VeriLook Back to Homepage
Back to Products
Currently there are many methods of biometric identification: fingerprint, eye iris, retina, voice, face etc. Each of these methods has certain advantages and disadvantages which must be considered in developing biometrical systems, such as: system reliability, price, flexibility, necessity of physical contact with the scanning device and many others. Selecting a certain biometrical identification method or using a multi-biometrical system can help to support these often discrepant requirements.

Face recognition can be an important alternative for selecting and developing an optimal biometrical system. Its advantage is that it does not require physical contact with an image capture device (camera). A face identification system does not require any advanced hardware, as it can be used with existing image capture devices (webcams, security cameras etc.).

A face does not have as many uniquely measurable features as fingerprints and eye irises, so facial recognition reliability is slightly lower than these other biometrical recognition methods. However, it is still suitable for many applications, especially when taking into account its convenience for user. Facial recognition can also be used together with fingerprint recognition or another biometrical method for developing more security-critical applications.

The multi-biometrical approach is especially important for identification (1:N) systems. In general, identification systems are very convenient to use because they do not require any additional security information (smart cards, passwords etc.). However, using 1:N-matching routines with only one biometrical method, can result in a higher false acceptance probability, which may become unacceptable for applications with large databases. Using face identification as an additional biometric method can dramatically decrease this effect. This multi-biometrical approach also helps in situations where a certain biometric feature is not optimal for certain groups of users. For example, people who do heavy labor with their hands may have rough fingerprints, which can increase the false rejection rate if fingerprint identification was used alone.

Thus, facial recognition should be considered as a serious alternative in the development of biometrical or multi-biometrical systems.

Why VeriLook?

Neurotechnologija has developed a PC-based face recognition algorithm VeriLook 3.0 designed for biometrical system integrators. VeriLook 3.0 offers capabilities of the most advanced and convenient facial identification systems at a reasonable cost:

  • Reliability. The VeriLook 3.0 algorithm has been tested with standard face databases (FERET, XM2VTSDB and others). The results are one of the best among existing face identification systems on the market.
  • Speed. VeriLook 3.0 face enrollment time is less than 0.3 sec. and matching speed is 100,000 faces per second in 1:N identification mode.
  • Multiple faces' processing. VeriLook 3.0 detects all faces in the current frame and can process all of them simultaneously.
  • VeriLook doesn't require any specific hardware. Face image can be obtained from low cost camera or web cam. Image processing and recognition are performed on standard PC.
  • Both face and fingerprint recognition techniques from the same vendor. Compatible product interfaces and customer support from the same source allow simple multi-biometric system integration and helps to achieve high system recognition quality. VeriLook algorithm can be used alone or together with other Neurotechnologija biometrical algorithms.
  • VeriLook is designed not only for verification, but also for identification (1:N matching).
Algorithm

The VeriLook 3.0 face recognition algorithm implements advanced face localization, enrollment and matching using robust digital image processing algorithms:

  • Fast and accurate face localization for reliable detection of multiple faces in still images as well as in live video streams.
  • Simultaneous multiple face processing and identification in single frame. All faces on the current frame are detected in less than 0.07 sec and then each face is processed in less than 0.13 sec.
  • VeriLook 2.0 face template matching algorithm compares up to 100,000 faces per second;
  • Applications implemented using VeriLook SDK can handle large face databases, as one face features template is only 2.3 KBytes;
  • Applications implemented using VeriLook SDK can handle large face databases, as one face features template is only 2.3 Kbytes.
  • Features' generalization mode generates the collection of the generalized face features from several images of the same subject. Then, each face image is processed, features are extracted, and the collections 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.

Note: All performance evaluations were performed using a PC with 2.8 GHz Intel Pentium4 CPU

Reliability Tests


Click to enlarge

VeriLook 3.0 was tested with face images from many cameras. The most interesting testing results are those obtained with standard databases, because in this case they can be compared with testing results of other algorithms. Usually the algorithm recognition quality is expressed by receiver operating curves (ROC), which show the dependence of false rejection rate on the false acceptance rate. The presented ROC shows the results of testing VeriLook 3.0 with face images from XM2VTSDB database. The red curve shows the performance results of VeriLook 3.0 without generalization, and the green one shows the results of VeriLook 3.0 with generalization.

VeriLook 3.0 algorithm technical specifications
Recommended minimal image size: 640 x 480 pixels
Multiple faces detection time: (using 640 x 480 image) 0.07 sec.
Single face processing time: (after detecting all faces) 0.13 sec.
Matching speed: 100,000 faces/sec.
Size of one record in the database: 2.3 Kbytes
Maximum database size: unlimited
System Requirements
PC with 1GHz processor;
128 Mb of RAM;
Algorithm's Demo


Click to Enlarge

The VeriLook demo application for Microsoft Windows 2000/XP/2003 can be downloaded for evaluation of the VeriLook face recognition algorithm. The application enrolls and identifies faces from almost any camera or webcam, and image files. Internet connection is not required to run the application.

Related products:
These products are based on VeriLook 2.0 algorithm:

VeriLook 3.0 Standard SDK is based on VeriLook 3.0 technology.

Download our VeriLook brochure
(All documents are in PDF format - click on a link to view a document in the browser, or if you would rather download the document, ‘right click and choose save target as.’)
Any queries, please email us on: :   info@fingerprint-it.com
Back to Homepage Back to top