Evolutionary Deep-indicators Algorithm in Facial Recognition improvement over SoC

Abstract

    This Paper proposes a new approach for facial recognition based on an Evolutionary Deep-indicators Algorithm. The main purpose of this strategy is to reach a model which can compete with human vision sensibility. As it can be called intelligent and optimized model, it revolves around a facial chromosome that benefits from all paradigms in the same area such as Gaussian model, Deep learning, Eigen vector, Evolutionary mechanism, added to an energy factor. This model will be then implemented on Jetson TK1 board to verify its time response speed compared to a regular CPU. The experimentation was conducted, after checking multiple facial data bases, on AT&T one, regarding its accuracy and popularity across the international community. Compared to existing models, significant results are offered, reaching 97.5%, with real time system RTS tendencies.