Artificial intelligence
Image recognition and computer vision
A camera or a phone photo can be a source of data. We build systems that recognize objects, read labels and detect deviations, and pass the results to your software.
What we can do for you
Quality control
Detecting defects, missing parts and non-conformities in photos or camera feed.
Counting and recognition
Recognizing products, packaging and objects and counting them in an image.
Label and code reading
Reading text, serial numbers and codes in difficult conditions.
Mobile app
A photo taken with a phone analyzed on the device or in the cloud.
About this service
AI adoption in a company usually starts with a single process: handling customer inquiries, processing documents, searching company knowledge or forecasting. Depending on the task we build chatbots and assistants, AI agents, process automation, OpenAI API (ChatGPT) integration, generative solutions with RAG, or predictive models.
As a software house we handle the engineering side: connecting the model to your systems, data security (with GDPR in mind), control of model usage costs, and the ability to switch providers without rebuilding the application.
Why Cormo
Faster inspection
Image analysis usually takes seconds and the result is saved in the system.
Repeatability
The same criteria for every photo and every shift.
Tied to the process
The result goes to the warehouse, ERP or a quality report.
Technologies
- Python
- OpenCV
- PyTorch
- React Native
- FastAPI
- Docker
Experience you can rely on
For years we have built business systems in PHP, Python and JavaScript. We treat language models and machine learning as one more component of such a system: first we establish which process should benefit and what data that requires.
We work in line with ISO/IEC 27001
Data security is part of our process, not an add-on at the end of a project.
How we work
- 01
Meeting
We learn the business goal, the users and the project constraints.
- 02
Estimate
We settle the scope, a first estimate and a schedule.
- 03
Delivery
We design, build and test in short iterations.
- 04
Support
We deploy, monitor and evolve the solution after launch.
Estimate calculator
Estimate your project in 2 minutes
Answer a few questions and we will prepare a first estimate and send it to your email. No strings attached.
See also
Chatbots and AI assistants
An assistant that answers customer and employee questions from your documents, price lists and procedures, and hands the case to a person when needed.
AI agents
An AI agent does not only answer, it acts: it fetches data, calls APIs, prepares documents and asks for approval where a person should decide.
Process automation
We take over repetitive work with documents, emails and spreadsheets. Your team handles exceptions and decisions instead of retyping data.
Generative AI
We connect language models to your company knowledge. With RAG, answers rely on current documents and not only on what the model learned earlier.
AI consulting
Before you invest in artificial intelligence, we check where it will bring a measurable result, which data is needed and what it will cost.
Predictive AI
The data your company already holds can suggest decisions. We build models that forecast demand, flag deviations and assess risk.
Data science and analytics
We organize data from many sources and present it in a form you can use daily: reports, dashboards and analyses for management and teams.
OpenAI (ChatGPT) integration
We connect OpenAI models to the apps, CRM and processes in your company. We design it so you can change the model provider without rebuilding the whole system.
AI document processing
Instead of retyping invoices, contracts and orders, the system reads them, pulls out the needed data and hands it to accounting software or an ERP system. A person checks only what is uncertain.
AI for e-commerce
A store holds data that can turn into sales: order history, search queries and product descriptions. We add AI features that help customers and save your team time.
AI-powered applications
We help you build a new AI-based product or add AI features to an existing app or SaaS platform, so they are fast, secure and affordable to run.
Frequently asked questions
What exactly do you deliver in an image recognition project?
We deliver a system that takes a photo or camera image, recognizes what you need and passes the result to your software. That can be defect detection, counting products, reading labels and serial numbers, or a mobile app that analyzes a phone photo. It includes the model, backend, integrations and documentation. We do not design cameras, lighting or the station itself. That is done by the client or a hardware partner, while we handle the software.
What does a computer vision project look like and how long does it take?
The first step is collecting real photos from the place where the system will work, because everything depends on them. Then we check whether the task is solvable by building a trial version and measuring its performance. If results are good, we extend it with integration and an interface. We work iteratively. Duration depends on the amount and quality of data and how hard the conditions are, so we give a realistic date after a test on your photos.
What drives the cost of an image recognition system?
The biggest factors are task difficulty (counting simple items versus finding tiny defects), image conditions and how much labeled data is available to train the model. It also matters whether analysis runs on a phone, a local device or in the cloud, and how fast it must be. Integrations with your systems add scope. We start with a trial test on your photos, because without them any figure would be a guess.
How accurate is image recognition, and what about errors in difficult conditions?
Accuracy depends on photo quality, lighting and the variety of examples, so we do not promise any result upfront. We measure it on your data and show where the model fails, for example with glare or dirt. For uncertain cases we plan for human review. Images can contain sensitive information, so we restrict access and follow practices aligned with ISO/IEC 27001.
What happens to the model after launch when products or conditions change?
Vision models age when packaging, lighting or the product line changes. After launch it is worth collecting cases where the system was wrong and retraining the model from time to time. We can monitor this and run it in later stages. The code, documentation and prepared data belong to you, so you are not tied to us. When the number of cameras or photos grows, we adapt the architecture to the larger load.
Get in touch
Tell us about your idea
Describe what you need. We will reply with a proposal for the next steps.