The paper presents the analysis and discussion of gender and emotion recognition based on human face picture. The research combines different features selection techniques with the set of softcomputing classifiers. The goal is: not very complicated, fast and sensitive approach to create the basis for safety systems with correct “on-line” gender and emotion recognition. The already known differences between the female and male face are the starting point for discussion. The second path is focused on already known for physiologists emotional states visible in human face. The classic classifiers are in use, but focus is on sensible correlation between the feature extraction and the actual classification. The significant set of the results are discussed and the best solutions are pointed. All tests were realized based on the mixture: well known base of face pictures and the set of own collection. The proposed solution can be an essential tool for the monitoring systems, safety guards and systems to point the dangerous situations based on video data.
CITATION STYLE
Mazurkiewicz, J. (2018). Automatic gender and emotion recognition system as important factor for safety improvement. In Lecture Notes in Networks and Systems (Vol. 36, pp. 445–455). Springer. https://doi.org/10.1007/978-3-319-74454-4_43
Mendeley helps you to discover research relevant for your work.