Abstract
A new framework for the Recognition, Mining and Synthesis (RMS) system, has been proposed to make meaningful use of the enormous amount of information. Based on the same concept, we propose a face RMS system, which consists of face detection, facial expression recognition, and facial expression exaggeration components, for generating exaggerated views of different expressions for an input face video. In this paper, the parallel algorithms of the face RMS system were developed to reduce the execution time on a multi-core embedded system. The experimental results show the robustness and efficiency of face RMS system under complex environments. The quantitative comparisons indicate the proposed parallelized strategies has a significant increase in computational speedup compared to the single-processor implementation on a multi-core embedded platform. © 2011 IEEE.