Machine Learning & AI

For an educational startup named Alphary, we designed and developed a language learning application with an AI assistant that analyzes students’ answers and accelerates vocabulary acquisition through recent and relevant feedback. The application relies on NLP algorithms with corpus statistics, semantic analysis, information extraction, and machine learning models. Intellias contributed to Alphary’s recognition by Oxford University Press for their breakthrough NLP solution in the educational sphere.

The Intellias team has built an innovative solution for an Android car keyboard application to recognize drivers’ handwritten text. Our experts have successfully conducted an R&D project that demonstrates our strong technological capabilities and background in neural networks, machine learning, and artificial intelligence. This solution is extremely intuitive, recognizing any natural handwriting: uppercase, lowercase, cursive, block, and even superimposed text. The application’s ability to capture handwritten content from scanned images and even suggest and predict words based on a user’s habits and writing style provides convenience to drivers and increases safety.

Intellias team proved the feasibility of transition from RADAR/LiDAR sensors as the primary data source to stereo vision cameras for further development of a pseudo-LiDAR. This project proved that stereoscopic vision combined with object recognition AI-based algorithm can output data of comparable quality to that of actual Lidar/radar sensors. Moreover, simulated Lidar data has an advantage of higher signal density than actual Lidar data, so the strengths of these data modalities can be complementary.

Intellias designed a contactless payment solution with client authentication based on computer vision and geofenced location tracking. We have provided automatic license plate recognition, car trajectory tracking, and automatic payment based on credit card information. Once the object detection analysis outputs a positive result, it triggers optical character recognition for the license plate detection. The AI&ML team has achieved 94.3% of recognition accuracy even at long distances, in poor weather conditions, and for dusty license plates.