Media Distillery is an AI-based platform that comprises Machine Learning methodologies to recognise every visual and audial aspect inside a video, from Face Recognition to Topic Detection. 

Face recognition: used to identify individuals on a continuously incoming stream of data. By using deep Convolutional Neural Networks, Media Distillery technology recognizes the faces of all people that are known to the algorithms. With this, users can receive notifications when their favourite athletes, politicians or pop stars are on television, monitor the context they appear in, and receive personal recommendations.

Speech recognition: Media Distillery is always using the latest speech recognition algorithms to ensure high-quality recognition optimized for the type of audio or video. The large vocabulary system based on deep learning is able to recognize a wide spectrum of languages. A skilled data science team is able to create a speech model for each application to ensure high quality.

Object recognition: General object recognition gives additional value to the platform by providing more context to the analyzed content. By using the Media Distillery query language, users can combine the results of, for example, face recognition with certain objects that are found. A database of over a thousand objects enables very detailed context description to enrich the results retrieved by the system.

Logo recognition: To recognize brands and logos at a large scale in real-time, the latest GPU-powered Deep Learning algorithms are used. In a multi-step approach, the algorithms used first identify areas of interest using Region Proposal Networks and then determine if there is a logo visible. Media Distillery can train the system by providing it with a number of example images. From then on, it will be able to recognize a new brand.

Text (OCR) recognition: The Media Distillery state-of-the-art text recognition technology can translate visible words in video streams into searchable text. This way you can search through text that appears in video the same way you can search through text that exists in documents. This technology can help translate and interpret subtitles, identify brands and even index name tags.

Topic detection: To provide a more high-level entry to the raw data retrieved by all single analyses, the user is enabled to query topics in the Media Distillery search engine by using topic detection. Topic detection uses models that create word embeddings based on N-grams, and with the help of these embeddings, advanced machine learning algorithms can be trained to classify entire documents for topics.