Visual Lip Segmentation in Patients with Cleft Lip and/or Cleft Palate

Lip segmentation in patients with cleft lip and/or cleft palate is a process that can be carried out by using the skin and lip colors as a base. This study proposes an algorithm capable of detecting the external lip edge. The algorithm detects the face region by identifying color and then the lips are segmented by using snake and fuzzy c-means. The segmentation was tested on 91 face images achieving a sensitivity of 0.98 and a specificity of 0.90. The specific contribution of this paper focuses on performing the segmentation of the lips without relying on geometric features of the face, location of the eyes or of the typical artifacts of clinical instrumentation in patients with CLP.