Danil — ML and Data Science Developer
Languages
Frameworks
Libraries/APIs
Danil took part in developing a system to monitor public transport drivers, ensuring they don't use mobile phones while driving. The system was also required to check whether the camera in the driver's cabin was rotated correctly and monitor it to ensure that it was working all the time. He also organized deploying the final models to the client's machine.
Read moreDanil played a crucial role in creating a solution for merchandisers who compare the real arrangement of goods with a plan. He applied Optical Character Recognition (OCR) and one-shot learning techniques to search a product database. The generation of images in Blender and the development of tools marking real goods were required. Danil experimented with various detection and classification approaches, taught OCR models, developed image generation using Blender, and ported and optimized models for Android devices.
Read moreDanil contributed to a system designed to identify traffic violations by detecting cars, comparing them across camera angles, recognizing license plates, and identifying violations. The project required different OCR approaches for license plate recognition.
Read moreDanil created an application that automatically segments text into semantic paragraphs. Various NLP approaches and neural networks based on transformers, such as BERT, were used.
Read more
