Computer Vision Lab

Sirma Computer Vision Lab is a research unit of Sirma Solutions. We develop technologies for computer interpretation of 2D and 3D image data sets and video streams. The laboratory conducts research in object detection and recognition areas, human detection and motion analysis, OCR, scene recognition, material recognition, visual measurement etc.

We strive to create products and technologies which find application in diverse industries such as manufacturing, media and entertainment, healthcare, security and robotics.


Invent new technologies relevant to real world scenarios with many business applications – stock images websites, travel portals, digitization of cultural heritage.

Develop a framework for assisted and semi-automatic annotation of images and videos using semantic categories instead of text expressions.

Create open/linked data bridges for image annotation and research – links and references to main big knowledge bases like WordNet, GeoNames, DBPedia, etc.

Develop a framework for assisted image/semantic search in knowledge bases and collections of information and open linked data in semantic repositories.


MARKETvidia™ product line

MARKETvidia™ is an end-to-end platform which integrates facial analytics, in-store analytics, marketing analytics, loyalty management platform and semantic technologies. It helps companies to obtain a 360 customer view and improve customer experience.

With the emergence of omni-channel consumer it has become more difficult to distinguish a specific customer across the variety of touch points (e.g. in-store shopping, e-/m-commerce, social media). Our platform enables retailers to recognize customers and target them in the retail environment. It also identifies customer categories, personal preferences and anticipates their future behavior.

learn more

OCR Toolkit

We are currently developing the OCR Toolkit, optimized for text recognition of images, captured from smartphone digital cameras. Our software achieves state-of-the-art results in low-quality images that are very challenging for other OCR SDK libraries.

There are lots of applications that will benefit from the improved OCR recognition quality, as document scanning, text extraction from receipts, business cards, etc.

Project Janus:

We have started a project related to human movement analysis, which we believe, will become the next revolution in computer vision, introducing a myriad of opportunities for advancement in the areas of computer games, security and healthcare.