Detection of Temporomandibular Disorder from Facial Pattern

The analysis of temporomandibular disorder (TMD) is a challenging problem. This paper describes a new approach for detecting TMD. A measure of nonlinear dynamics of the variations in the movement of colour markers positioned on the subjects' faces was obtained via estimating the maximum Lya- punov exponent. Static features such as the number of outliers and kurtosis have also been evaluated. Support vector machine (SVM) classifier was used to distinguish patients with TMD and healthy subjects on the basis of the values of the above features. Accuracy of 100% has been achieved on a limited data set.