Three-dimensional data generated from range scanners is usually composed of a huge amount of information. Simplification and compression techniques must be adopted in order to reduce transmission or processing time and to allow real-time visualization. In this paper we propose an approach to semantic simplification of triangular meshes representing faces. The algorithm is aimed to preserve facial features and can be used especially for face recognition systems purposes. In a first phase we detect salient regions using a 3D face detector based on curvature analysis and holistic classification. In a second phase, vertex decimation is applied to the mesh with different decimation parameters for salient and non salient-regions. We have tested our algorithm on a set of 150 acquisitions obtaining good visual quality meshes with approximately 90% or more of decimated vertexes.