Biometric Mirror uses an open dataset of thousands of facial images and crowd-sourced evaluations. Source: Sarah Fisher, University of MelbourneResearchers from the University of Melbourne have developed an artificial intelligence (AI) system capable of detecting and displaying a person’s physical attractiveness and personality traits, both of which are determined by simply assessing the photograph of a person’s face.

Called Biometric Mirror, the system analyzes a person’s grasp of AI, as well as their reaction to the data concerning their unique features.

Standing in front of the Biometric Mirror, a person’s range of facial characteristics are first detected and then compared to those of thousands of other facial images that have already been appraised for their psychometrics by crowd-sourced responders.

Characteristics — 14 in total — such as gender, age, ethnicity, attractiveness, emotional stability and weirdness are all displayed by the Biometric Mirror. Every moment the person stands in front of the mirror gives the system more time to personalize the characteristics.

Led by Dr. Niels Wouters from the Centre for Social Natural User Interfaces (SocialNUI) and Science Gallery Melbourne, the primary goal of the research was to explore how such technology might increase concerns about data storage, consent and algorithmic bias.

“With the rise of AI and big data, government and businesses will increasingly use CCTV cameras and interactive advertising to detect emotions, age, gender and demographics of people passing by," Dr. Wouters said. "Our study aims to provoke challenging questions about the boundaries of AI. It shows users how easy it is to implement AI that discriminates in unethical or problematic ways which could have societal consequences. By encouraging debate on privacy and mass-surveillance, we hope to contribute to a better understanding of the ethics behind AI."

As such, the Biometric Mirror was designed to highlight the possible consequences of algorithmic bias and assumptions.

"While collecting personal information about your shopping preferences to tailor an individual service may seem harmless, capturing this information without consent makes it impossible to know if a prediction is based on correct data," said Dr. Wouters. "The use of AI is a slippery slope that extends beyond the realm of shopping and advertising. Imagine having no control over an algorithm that wrongfully considers you unfit for management positions, ineligible for university degrees, or shares your photo publicly without your consent."

"One of your traits is chosen — say, your level of responsibility — and Biometric Mirror asks you to imagine this information is now being shared with your insurer or future employer," Dr. Wouters added. "This project is a transparent demonstration of the potential consequences for individuals."

Yet, Dr. Wouters cautioned that the system is not meant to be used as a tool for psychological analysis.

"Biometric Mirror only calculates the estimated public perception towards facial appearance. It is limited by its inaccuracy, because only a relatively small and crowd-sourced dataset informed its design. It is inappropriate to draw meaningful conclusions about psychological states from Biometric Mirror," said Dr. Wouters.