Palate Shape and Depth: A Shape‐Matching and Machine Learning Method for Estimating Ancestry from Human Skeletal Remains |
| |
| Authors: | Christopher A. Maier M.A. Kang Zhang B.S. Mary H. Manhein M.A. Xin Li Ph.D. |
| |
| Affiliation: | 1. Department of Anthropology, University of Nevada Reno, Reno, NV;2. Department of Electrical and Computer Engineering, Louisiana State University, Baton Rouge, LA;3. Department of Geography and Anthropology, Louisiana State University, Baton Rouge, LA |
| |
| Abstract: | In the past, assessing ancestry relied on the naked eye and observer experience; however, replicability has become an important aspect of such analysis through the application of metric techniques. This study examines palate shape and assesses ancestry quantitatively using a 3D digitizer and shape‐matching and machine learning methods. Palate curves and depths were recorded, processed, and tested for 376 individuals. Palate shape was an accurate indicator of ancestry in 58% of cases. Cluster analysis revealed that the parabolic, hyperbolic, and elliptical shapes are discrete from one another. Preliminary results indicate that palate depth in Hispanic individuals is greatest. Palate shape appears to be a useful indicator of ancestry, particularly when assessed by a computer. However, these data suggest that palate shape is not useful for assessing ancestry in Hispanic individuals. Although ancestry may be determined from palate shape, the use of multiple features is recommended and more reliable. |
| |
| Keywords: | forensic science forensic anthropology palate shape ancestry estimation palate depth 3D digitizer shape‐matching machine learning |
|
|
