Enhancing Facial Emotion Detection for Depression Detection using Image Integration by Hybrid Dataset Approach

Depression is a critical mental health challenge that impacts millions globally, manifesting through various emotional, cognitive, and behavioural changes. Traditional diagnostic methods often rely on self-reported data and clinical interviews, which may not always capture the refined emotional shifts associated with depression. The proposed research aims to develop a novel approach for depression detection by analysing emotional patterns and expressions using images collected from the interviews and standard data set sources of RAF-DB, FER2013. By applying Machine Learning(ML) techniques, including Convolutional Neural Networks (CNNs) and Haar Cascading, the study builds predictive models that identify depressive symptoms based on emotions that they portray. This emotion-centred approach offers a more objective and sensitive method for early detection of depression, providing a valuable tool for both individuals and healthcare professionals to monitor and address mental health more effectively.