Segmenting surfaces into meaningful parts is useful in 3D object recognition, mesh simplification, etc. Many previous works have been done in range image segmentation. However, there are few existing techniques for segmenting arbitrary surfaces represented by triangle mesh.

The goal is to develop a new algorithm that robustly and efficiently segment a dense triangle mesh.

We propose a robust edge detection algorithm for triangle meshes and its application to surface segmentation. The proposed edge detection technique is based on eigen analysis of the surface normal vector field in a geodesic window. To compute the edge strength of a certain vertex, the neighboring vertices in a specified geodesic distance are involved. Edge information are used to further segment the surfaces with the watershed algorithm. The proposed algorithm is novel in robustly detecting edges on triangle meshes against noise. The 3D watershed algorithm is an extension from previous works of Mangan and Whitaker.

• Y. Sun, D. L. Page, J. K. Paik, A. Koschan, and M. A. Abidi, "Triangle meshes-based edge detection and its application to surface segmentation and adaptive surface smoothing," Accepted by IEEE Int'l Conf. on Image Processing, 2002.