Abstract | ||
---|---|---|
We present a qualitative study on the distinction of pecking styles in prehistoric rock art captured by high-resolution 3D scans. Different pecking styles result from different shapes, sizes, depths and spatial distributions of individual peck marks. Pecking style distinction enables inter alia automated detection of superimpositions. To our knowledge, this is the first attempt towards an automatic analysis and characterization of pecking styles in rock art. We model pecking style similarity by local descriptions of the surface joining full 3D and 2D (image-space) representations. Our results show that different pecking styles can be efficiently retrieved and distinguished by combined 3D/2D surface analysis. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/CBMI.2019.8877469 | 2019 International Conference on Content-Based Multimedia Indexing (CBMI) |
Keywords | Field | DocType |
Surface description,3D description,Surface texture,Petroglyphs,Clustering,Rock art superimpositions | Pattern recognition,Computer science,Feature extraction,Pecking order,Rock art,Natural language processing,Artificial intelligence,Peck (Imperial) | Conference |
ISSN | ISBN | Citations |
1949-3983 | 978-1-7281-4674-4 | 0 |
PageRank | References | Authors |
0.34 | 13 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Markus Seidl | 1 | 0 | 0.34 |
Matthias Zeppelzauer | 2 | 186 | 21.35 |