18a Plas St. Pol de Leon

Penarth Marina

Penarth

Cardiff, UK

CF64 1TR

Tel: 029 2071 2664

Biometric technologies have developed now to the level where reliable and affordable face recognition solutions are available to SME's as well as larger organisations.  A database software system developed by computerisation limited can now integrate Face Recognition. Using a low cost web cams and our software modules face recognition can be built into almost any business application.

When you think about it, face recognition is one of the most natural of human identification attributes. We all do it all the time. We give confidential information to people we trust, we know who they are because we recognise their face.

Well your computer systems can now do this for you. There are a wide variety of business applications where this can be deployed, for example:-

• Time & Attendance*
• Access Security
• Identifying Registered customers
• Confirming a persons Authority
• Registering a persons Arrival

Computerisation can provide bespoke solutions utilising the latest Face Recognition Technologies.

*Computerisation has an off the shelf package for Time and Attendance called ClockInOut. ClockInOut is a biometric system that uses both Finger Reading & Face Recognition technologies. For further information see http://www.clockinout.co.uk/ 

 Face Image Constraints

Face recognition accuracy heavily depends on face image quality. Especially, maximum care should be taken in acquiring good quality facial images in enrolment step. During enrollment one or more (if available) images are converted into facial features template which is saved into the database and can be further used to rapidly identify or verify the person.

The following basic recommendations and requirements should be taken under consideration:

Face pose and expressions

1. Use near-frontal face images for enrollment with a rotation deviation of up to 10 degrees in any direction (yaw, pitch, roll). Our applications supports roll angle deviation up to 180 degrees.
2. Use more than one image for enrollment to cover slightly different face views in yaw and pitch directions. In case of
3. successful coverage, faces up to 25 degrees deviation from frontal can be recognized.
4. Neutral face expression is preferred in the enrollment step. During identification slight changes in facial expression do not influence face recognition accuracy.
5. Persons wearing glasses should use several images - with and without glasses - for enrollment. Thus, during identification they will be recognized in both cases.
6. Glasses with heavy frames and sunglasses will decrease face recognition accuracy.
7. Changes in face appearance because of facial hair should be accommodated in the same manner as wearing of glasses.

1. Lighting should be equally distributed on each side of the face and from top to bottom with no significant shadows within the face region. This can be achieved by using direct frontal light or diffuse lighting.
2. Avoid sunlight or any other additional lighting.
3. Avoid lighting which can produce glares on glasses or even face skin.

1. Use cameras of similar quality for both enrollment and identification.
2. Some cameras can be configured to produce mirrored images, i.e. left eye of the persons face can become "right" eye in the face image. Make sure that face orientation is uniform across all the images used in face recognition because facial features template extracted from mirrored face images of the same person will not match with those extracted from not-mirrored ones.