Vision Field Notes

Build a Computer Vision Portfolio That Gets Clients

A computer vision portfolio has one job: to help a stranger believe you can solve their problem. Most portfolios fail at this because they show a list of tutorials, a pile of notebooks, or a headline number with no context.

A good portfolio shows a few projects, each explained clearly and honestly, in a way that a non-specialist can follow in a couple of minutes. This article covers what to include, how to present results without overstating them, and how to make demos that people actually open.

Who is reading

Think about the people who will look at your work.

Write each project page so the top answers the first reader, and the lower sections answer the second.

Choose projects that look like real work

Three to five strong projects beat fifteen weak ones. Prefer projects that look like paid work:

For example, the author built CV Test Bench, a tool to test detection models on camera feeds with alerts and zones. A tool like that shows that you think about the whole workflow and not just a model file.

Avoid making your portfolio only well-known tutorial datasets and standard exercises. They show you can follow instructions, but many other people show the same thing. If you do use a public dataset, add something of your own: a new test, a deployment, a clear error analysis, or a realistic use case.

If you have no client work yet, create your own scenario and be clear it is a self-initiated project. That is acceptable. Pretending it was client work is not.

What each project page should contain

Use the same structure every time, so readers know where to look.

  1. The problem, in one or two plain sentences. What was the goal and who would use the result?
  2. A visual. A short video or GIF of the output on real footage is the most convincing thing you can show. Before-and-after helps.
  3. Your role and the scope. What you did, and what you did not do.
  4. Data. Where it came from, how many images or clips, how it was labelled, and how it was split. Say that you split by video or scene, not randomly by frame, if you did. See train/validation split for video frames.
  5. Method. Model, key settings, and why you chose them. Keep it short.
  6. Results, honestly. Metrics on held-out data, per-class where it matters, and what the numbers mean in practical terms. See mAP, precision and recall.
  7. Failures. Show where it goes wrong and what you learned. This builds trust more than a flawless demo.
  8. Deployment. How it runs, on what hardware, and what you measured. Use real measurements only. See measuring FPS and latency correctly.
  9. Links. Code, a live demo, and a write-up.
Wireframe of a project page with nine stacked sections: 1 problem in one or two plain sentences; 2 visual, a short video or GIF on real footage, shown as a larger block with a placeholder for output on real footage; 3 your role and the scope; 4 data: source, size, labelling, split; 5 method: model, key settings, why; 6 results on held-out data, per class; 7 failures and what you learned; 8 deployment: hardware, measured speed; 9 links: code, live demo, write-up. A blue bracket beside sections 1 to 3 is labelled business reader, understands the problem and sees it working in seconds. An orange bracket beside sections 4 to 9 is labelled technical reader, checks the split, the metrics, the failures and the hardware.
Caption: The top three sections serve the person deciding whether to keep reading; everything below serves the person checking your method. Using the same order on every project page makes both jobs easier.

Present results honestly

Clients with experience have seen inflated claims. Honest reporting sets you apart.

Two frames side by side with detection boxes. On the left, titled works, a worker in a hard hat and orange high-visibility vest in a warehouse is boxed and labelled person 0.89. On the right, titled fails, a woman walking across a room seen from a high wide-angle camera is boxed but labelled dog 0.48.
Caption: The same model, shown honestly: a clean detection next to a wrong label from an unusual high, wide-angle view. A pair like this tells a client more than a page of perfect examples. Footage: Intel IoT DevKit sample videos (CC BY 4.0). Detections: YOLOv8n.

Never invent a client, a case study or a result. If a client was involved but their name is confidential, say that the work was for a client in a certain sector and that details are private, and only if it is true.

Make demos people will open

A demo that works with one click is worth more than a long description.

Test the demo from a fresh machine or a fresh environment. A demo that breaks on first click does more harm than having none.

If your projects need a hosted site, a domain and hosting for a personal page is optional. A GitHub profile and a simple page are enough to start.

Privacy and rights

Do not publish footage of identifiable people without permission. Blur or avoid faces and number plates in public material, or use footage you recorded with consent or that has a licence permitting reuse. Do not publish anything covered by a client's confidentiality terms. When in doubt, ask. See privacy and ethics in camera analytics. This is not legal advice.

Write a clear profile

Besides project pages, your front page or profile needs:

Keep it short. A visitor should understand in under a minute what to do next.

Keep improving it

Review the portfolio every few months. Remove old projects that no longer represent you. Replace weak visuals. Add what you learned from real work, within confidentiality limits. If you take on freelance work, use the lessons to improve your pitch. See freelancing in computer vision.

Checklist

Next steps: host computer vision demos for free on GitHub Pages, freelancing in computer vision.