Compute aided diagnosis of facial paralysis based on pface

In this paper, a compute aided diagnosis approach is proposed to physicians in the diagnosis of single-sided facial paralysis. This approach is different from the existing nine subjective and hand-performed international scales such as House-Brackman. For voluntary expressions of a patient, this approach used Pface, which stems from Dface, to measure the asymmetry between two sides of the face. The experiments on test subjects revealed that Pface could differentiate the paralysis stats and normal stats and has the ability of automatic grading facial paralysis. Moreover, Pface of specific face areas can be used in supervision of the rehabilitation process.