At Royal Access Control we have many years of experience when it comes to biometric systems. Having encounterd the many problems main line biometric time and attendance systems have, example, lenghty enrollment and difficult software usage that confuses operators (which in the end causes system failure), we have developed easy to use software packaged in seperate segments, to maximize flexibility.

 

 

At Royal Access Control, we strive to bring a complete time-and-attendance solution to companies which can be used with ease, peace of mind and as little hassle as possible.

One of our goals with this sytem is to make it as affordable as possible for the end-user, making it possible to easily maintain the system by using standard over the counter hardware, making it more cost effective.

 

 

Our approach was taken over years of trail and error.

We developed the system with this goal - The end-user has a wide variety of choices.

These choices will include everything from softare packages, required hardware and layout of system units on networks to standalone units. The end-user can even decide to install the system himself depending on the hardware option and their relevant knowledge.

 

 

This version of ClockMate™ works on a neuro facial recognition engine which is widely used and known for its reliability. This engine is capable of processing and identifying with a comparison speed of 100,000 faces per second.

This time-and-attendace system can also be used as access control. The software allows for a setup of 2 relays.

One relay will be switched on a successful identification while the 2nd one can be used to trigger scheduled alarms or any desired scheduled event on any other type of hardware (both these are optional).

The program can be set up to enforce auto log-outs for users that do not log out at the end of the day, the hour value can be set as required.

ClockMate with Facial Recognition also consists of an advertisement display when the system is not in use. The time delay before the software switch to the adverts can be set as required, also a display time for each ad can be set individually.

Personalized messages can be set for individuals that will be displayed to them when logging in. These messages can be set to display a number of times or only once. The operator can also deicde to disable the user from logging and only display the messaged to enforce instructions.

This version of ClockMate™ can run on a network or as a standalone sytem.

• Network Version

Multiple instances can be loaded onto the same network for both the verification and enrollment modules. Each verification unit is identified with a unique name. When enrolling an individual he/she can be assigned to stations as required, thus doubling the system to access control.

• Standalone Version

Multiple verification units can exist on one premise but have only one enrollment station. This will act as the master unit and the rest slave units. A memory stick can be used to transport records between the units. Each verification unit is identified with a unique name. When enrolling an individual he/she can be assigned to stations as required, thus doubling the system to access control.

• An advanced Data Filter (Time Manager) is also available for companies that requires an in depth reporting solution that calculates overtime, weekends, public holidays, rates etc and export this data to 30 of the leading payroll systems.

 

 

There are numerous benefits to this system.

ClockMate™ with Facial Recognition benefits :

• No membrane that can be damaged
• No thermal plate that needs replacement
• Faster verification time (identifying with a comparison speed of 100,000 faces per second)
• Faster enrollment time (under 2 seconds)
• Involves non-intrusive, contact-less process
• Completely hygienic
• More difficult to bypass (liveliness check)
• More user friendly
• System can work with good quality web cameras that makes it easier and much more cost effective to replace, if necessary, compared to a hand/palm or fingerprint scanner.
• System has no limitation compared to many hand/palm/fingerprint biometric systems which allows only a certain amount of templates.
• No need for record download on the network system, all records are available immediately.
• Standalone system can store millions of records.
• User has the option of purchasing only the software and use their own hardware if it meets the requirements.
• Software packages and hardware can be bought as needed to expand an existing system.
• ClockMate™ with Facial Recognition can double as an access control system.

 

 

Installation notes, CD's and training can be provided to users and distributors who feel comfortable installing the system themselves.

Alternatively arrangements can be made with Royal Access Control to install and maintain the system.

Online and telephone support will be available for all users and distributors.

 

 

The algorithm implements advanced face localization, enrollment and matching using robust digital image processing algorithms.

• Simultaneous multiple face processing. Performs fast and accurate detection of multiple face in live video streams and still images. All faces on the current frame are detected in 0.07 seconds and then each face is processed in 0.13 seconds.
• Live face detection. A conventional face identification system can easily be cheated by using a photo of another person. This engine is able to prevent this kind of security breach by determining whether a face in a video stream is a live face or a photo.
• Face image quality determination. A quality threshold can be used during face enrollment to ensure that only the best quality face template will be stored in the database.
• Tolerance to face posture. This engine has certain tolrance to posture that assures face enrollment convenience - rotation of a head can be up to 10° from frontal in each diretion (nodded up/down, rotated or tilted left/right).
• Multiple samples of the same face. Biometric template records can contain multiple face samples belonging to the same person. These samples can be enrolled with different face postures and expressions, from different sources and in different time thus allowing to improve matching quality. Ex. with or without eyeglasses, with or without facial hair, with different facial expressions.
• Identification capability. The engine's functions can be used in 1-to-1 matching (verification), as well as 1-to-many matching (identification).
• Fast face matching. The face template matching algorithm compares 100,000 faces per second.
• Compact face feature template. A face feature template occupies only 2.3 kilobytes, thus applications can handle large face databases.
• Features generalization mode. This mode generates the collection of the generalized face features from several image of the same subject. Then, each face image is processed, features are extracted, and the collection of features are analyzed and combined into a single generalized features collection, which is written to the database. This way, the enrolled feature template is more reliable and the face recognition quality increases considerably.

• All performance evaluations were performed using a PC with a 2.8GHz Intel Petium 4 CPU.

 

 

Matching threshold - the minimum similarty value that verification and identification functions accept for the same face. Matching threshold should be determined from the list (recommended).

FAR	SCORE
10 %	12
1 %	24
0.1 %	36
0.01 %	48
0.001 %	60
0.0001 %	72
0.00001 %	84
0.000001 %	96

• If FAR = 0.001 %, then the probability that a false acceptance situation will occur during 1 : N identification (where N = 10,000) is 1 - (1 - 0.00001) ^ 10,000 = 9.52 %
• If FAR = 0.0001 %, then the probability that a false acceptance situation will occur during 1 : N identification (where N = 10,000) is 1 - (1 - 0.000001) ^ 10,000 = 1.00 %

• Matching threshold/FAR should be selected according to the system's development requirements and taking the identification false acceptance accumulation into account.