Recognition is the ability to interpret and assign meaning of what is perceived. The recognition of emotions in facial expressions by computer is an emerging and challenging problem to be explored in various areas of application.In the context of human and behavioral cognition, we seek to understand if there is a consensus between the ways of expression externalized by individuals, whether they come from biological or social factors.In the computational area, understanding computationally what humans are expressing through face-captured images or videos opens up a range of possibilities to be explored.Computational resources allow the elaboration of algorithms that have the ability to interpret and read facial expressions performed by humans, in this sense, it is a tool of relevant importance to approximate the interaction performed by human-computer.There are instruments called assessment scales, used to investigate the existence of symptoms in mental health, which can alert the existence of psychological distress. Thus, this research project aims to study the possible association of psychological symptoms with the recognition of emotions in facial expressions as use of computational models Initially, psychological symptom rating scales will be applied to volunteer participants. Then, the facial expressions of the participants, digitally captured, should be recorded based on a series of protocol-determined guidelines. The captured faces will be analyzed based on their own dataset, using a computational method called convolutional neural network, where the results can be linked with the meaning of the respective facial expression presented, be it fear, anger, satisfaction, neutral, among others.The results of this step should provide a basis for comparative analysis with the information collected and the psychological symptom rating scales.

Project Registered in SIGPEX UFSC 201905318.