Face recognition, the art of matching a given face to a database of faces, is a non-intrusive biometric method that dates back to the 1960s. Most face recognition algorithms fall into one of two main groups: feature-based and image-based algorithms. Feature-based methods explore a set of geometric features, such as the distance between the eyes or the size of the eyes, and use these measures to represent the given face. These features are computed using simple correlation filters with expected templates. These methods are somewhat invariant to changes in illumination and can partially compensate for changes in camera location. However, they are sensitive to aging and facial expressions.
Image-based systems, the other main approach to face recognition, are based on ideas like eigenfaces. After a large training set of images has been collected, principal component analysis is used to compute eigenfaces. Each new face is then characterized by its projection onto this space of principal eigenfaces. This approach is extremely sensitive to small variations, both external and internal, though it is still one of the most popular methods in industry. Three-dimensional systems are intrinsically position- and light-invariant, and when computed as described here, can also be invariant to some facial expressions. Three-dimensional systems can obtain results not possible with 2D systems, such as distinguishing between identical twins under various facial expressions. I-CUBE offers 3D, real time, multiple facial (up to 4 in the image) facial recognition systems.
Speed, accuracy and intelligence are among the key qualities that differentiate I-CUBE products from other biometric technologies.
● SPEED: Using a revolutionary core technology called HNet, I-CUBE Biometrics delivers cutting-edge security with basic hardware requirements and split-second processing times.
The CBSMS product line offers powerful identity and verification technology for enterprises of all sizes, for physical and logical access control, and for third-party development. CBSMS has enterprise-ready biometric solutions for diverse government agencies, as well as the financial services, hotel, airport, gaming, retail, manufacturing, e-commerce, security and health sectors. Applications are unlimited due to the ongoing customisation of the software to suit the specialised needs of individual clients.
APPLICATIONS AND SOLUTIONS:
We offer a wide range of Facial Recognition Solutions, designed for use within general surveillance and access control applications. This system is based upon a Client-Server architecture, whereby the Server application generates and stores all facial biometric templates that are subsequently distributed to one or more Discovery Client applications. Both the Discovery Client and Server applications perform facial tracking, enrollment, verification (one-to-one identification) and classification (one-to-many identification) operations. In addition, Discovery Client applications are fully functional when disconnected from the Server.
The Acsys Discovery application illustrates the functionality of Acsys facial recognition within technology in a variety of practical applications, these being:
1) Facial enrollment from either live video stream input (i.e. camera, VCR, broadcast, etc.) or from static images (i.e. JPEG files).
2) Facial recognition in classification mode (one-to-many identification).
3) Facial recognition in verification mode (one-to-one identification).
4) Facial verification integrated with a Wiegand based identification signal (i.e. proximity card, keypad, etc.).
5) Operation of R410/R810 relay controller following classification or verification operations (i.e. for opening door, controlling signs, etc.)
6) Interface for remote alarm on classify/verify operations (i.e. mobile wireless PDA, PECOS)
7) Speech synthesis on recognition (classification) of an individual.
Please contact CBSMS for a customised proposal, taking into consideration your requirements, existing solutions and possible revenue sources.