This post is also available in: English
We show that faces contain much more information about sexual orientation than can be perceived and interpreted by the human brain. We used deep neural networks to extract features from 35,326 facial images. These features were entered into a logistic regression aimed at classifying sexual orientation. Given a single facial image, a classifier could correctly distinguish between gay and heterosexual men in 81% of cases, and in 74% of cases for women. Human judges achieved much lower accuracy: 61% for men and 54% for women. The accuracy of the algorithm increased to 91% and 83%, respectively, given five facial images per person. Facial features employed by the classifier included both fixed (e.g., nose shape) and transient facial features (e.g., grooming style). Consistent with the prenatal hormone theory of sexual orientation, gay men and women tended to have gender-atypical facial morphology, expression, and grooming styles. Prediction models aimed at gender alone allowed for detecting gay males with 57% accuracy and gay females with 58% accuracy. Those findings advance our understanding of the origins of sexual orientation and the limits of human perception. Additionally, given that companies and governments are increasingly using computer vision algorithms to detect people’s intimate traits, our findings expose a threat to the privacy and safety of gay men and women.
What about the privacy and safety of young boys and dudes who just want to be left in peace in the gym locker room?
YET AGAIN a scientific study has validated a Heartiste real world observation. Megapreen incoming! CH has been saying gayface is real since inception date 1488. From a May 15, 2008 Chateau post:
There is such a thing as a “gay face”. Hard to describe, but you know it when you see it. Think big bright feminine eyes, full lips, and an all-around glow.
The gayface composite photo that accompanied the above study:
Swishiognomy is real.
Would gaypedoface be redundant?
You can almost draw diagonal lines representing femininity and masculinity levels, connecting the gay male face with straight female face, and the straight male face with the lesbo female face.
There is (for lack of a better science-y description) a feminine glow and openness in the faces of the straight woman and the gay man composites. Oppositely, there’s a masculine hardness and compactness in the faces of the straight man and the lesbo woman composites. (And honestly that’s not even a very representative composite of most dykes I’ve seen….my composite lesbian face would be a lot fatter, uglier and mannish.)
Gabber @lglookingglass adds,
Gay Face is the hollowing out of the checkbone structure.
This approach applies to almost all chronic health conditions as well. If you want a really deep cut, realize that doctors do about 1/2 their diagnosis from seeing your face. It’s why they’ll catch rare things: they’ve seen it.
According to the study, the GayI was better than humans at accurately identifying by facial features alone the gays from among the straights. But I bet a person who was exceptionally observant and had spent time around many gays would have a more honed gaydar than the average human test subject, so I wonder if the GayI hit rate can’t be matched by, say, an urban SWPL with a social circle that included a lot of homos.
Or maybe the urban SWPL’s gaydar would be blunted due to inurement to constant exposure, familiarization, and normalization.
Fistiognomy is real.
I detect a pattern.