NEC unveils AI face recognition
Thu 3 Nov 2016
NEC Corporation has launched a new software program that uses artificial intelligence (AI) in video footage search to quickly identify a person by facial recognition.
NeoFace Image Data Mining (Idm) is a new product offering from NEC that can use video footage, for example, data gathered by CCTV cameras, and scan it to accurately identify an individual whose image is captured on camera. It can also be used to search for people who appear at a certain time and place, or who appear with other specified individuals.
A complete search for a specific person among one million captured images can be concluded in under 10 seconds.
Idm combines existing facial recognition technology with profiling parameters – what NEC refers to as ‘Profiling Across Spatio-Temporal Data’ technology. By combining image identification with profiling, the software is able to create groups of similar subjects, and then conduct a high-speed search for more specific patterns.
Images are classified based on a ‘tree-shaped data management structure’, which groups images by similarity. Artificial intelligence will allow the system to continuously improve the way it identifies people and objects through machine learning, and improving itself through training.
Noritaka Taguma, General Manager for Infrastructure at NEC said, “In recent years, there is growing demand for advanced analysis of camera footage for utilization in security and marketing applications. NeoFace Idm meets this demand by providing high-speed, high-precision searches for persons who appear in specific patterns, which could not be achieved through manual searches or conventional technology.”
Some applications of the new technology identified by NEC include criminal investigations, searching for lost children or missing persons, and improved customer service. NeoFace Idm can also be used to identify suspicious activity, such as individuals who repeatedly show up near restricted areas.
A beta version of NeoFace technology has been tested by police forces in Northern Australia, who found it useful in identifying people engaged in criminal activities but also, in at least one case, in locating an unconscious victim of assault. After a successful trial, the police force has elected to broaden its use of NeoFace, noting that the system helps to reduce investigation times, and that it could also “assist police to identify missing persons and also those in the community who suffer from Alzheimer’s or other similar health issues to assist police in getting them the care they need.”