Finnish researchers have found that a person's dancing style is nearly always the same regardless of music type.
Using machine learning and motion capture technologies, computers are now able to identify people based on their dancing styles, according to researchers at the Centre for Interdisciplinary Music Research at the University of Jyväskylä.
Motion capture technology - often used in movie special effects as well as many other applications - records the movement of objects or people with the use of a camera and computer.
In the research at Jyväskylä Univeristy, the movements of 73 people were captured and analysed as they danced to various musical styles including blues, country, EDM, jazz, metal, pop, reggae and hip hop, according to Pasi Saari, data analyst and co-author of the study.
Using machine learning, the researchers analysed the dancing movements of each participant. As they danced to each genre, the researchers were disappointed to find that the computer algorithm was only able to identify the correct music genre less than 30 percent of the time.
Dance like "fingerprints"
On the other hand, however, the algorithm correctly identified each of the 73 dancing participants 94 percent of the time.
"It seems as though a person’s dance movements are a kind of fingerprint. Each person has a unique movement signature that stays the same no matter what kind of music is playing," Saari explained.
Some musical styles were easier for the computer to identify than others. The technology appeared to have a difficult time knowing when people were dancing to metal music, according to researcher Emily Carlson.
"There is a strong cultural association between metal and certain types of movement, like headbanging. It's probable that metal caused more dancers to move in similar ways, making it harder to tell them apart," she said.
The intention of the research was not to see whether dance identification tech could be used in tandem with face recognition technology, however.
"We're less interested in applications like surveillance than in what these results tell us about human musicality," she explained.
"We have a lot of new questions to ask, like whether our movement signatures stay the same across our lifespan, whether we can detect differences between cultures based on these movement signatures, and how well humans are able to recognise individuals from their dance movements compared to computers. Most research raises more questions than answers, and this study is no exception."