The core technology for Facial Recognition in a Crowded Scene is internationally patented. Further it is surrounded and supported by other innovative technologies which are unique to iOmniscient. It is recognized as the first (and at this stage the only) effective "many to many" Face Recognition system available.

We offer three types of products. We have Detection products, Identification products and IQ Hawk which provides a convergence of these products and enables them to work together. The Detection Products consist of the IQ Series which are rated based on their level of intelligence. IQ-Infinity provides the capability to run all the products from IQ-100 to IQ-140 at the same time on the same camera.

There are two categories of Identification products – for Face Recognition and for License Plate Recognition. IQ Hawk is available for those customers who want to perform Detection and Identification on the same camera.

Finally, there are a range of Industry Specific Application Products such as Vehicle Speed Detection and Queue Management which are available separately.

IQ-180 is a super-sensitive version of IQ-140. So sensitive in-fact we keep it reserved for very special projects where the customer needs to detect very tiny objects in very low contrast areas. We find that IQ-140 is sufficient for 99.9% of our customers.

Technically, IQ-180 can detect objects that are 4x4 pixels in size and it is capable of detecting objects that may be invisible to the human eye. An example would be a black bag on a black floor, hidden by a shadow. Even if the naked eye can not see the object due to the low contrast, the IQ-180 may still be able to detect it.

Other systems require the subject to be in a controlled environment with steady lighting. Further they require 300 pixels between the eyes and sometimes require more than one camera view. This makes them computing heavy and unusable in practical environments where the technology is required to be used with standard security cameras.

These variables would be dependent on the camera used in the application. IQ-FACE requires a picture with a clear resolution with at least 22 pixels between the eyes for effective identification of faces. Therefore, camera features such as shutter speed and mega-pixel capabilities would be important to enable clearer pictures to be captured allowing for higher velocity facial detection and recognition.

No, the system is not limited by these characteristics.

The system requires 22 pixels between the eyes for accurate facial detection and recognition. Images of up to 8 pixels can be processed; however accuracy of facial identification would be affected.

The system will work as long as both eyes can be seen. In most situations this means that the face can be tilted in any direction for up to 30 degrees and the detection would still be reasonably accurate.

Or does it include other algorithms?The system understands many different characteristics of the face such as the bone structure, the position of the eyes and others.

iOmniscient's system is designed for many to many facial detection and matching to a images in database for eventual recognition and/or identification. It is able to provide 80% accuracy which is significantly higher than what any human can achieve in a similar environment and much more than any comparable system in the market.

This would depend on the size of the database. With a database of over a few thousand faces the system would perform facial recognition in less than one second.

Theoretically there is no limit.

iQ-Face can be implemented in various security, marketing and customer service applications. For example IQ-Face can be implemented to recognize known shoplifters as they enter the store or VIP clients of a hotel even before they reach the reception desk. It can also be used to find matches from a pre-existing database for images of faces recorded at a terrorist incident.

Yes. The IQ series system has a universal interface and hence it will work with all MJPEG systems and with all other systems that use the industry standard RTSP. Customized interfaces can be built using the IQ API for systems that do not use the above industry standard protocols.

Yes. On detection of an event our system will send alarm information to the PTZ controller via XML, enabling the camera to zoom in on the event and track the perpetrator if necessary. Detection can also be performed on a PTZ when it is stationary or on a guard tour. However when the PTZ camera is moved it can longer see certain parts of the image and smart criminals can easily defeat a PTZ based detection system. For this reason we have developed the patented IQ-Hawk ststem that performs both detection and identification at the same time.

Yes. Our software can operate just as effectively with Thermal and Infrared cameras.

All our software requires is a digital image from the camera. An analog feed can easily be converted to a digital feed using a Video Capture Card or encoder.We can recommend a few that work effectively with our system.

Certainly. We have a universal interface with nearly all IP cameras available.

All systems are totally scalable. The customer can decide to have a single camera system and he can grow this to have thousands of cameras. The minimum system requirement is dependent on the application that needs to be run and the number of cameras.

Note that all IQ algorithms are incredibly computing light. Detection algorithms can require 4 times less computing power than for competitive products. With IQ Hawk the storage and networking bandwidth requirements can be up to 200 times lower than for standard mega-pixel based systems.

Detailed hardware specifications are available from your account manager.

Yes. All IQ products can operate across a wireless network which enables you to have a completely mobile surveillance system. This also enables the systems to be installed and uninstalled at any site at short notice. iOmniscient software can also be monitored and managed on a Wireless PDA which allows the Security Personnel to receive, review, clear and archive alarms whilst in the field in real-time.

Note that a wireless network must be well designed to operate effectively. A poorly designed network can result in lost information and alarms not being received in a timely manner.

Yes. The architecture is completely flexible. A user can monitor and manage any camera from any location as long as he is authorized to do so.

Yes. We have a remote client capability that enables users to login to any of their server from any computer. Similarly, if there are 2 server PC's in separate locations then both can be viewed simultaneously. Access to particular cameras can be restricted by the authority level of the viewer

Hypothetical example: In every building in an airport there is a Security Station responsible for the security of their building. Each Security Guard is able to monitor the cameras within their building using the IQ Products, but they are not authorised to view cameras in other buildings. The Head of Security wants to view events on every camera in every building on his screen, whilst the Security Guards are monitoring them. This is a standard feature of all of our products. All cameras are analysed and viewed in real-time and can be monitored from multiple workstations.

Certainly. From within a single client screen the user is able to access an infinite number of cameras, located anywhere in the World. If an alarm were to occur on a server he is logged in on, an alarm tag would pop up on the client screen specifying that an event is occurring on the respective camera. The operator can then access that camera and review the alarm, before deciding whether to archive or ignore the alarm. All cameras are viewed in real-time.

All systems are totally scalable. The customer can decide to have a single camera system and he can grow this to have thousands of cameras.

The number of cameras that can be operated on standard PC servers is dependent on the particular applications and on the type of server hardware. One can run up to 45 cameras of the IQ series software and over 100 cameras for VMS on a typical large server. Detailed hardware specifications are available on request.