What a stupid article.Craniometry has been used to distinguish races going back hundreds of years. It was stigmatized along with IQ tests and catastrophism in the 1950's. There are still countless papers out there where researchers distinguish between races under different, unrelated pretexts, which is the only acceptable form of research. It would be stupid easy for AI to distinguish between races. Here's an example, published under the pretext of "understanding male osteoporosis": https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5004623/ >Black men had higher aBMD at the whole body, total hip and femoral neck compared to White and South Asian men independent of body size adjustments, with no differences between the latter two groups. White men had longer hip axis lengths than both Black and South Asian men. >At the tibia and radius diaphysis, Black men had larger bones with thicker cortices and greater bending strength than the other groups. >At the metaphysis, South Asian men had smaller bones (p = 0.02) and lower trabecular vBMD at the tibia (p = 0.003). Here's one focused on craniometry: https://www.jpsr.pharmainfo.in/Documents/Volumes/Vol6Issue11/jpsr06111407.pdf >Craniometry is the measurement of cranial features in order to classify people according to race, criminal temperament, intelligence, etc. Using the skull-based categorization, anthropologists identified three or four racial groups; • Caucasoid characterized by a tall dolichocephalic skull, receded zygomas, large brow ridge and projecting-narrow nasal apertures. • Negroid characterized by a short dolichocephalic skull, receded zygomas and wide nasal apertures. • Mongoloid characterized by a medium brachycephalic skull, projecting zygomas, small brow ridge and small nasal apertures.