It’s all in the face
We recognize one another through our faces; face recognition would therefore seem to be the ‘most natural' of biometrics technologies. Facial recognition systems are automated systems with the ability to identify individuals by their facial characteristics, such as the distance between the eyes, nose, mouth and ears. These characteristics are analyzed and compared in order to identify or verify a person's identity.
Enhancements and improvements are regularly being introduced to this rapidly evolving technology. This includes, for instance, the development of 3D sensors, recognition of moving faces, processing of side views of faces and development of models to allow for ageing.
Enhancing biometric precision
The effectiveness of facial recognition technology depends on several key factors:
- Image quality: Is the system attempting to distinguish between cooperative or non-cooperative subjects? Cooperative subjects are those that have voluntarily allowed their facial image to be captured. Non-cooperative subjects are those typically captured via surveillance cameras or by a witness using their smartphone.
- Algorithms for identification: The second key performance factor is the power of the algorithms that are used to determine similarities between facial features. The algorithms analyze the relative position, size, and/or shape of the eyes, nose, cheekbones and jaw. These features are then used to search for other images with matching features.
- Reliable databases: Lastly, facial recognition accuracy depends on the size and quality of the databases used; to recognize a face, you have to be able to compare it to something! The challenge is to establish matching points between the new image and the source image, in other words, photos of known individuals. Therefore, the larger the database of targeted images, the more likely a match can be found.
Flexible and powerful
Face recognition technology has a very wide range of applications; for instance, using the built-in camera of a smartphone, tablet or computer, facial recognition software can replace passwords for device and user account access. In law enforcement, the technology can aid in the identification of suspects, whilst in border control deployments it can streamline security operations. Another popular application for facial recognition systems is access control at high-value sites. In the commercial sector, retailers and marketers are adopting the technology as a means to gather crucial demographic data.