We have developed software for facial emotions recognition. EmoDetect recognizes up to 20 informative local facial features that characterize a human's psycho-emotional state (ASM).
Our unique classifier of emotions combines separated algorithms to make a quality of emotion recognition more accurate. The classifier can define six basic emotions: joy, surprise, sadness, anger, fear, disgust.
Technologies and opportunities:
The coding system of facial movements of P. Ekman - calculation of motor units and their classification by the coding system of facial movements of P. Ekman (FACS Action Units)
Recognition of emotions by three independent classifiers - a neural network trained on a huge basis, a system of decision rules and system based on a weighted sum of features
The ability to set a neutral facial expression by the operator for even greater adaptability of the algorithm to the individual characteristics of each person
Plotting a graph of dynamic changes in the intensity of emotions of a participant and the formation of a report on the results of video processing
API to integrate EmoDetect into your products
Record video files from a webcam are available
The program has built-in technologies for determining the orientation of the head and tracking the direction of gaze, controlling the mouse cursor on the computer (eye tracking + head / face movements)
Developed in our company neuroSkill software allows conducting researches on the evaluation and improvement of human's physiological and cognitive state.
List of test categories:
Cognitive memory test: working memory, visual gnosis, reaction time
Cognitive attention test: visual attention, visual gnosis, reaction time