MitrApp: An Intelligent Recommendation System For Counselling

Abstract

In modern era there has been a phenomenal increase of suicidal syndromes with teens and student population being susceptible the most. Since most of the teens and youth are active in social media, the framework serves more to predict the suicidal tendency of the user. The proposed App captures the face of the user to identify his emotional state and immediately play or encourage him to go through audio or video content that serves as an immediate counselling session with no human intervention. Facial emotion recognition (FER) is an important topic in the fields of computer vision and artificial intelligence owing to its significant academic and commercial potential. This review focuses on studies that exclusively use facial images, because visual expressions are one of the main information channels in interpersonal communication. this paper provides a brief review of researches in the field of FER conducted over the past decades. Deep-learning-based FER approaches using deep networks enabling “end-to-end” learning are then presented. This review primarly focuses on two datasets namely, KDEF(Karolinska Directed Emotional Faces) dataset and Kaggle FER2013 dataset. The proposed App captures the face of the user to identify his emotional state and immediately play or encourage him to go through audio or video content that serves as an immediate counselling session with no human intervention. This paper takes suggests instant counter measures such as recommending some anti-suicidal videos and some online expert support. Since people having suicidal tendency will post/ likes the photos/ images related to the suicide thoughts detection of suicide related objects like suicide rope will help in predicting suicidal behaviour more accurately. Since a large section of community(about 28%) are attempting suicides by means of suicidal rope, a model is trained on the most frequently used suicide rope images.