Automatic Facial Recognition System Assisted-facial Asymmetry Scale Using Facial Landmarks

Abstract

Objectives: This study aimed to demonstrate the application of our automated facial recognition system to measure facial nerve function and compare its effectiveness with other conventional systems and provide a preliminary evaluation of deep learning-facial grading systems. Study Design: Retrospective, observational. Setting: Tertiary referral center, hospital. Patients: Facial photos taken from 128 patients with facial paralysis and two persons with no history of facial palsy were analyzed. Intervention: Diagnostic. Main Outcome Measures: Correlation with Sunnybrook (SB) and House-Brackmann (HB) grading scales. Results: Our results had good reliability and correlation with other grading systems (r = 0.905 and 0.783 for Sunnybrook and HB grading scales, respectively), while being less time-consuming than Sunnybrook grading scale. Conclusions: Our objective method shows good correlation with both Sunnybrook and HB grading systems. Furthermore, this system could be developed into an application for use with a variety of electronic devices, including smartphones and tablets.