A Novel Approach towards Key-point based Real-time Children Emotion Prediction

Emotion prediction is crucial in mental healthcare. It is vital in children as it aids in managing behavioral issues and early identification of emotional distress that can lead to helpful mental health support. The research uniquely centres on children’s emotional expressions, addressing a gap in existing emotion detection studies, which often focus on adults. By specifically tailoring the model to recognize subtle expressions unique to children, the study contributes valuable insights into child psychology and emotion recognition. To address this gap, this work attempts to establish a comprehensive children’s emotion dataset that can facilitate the study of emotions across various pose orientation. The approach introduces advanced key-point detection techniques that capture a higher density of facial landmarks, allowing for more nuanced analysis of emotional expressions. This fine-grained detection enables the identification of subtle changes that are critical in interpreting children’s emotions. An effective face detector with deep architecture is designed to handle all pose orientations from key image frames. Optimal features are then chosen by re-ranking the features using a hybrid feature selection mechanism. The emotion category is revealed by careful analysis of sequences of emotion identification from these features and is not based on a single frame. This framework holds promise for educational institutions and healthcare facilities, offering insights into children’s behavior through emotion analysis. Through experimental analysis and comparisons with three existing SOTA emotion prediction models, it is observed that the proposed system consistently outperforms existing models by exhibiting an accuracy of 77.7 on average. Overall, this study recommended that the proposed model is suitable for children’s emotion prediction.