A paper on arxiv called “Automated Inference on Criminality using Face images” by Xiaolin Wu and Xi Zhang, argues that: ” Via supervised machine learning, we build four classifiers (logistic regression, KNN, SVM, CNN) using facial images of 1856 real persons controlled for race, gender, age and facial expressions, nearly half of whom were convicted criminals, for discriminating between criminals and non-criminals. All four classifiers perform consistently well and produce evidence for the validity of automated face-induced inference on criminality, despite the historical controversy surrounding the topic. Also, we find some discriminating structural features for predicting criminality, such as lip curvature, eye inner corner distance, and the so-called nose-mouth angle. Above all, the most important discovery of this research is that criminal and non-criminal face images populate two quite distinctive manifolds. The variation among criminal faces is significantly greater than that of the non-criminal faces.”
Of the four classifiers, the CNN classifier performed the best, identifying the faces of criminals with 89% accuracy. The other three classifiers were “only few percentage points behind in the success rate of classification.” They used “ID photos of 730 criminals, of which 330 are published as wanted suspects by the ministry of public security of China and by the departments of public security for the provinces of Guangdong, Jiangsu, Liaoning, etc.; the others are provided by a city police department in China under a confidentiality agreement. We stress that the criminal face images … are normal ID photos not police mugshots”. Interestingly, the criminals involved had committed a range of crimes: “Out of the 730 criminals 235 committed violent crimes including murder, rape, assault, kidnap and robbery; the remaining 536 are convicted of non-violent crimes, such as theft, fraud, abuse of trust (corruption), forgery and racketeering. They were compared to “ID photos of 1126 non-criminals that are acquired from Internet using the web spider tool; they are from a wide gamut of professions and social status, including waiters, construction workers, taxi and truck drivers, real estate agents, doctors, lawyers and professors”. All were “male Chinese of young or middle age”, though it’s not clear how the authors knew that all of the 1126 were not criminals!
The facial features which give away the criminals are apparently “the curvature of upper lip … the distance between two eye inner corners… and the angle enclosed by rays from the nose tip to the two corners of the mouth.”
There are obvious issues with this, but it does suggest that maybe Lombroso was on to something. But if we must accept anthropological criminality or positivist criminology may hold some truth, a lot of cherished beliefs will have to be questioned.