Abstract: In the area of cartography and geographic information science, the center points of area features are related to many fields. The centroid is a conventional choice for center point of area feature. However, it is not suitable for features with a complex shape for the center point may be outside the area or not fit the visual center so well. We propose a novel method to calculate the center point of area feature based on triangulation skeleton graph. We define two kinds of centrality of vertices in skeleton graph according to the centrality theory in graph and network analysis. Through the measurement of vertices centrality, the center points of polygon area features are defined as the vertices with maximum centrality. The complexity and special cases are discussed. A cognitive experiment is designed to test the usability of our method based on 448 districts and cities area features. The experimental result shows that the method is more suitable for complex area features than conventional centroid.