NEC Corporation today announced the development of a “Person Re-identification Technology” that is capable of matching images of people whose figures are partially hidden from cameras, even if the image is taken from behind or from the side.
This technology analyzes the entire appearance of a person’s photo image, such as their clothes and body shape, to determine whether they match with other images of people. Using the image analysis and deep learning technologies that NEC has cultivated through Facial Recognition Technology and other technologies, NEC was able to establish this high-precision technology that does not rely solely on facial images.
In many cases, Facial Recognition Technology alone may not be enough to match a person whose face is partially concealed. Conventionally, once a person was matched using Facial Recognition Technology, the appearance of that person could then be collected from images taken by multiple cameras. However, when there were many people and objects in an area, such as chairs and counters, people appearing in images of those areas cannot be fully scene, making it difficult to match them.
This technology enables a wide range of people to be recognized, even in places where there are many people or visual obstructions that prevent a person’s face or body from being fully seen.
Potential applications for this technology include security support in large-scale facilities with many people or visually blocked areas, as well as assistance in the search for lost children.
“NEC has a large portfolio of world-class biometrics certification technologies that include facial and fingerprint recognition (*1),” said Masayuki Mizuno, general manager, Biometrics Research Laboratories, NEC Corporation. “We are now expanding this portfolio within our NEC Safer Cities (*2) solutions, our NeoFace facial recognition AI-engine that boasts the world’s No.1 (*3) accuracy, and NEC’s advanced video analyzer.”
Main features of this technology include the following:
- Even persons who are not fully visible to a camera can be matched
NEC’s unique ingenuity in deep learning technology is used to match a person’s image by automatically selecting other parts of thier image when there is overlap between multiple people, such as in crowded or shaded environments where a person’s full image cannot be viewed. The matching rate for a person is as high as 90% (*4).
- Matching is possible with images taken from behind or from the side
Effective use of deep learning techniques can match people from numerous angles, such as from behind or from the side, and shot with multiple cameras. As a result, this technology can effectively match people using camera images where the face is not visible.
Corporate press release
The Latest on: Person Re-identification Technology
via Google News
The Latest on: Person Re-identification Technology
- Cheers to Heightened Health (Privacy) in 2021on January 19, 2021 at 8:27 am
The proposed changes aim to strengthen patient access to their PHI by permitting individuals to inspect their PHI in-person ... due to it being capable of re-identification; and Inferences ...
- Optus warns not to punish whole economy for tech giant sins in Privacy Act changeson January 18, 2021 at 11:11 pm
"A person's detailed individual record cannot be adequately de-identified or anonymised, and should not be sold, shared, or published without the person's explicit, genuine, informed consent," she ...
- Personally Identifiable Information (PII)on January 6, 2021 at 4:01 pm
Advancing technology ... and re-identification techniques tend to be successful when multiple sets of quasi-identifiers are pieced together and can be used to distinguish one person from another.
- De-Anonymizationon December 26, 2020 at 4:00 pm
De-anonymization, also referred to as data re-identification, cross-references anonymized information with other available data in order to identify a person ... The technology-savvy era is ...
- Say Hello to Deep Vision’s Polymorphic Dataflow Architectureon December 24, 2020 at 6:04 am
One thing I like about the folks at Deep Vision is that they know where they are targeting their technology ... might wish to use are person identification, person tracking, pose estimation, product ...
- Person and Vehicle Re-identificationon December 14, 2020 at 6:32 pm
Person and vehicle identification and re-identification have recently become major topics ... University after I received the master degree in computer application and technology from the School of ...
- Adversarial Learning for Person Re-IDon December 11, 2020 at 12:30 pm
Person identification and re-identification (Re-ID) has recently become a major ... ID to classes of persons with soft biometric features rather than individuals. The technology may be applied to many ...
- ALERT Airport Re-Identification Dataseton August 17, 2020 at 11:09 am
As part of the ALERT video analytics effort, researchers at Northeastern University and Rensselaer Polytechnic Institute developed an annotated dataset that accurately reflects the real-world person ...
- Systematic Review of Privacy-Preserving Distributed Machine Learning From Federated Databases in Health Careon June 1, 2020 at 6:24 pm
or to maintain it against re-identification (through linking of datasets causing accidental or deliberate re-identification). The technology of big data and artificial intelligence, however, itself ...
- NEC partners with C-DAC to deploy automated fingerprint identification system for Kerala State Police in Indiaon June 18, 2019 at 4:01 am
NEC's AFIS boasts the world's no. 1 authentication accuracy and is a core technology of the company's portfolio of ... capture the position of the inner canthus (for example, when a person is walking, ...
via Bing News