Lip Contour Identification in Texture Data of 3D Face Mesh Sequences

Parkinson's disease (PD) is a degenerative neurological disease affecting motor, cognitive and autonomic function with symptoms including a resting tremor, rigidity and reduced overall movement. Sufferers often experience communication changes, such as reduced vocal loudness and imprecise articulation, as a result of motor speech disorder. The extent of motor speech disorder (dysarthria) and the efficacy of treatment is currently subjectively assessed by speech and language therapists using standardised tests such as the Frenchay Dysarthria Assessment which assesses speech characteristics and oro-motor control. The outcome of these subjective assessments can be adversely affected by external factors such as the experience of the therapist, therefore there is a recognised need for more objective assessment methods. 3D dynamic computer modelling can be used to capture the movements of the human face in real time to produce a sequence of 3D face meshes over time. This dynamic 3D modelling can be used to objectively assess the extent of facial mobility inParkinson's disease patients with dysarthria. An important step in measuring facial mobility from a sequence of 3D meshes is to identify, in each mesh of the sequence, the location of facial features such as the lip outline. We describe an approach for identifying the lip outline using the mesh data and texture data of a face mesh using integral projection models and an active contour model.