Emotion Recognition and Large Language/Image Models

This project will deal with recognition of facial emotion recognition using generative models and comapring the results of GenAI models with key industry standard machine learning models. You will be building a transformer for facial emotion recognition – broadly expressions of happiness, anger, surprise, contempt, and sadness– and for recognising head movements – upward/downward, sideways, and left-right movements are related to the expressions of anger, happiness and so on.

The experience of this project will provide you with an introduction to an emerging branch of AI: systems trained for detecting emotional intelligence. Much of the work in AI is focussed on simulation of cognition – language understanding/production, image understanding/production, knowledge based systems for problem solving, and planning for example.

Once emtion recognition systems have reached a level of maturity – robust performance, minimal training and algorithmic bias, and serious ethical considerations – then the application of these systems will cover areas like marketing/sales, diagnosis, psychiatric diagnosis, fatigue levels amongst key workers like pilots, plant operators, law enforcement operatives.