CONTENT PREVIEW
Security

AI intersects with biometrics for smarter processing

01 April 2019
Work in progress: a construction worker walks past facial recognition screens at the entrance to Beijing Daxing International Airport. Passenger biometrics could revolutionise airport processes, especially when combined with artificial intelligence. Source: Getty Images

The combination of artificial intelligence and biometric identity management brings up abundant opportunities – but challenges must also be addressed

Biometrics are advancing in everyday use, including as an identity token in the air transport industry. More of the electronic devices that we rely on for productivity and entertainment use biometric scans to authorise access, and the ‘selfie’ culture encourages people to share images on social media, which can be converted to biometric tokens.

Google has been investing heavily in artificial intelligence (AI) for various applications. It is the top acquirer of AI start-ups ahead of Apple and Facebook, with 14 companies bought by the end of 2018. Although AI can be used to solve any number of complex problems using an unlimited range of data, advances in computer vision and image search have the greatest implications for the future of biometric identity. The acquisition in 2013 of deep learning and neural network start-up DNNresearch from the computer science department at the University of Toronto and the acquisition of two Oxford University spin-offs in 2014, helped Google to advance its computer vision, image recognition, and image search capabilities.

Google is not the only company working in this field: other notable computer vision programmes under way include Yandex (Russia) and Baidu (China). Anthony Chapman, senior director of product management and strategy at Collins Aerospace, believes that Google might have an edge.

“Technology providers who do facial matching are doing it against Facebook and all of those pictures that are on record, but Google are getting more into data integration,” he said.

Integrating data would allow Google to identify important contexts sooner. Potential applications include flagging online activity that may be relevant to travel clearance, predicting passenger behaviour, or identifying problematic associations.

Want to read more? For analysis on this article and access to all our insight content, please enquire about our subscription options at ihs.com/contact



(314 of 1633 words)
ADVERTISEMENT
ADVERTISEMENT
ADVERTISEMENT
ADVERTISEMENT
ADVERTISEMENT
ADVERTISEMENT
ADVERTISEMENT
ADVERTISEMENT