task built end to end and put into production usually starts at £15,000, and a platform running several models starts at around £40,000. What moves the figure is how much labelled material exists already, how accurate the result has to be, and where the model needs to run. A short feasibility study costs from £3,000.

  • Accuracy depends far more on the images than on the model. A camera in a fixed position with steady lighting reaches a much higher rate on a clear task than photographs taken by the public in varying conditions. The only honest figure comes from testing a model on a real sample of your own material before anything is built.

  • Less than most people expect. A model can usually be started from one already trained on general images and adapted with a few hundred examples of your own, rather than the tens of thousands often quoted. Where examples are rare, such as a fault that seldom occurs, more collection is needed and that is established early.

  • A single vision task usually takes eight to twelve weeks from agreed scope to live use, with a feasibility study beforehand running one to two weeks. A platform with several models runs in phases over several months, each phase live before the next begins. Collecting and labelling enough material is what most often stretches the timeline.

  • Yes. A trained model can run on a phone, a camera or a small computer on site, so images never leave the building. That suits work covered by data protection rules and places where the connection is poor. Running locally limits how large the model can be, and that is decided when the work is scoped.

Meet the humans at CodeLeap

A small, experienced team of designers, engineers and problem-solvers working closely with you from first idea to final delivery.

Find out what computer vision could read

A free 30-minute call with Vivian or Konrad. Bring the process or idea you have in mind; you'll leave with our honest view of whether it's worth doing and what the first step would be.

  1. 1 Send your enquiry
  2. 2 We get in touch within 24 hours
  3. 3 We send you a detailed proposal

Prefer to reach us directly? Email us at hello@codeleap.co.uk or call us at +44 (0) 330 122 1101

Book a consultation Get a quote

Related insights

Book a free call with Vivian

COO and co-founder · London

Request a callback

Leave your name and number and we'll call you back.