EmoEyes: A Machine Learning Exploration of Emotional States Through Eye Movement Tracking in Visual Content

In this paper, our primary focus revolves around addressing the intricate challenge of detecting human emotion through the analysis of eye expressions. The significance of the eyes as windows to the mind is a universally acknowledged phenomenon, offering profound insights into the underlying emotions of an individual. Leveraging this profound connection, we propose an innovative method for emotion detection by closely monitoring and interpreting the subtle nuances present in eye expressions. Our approach entails processing a series of live images, engaging in a dynamic analysis to discern the emotional states of individuals. By tracking the evolving patterns of eye expressions within a continuous stream of images, we aim to unveil the emotional landscape of the subjects. This method not only offers a real-time assessment of emotions but also provides a comprehensive understanding of the temporal dynamics inherent in human expressions using the modern era of computational ways like Machine Learning and computer intelligence. The proposed methodology extends beyond mere detection, as we introduce a novel dimension to our approach - the translation of detected emotions. Once an emotion is successfully identified through our method, we incorporate a mechanism to translate and articulate these emotional states. This step enhances the interpretability of our system, allowing for a more nuanced and communicative representation of the detected emotions.