A contactless biometric can be the form of a passive (biometric device continuously monitors for the correct activation frequency) or active (user initiates activation) biometric. Authentication of the user biometric should take place only by his/her voluntarily agree to present the biometric for scanning. A contactless biometric is one that does not require undesirable contact in order to extract the required data sample of the biological characteristic and in that respect a contactless biometric is most adaptable to people of variable ability levels.
Facial Recognition
A face image can be made using a normal camera such as a ready-made desktop camera. It is the most natural biometric for identity authentication. Two main approaches are used to perform face recognition, a global approach and feature-based approach. Feature-based approach rely on the identification of certain fiducial points on the face, including the points at the eyes, the side of the nose and the mouth, the points surrounding one's cheekbones etc. The positions of these points are used to reckon the geometrical relationships between the points. The regions surrounding the points can be analyzed locally as well. Results from all the local processing at the fiducial points are then combined to obtain the overall face recognition. Since detection of feature points precedes the analysis, such a system is robust to position variations in the image. However, automatic detection of the fiducial points is not accurate and consistent enough to yield a high accuracy rate for the face recognition.
Global approach processes the entire face image simultaneously without attempting to localize the individual points. This approach has some variants in the type of technology used, such as statistical analysis, neural networks or transformations. The famous examples for statistical analysis are the eigenface technique and local feature analysis while for neural network is the elastic bunch graph matching technique. The advantage of holistic approach is that it utilizes the face as a whole and does not destroy any information by exclusively processing only certain fiducial points. This generally yields more accurate recognition results. However, such technique is sensitive to variations in position and scale, and thus requires large training data sets.
The disadvantage is that the accuracy of this method is only suitable for verification, but is still can’t be used for identification. The face recognition is generally accepted by employees, compact, easy to use, a covert process and the cost is rather low. The performance will also be affected by variation in face due to aging, make-up, hair-style, glasses, pose and lighting condition in addition to not being able to separate twins.
Facial recognition has been used in projects to identify card counters in casinos, shoplifters in stores, criminals in urban areas, and terrorists abroad. Facial recognition templates are typically 83 to 1,000 bytes.
| 
