Straight skeletons for binary shapes

This paper reviews the concept of straight skeletons, which is well known in computational geometry, and applies it to binary shapes that are used in vision-based shape and object recognition. We devise a novel algorithm for computing discrete straight skeletons from binary input images, which is based on a polygonal approximation of the input shape and a hybrid method that combines continuous and discrete geometry. In our experiments, we analyze the potential of straight skeletons in shape recognition, by comparing their performance with medial-axis based shock graphs on the Kimia shape databases. Our discrete straight skeleton algorithm is not only outperforming typical skeleton algorithms in terms of computational complexity, it also delivers surprisingly good results in its straightforward application to shape recognition.