Individual Identification Using Dynamic Facial

Individual Identification using Dynamic Facial Expressions with Hidden Active Appearance Markov Models. Adam Matthew Gaweda, 2010. Thesis Paper, University of North Carolina Wilmington. Determining identity is becoming an increasingly important and heavily researched area of computational intelligence. Typically measurable biological characteristics, or biometrics, are used to quantify the physical features of an individual in order to use them as a means of identification. Common biometrics, such as fingerprints, the iris, and one’s voice, assist in the determining process. There have been psychological studies recently that indicate a new biometric, body language with a focus on the expressions made from the face, could be used. In this work, the hypothesis is that facial dynamics of an individual face could be used as an effective biometric for person identification. The method described here applies Stacked Active Shape Models for automated face detection and labeling, Active Appearance Models for feature extraction, and Hidden Markov Models for data analysis. Individual models are constructed for each person in this scenario and used to test identification with new video of facial expressions of the same individuals. Results confirm the hypothesis and demonstrate the efficacy of the potential approach.