An unobtrusive computerized assessment framework for unilateral peripheral facial paralysis

Abstract

Unilateral peripheral facial paralysis (UPFP) is a form of facial nerve paralysis and clinically classified according to conditions of facial symmetry. Prompt and precise assessment is crucial to neural rehabilitation of UPFP. The prevalent House-Brackmann (HB) grading system relies on subjective judgments with significant inter-observation variation. Therefore to explore an objective method for UPFP assessment, clinical image sequences are captured using a web camera setup while 5 healthy and 27 UPFP subjects performing a group of pre-defined actions, including keeping expressionless, raising brows, closing eyes, bulging cheek and showing teeth in turn. Firstly, facial region is decided using Haar cascade classifier, and then landmark points are acquired by supervised descent method (SDM). Secondly, these landmark points are used to generate a group of features reflecting the structural parameters of regions of eyebrows, eyes, nose and mouth respectively. Thirdly, correlation coefficients are computed between the raw features HB scores. To reduce feature dimensions, only those with correlation coefficients larger than an empirically selected value, 0.35, are input into support vector machine (SVM) to generate a classifier. With the classifier, exact match (discrepancy=0 between result from proposed method and HB scores) rate at 49.9%, and loosematch (discrepancy=1) rate at 87.97% are achieved on the experiment data. After sample augmentation, the final rate is increased to 90.01%, outperformed previous reports. In conclusion, it's demonstrated with an unobtrusive web camera setup, encouraging results have been generated with the proposed framework in this exploratory study.