Automatic documents, images and video processing

In this project I was responsible for developing deep learning algorithms for speech recognition, optical character recognition, and document segmentation to be used on the LMS platform for knowledge management. The LMS platform will help to optimize organizational knowledge management, automate employee compliance training and scale-up learning processes. The developed system will be supported by algorithms based on deep learning methods for the processing of audiovisual and text data.

Main tasks: • Development of speech recognition algorithms based on machine learning methods. • Development of OCR (Optical Character Recognition) algorithms. • Development of document segmentation algorithms.

Technologies used: Python, Pytorch

Learn more about the project

Project’s website: samelane.com