Skills and Qualifications
Neural Network Library
Our machine learning dev team developed a library for neural network construction and compiler optimization. These are...
Recognition of Air Signatures for Airsign
Our machine learning dev team developed an algorithm and a mobile application that implements biometrics according to...
Face, Sex, Age, Video Emotion Recognition System For NEC
Our machine learning development team has developed various video analytics tools to accurately identify people based...
High-Speed Vehicle Identification System
Our machine learning dev team developed a complex of neural networks that solved the search and recognition problem...
The main task of the project was to monitor public transport (buses, trams, etc.) drivers and record the cases of mobile phone usage while driving. The system was also required to check whether the camera in the driver's cabin is rotated correctly and monitor it to ensure that it is working all the time. He also organized the deployment of the final models to the client's machine.
Recognition of goods on the shelves
A solution was needed for merchandisers who compare the real arrangement of goods (realograms) with a plan (planogram). OCR and one-shot learning were used to search the product database using triplet loss network training. The generation of images in Blender was required, as was the development of tools marking real goods. Danil experimented with various detection and classification approaches, taught OCR models, developed image generation using Blender, and ported and optimized models for Android devices.
Vehicle detection and license plate recognition
A system to solve the problem of finding traffic violations. For the solution, it was necessary to detect cars, compare and identify cars from different camera angles, find violations, and recognize license plates. The project required different OCR approaches for license plate recognition, etc.
An application for breaking text into paragraphs for a podcast startup. Danil undertook the task of creating a system to automatically break text up into semantic sections. Various NLP approaches were used, as were neural networks - based on transformers such as BERT.