Depression Detection with Convolutional Neural Networks: A Step Towards Improved Mental Health Care

Depression is a mental disease affecting 5% of the population, and its prevalence is increasing. Depression is characterized by feelings of worthlessness, hopelessness, disinterest in enjoyable activities, and sadness, which can result in suicidal thoughts. Traditional approaches to recognizing depression have relied on manually crafted techniques to extract facial expressions, which have their limitations. To address these limitations, this paper proposes using convolutional neural networks (CNNs) as a practical approach for depression recognition. The proposed model in this study involves an eight-step process that includes input data, preprocessing, rescaling, model training, multi-classified results, selecting emotions based on accuracy, retraining the model, and finally, multi-classified results to determine the percentage of depression with greater accuracy.