CECS Technical Reports
CECS Technical Reports Coversheet
The CECS Technical Reports coversheet should be included for all posted Technical Reports. Please contact Dr. Yampolskiy with any questions.
"Avatar Facial Biometric Authentication" by Sonia Ajina, Roman V. Yampolskiy and Najoua Essoukri Ben Amara.
Abstract: With the increasing use of Internet technologies,
the impressive evolution of digital media and the emergence of
electronic commerce, a need for securing virtual worlds remains a
significant challenge because of incessant criminal acts (verbal
harassment, fraud and money laundry, theft or data piracy, etc).
In order to fill the gaps in information security, we propose,
in this paper, an approach for facial recognition applied in the
virtual world on the so calle d “avatars” based on the exploration
of wavelet transforms for the characterization and on Support
Vector Machines (SVM) for the classification.
Various experiments were carried out on a dataset of 1800
images collected from popular virtual worlds representing various
facial expressions of avatars. Recorded tests have shown
promising and encouraging results for such first contribution
within the framework of this new research direction.
"AI-Complete, AI-Hard, or AI-Easy: Classification of Problems in Artificial Intelligence" by Roman V. Yampolskiy
The paper contributes to the development of the theory of AI-Completeness. The intended goal is to provide a classification of problems in the field of Artificial Intelligence with respect to their solvability. We prove Turing Test to be an instance of an AI-Complete problem and further show certain AI applications to be AI-Complete or AI-Hard by utilizing polynomial time reductions. Finally, the paper suggests some directions for future work on the theory of AI-Completeness.