Robust Gap Removal from Binary Volumes

Abstract

We present a method for the robust detection and removal of cracks and holes from binary voxel shapes based on the shapes' surface and curve skeletons. For this, we first classify gaps or indentations in the input shape by their position with respect to the shape's curve skeleton, into details (which should be preserved) and defects (which should be removed). Next, we remove defects, and preserve details, by using a local reconstruction process that uses the shape's surface skeleton. We illustrate our method by comparing it against classical morphological solutions on a wide collection of real-world shapes.