This paper introduces a shape descriptor based on a com-bination of topological image analysis and texture information. Criticalpoints of a shape´s skeleton are determined first. The shape is describedaccording to persistence of the local topology at these critical points overa range of scales. The local topology over scale-space is derived using thelocal binary pattern texture operator with varying radii. To visualisethe descriptor, a new type of persistence graph is defined which cap-tures the evolution, respectively persistence, of the local topology. Thepresented shape descriptor may be used in shape classification or thegrouping of shapes into equivalence classes. Classification experimentswere conducted for a binary image dataset and the promising results arepresented. Because of the use of persistence, the influence of noise orirregular shape boundaries (e.g. due to segmentation artefacts) on theresult of such a classification or grouping is bounded.


Janusch, I., & Kropatsch, W. (2016). Shape Classification According to LBP Persistence of Critical Points. In N. Normand, J. Guédon, & F. Autrusseau (Eds.), Discrete Geometry for Computer Imagery (pp. 166–177). Lecture Notes in Computer Science - Springer, Berlin Heidelberg. https://doi.org/10.1007/978-3-319-32360-2_13