Case Studies

A property analysis software for a real estate investment firm looking to automate their property assessment efforts: detection of buildings and their types, vegetation, road access, and more.

A system for secure internal documents viewing to reduce data leaking and improve employee training experience

An AI-based bird detection system for backyard wildlife observation. Real-time detection and observation of over 120 bird species and 20 mammal species

A solution for a bankruptcy services company which automatically gathers data from online bankruptcy databases

A user-friendly app for simple analysis of urine test strips. Automatic test result generation based on the colors of the chemical pads.

Our client evaluates the construction of buildings and prepares bills of quantities. Buildings can be very different: a private house, an apartment building, or an office building. This process is time-consuming: making a cost estimation for a small building takes about two hours for an experienced specialist.

A digital guide for all museum-goers, our image recognition app is able to detect art pieces from any angle instantly and provide information about the piece in text form.

In the age of product marketplaces and steep competition, keeping an eye out for customer feedback is essential for marketing products. We were approached by a marketing agency looking to gather customer reviews of competitors' products on Amazon and analyze them to create better marketing materials with customer feedback in mind.

We have developed a computer vision monitoring system for a bottling factory. The system helps to identify improperly canned bottles and low filling lines, reducing the number of defective bottles and improving customer satisfaction by providing consistent quality of products. The system is more efficient than daily checkups of random bottles as it detects every faulty bottle, eliminating the need to throw out a whole batch.

Machine learning is a field of software development that has become very popular not only among software developers themselves but among regular people too. Developing a machine learning model of your own requires a high level of knowledge and experience in the field. We have been a part of a project dedicated to making machine learning accessible to anyone.

With the huge amount of information coming our way everyday, it becomes increasingly difficult to keep up with the current events as news are often segmented into bite size pieces of content in order to increase the amount of clicks and visitors to a website. The amount of different news websites out there makes research even more difficult as you have to visit multiple websites to get the full story. Our client, a new local startup, has decided to put an end to this and create a platform which would automatically gather news articles from different websites and present them in one cohesive timeline with various filtering and search options.

We were tasked with the development of a system which would take an image as input and provide a social media caption as output. The text had to not only match the content of the image, but also be indistinguishable from that written by a human.