VeriLook Embedded Algorithm Features and Capabilities

VeriLook Embedded face recognition algorithm is intended for embedded and mobile biometric system integrators. The VeriLook Embedded 1.1 technology is a port of VeriLook 5.2 technology for ARM-based processors.

VeriLook Embedded provides the same quality of PC-based facial recognition on embedded and mobile devices The technology implements advanced face localization, enrollment and matching using robust digital image processing algorithms:

• Simultaneous multiple face processing. VeriLook Embedded performs accurate detection of multiple faces in live video streams and still images.
• Live face detection. A conventional face identification system can be tricked by placing a photo in front of the camera. VeriLook Embedded is able to prevent this kind of security breach by determining whether a face in a video stream is "live" or a photograph.
• 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 into database.
• Tolerance to face position. VeriLook Embedded allows for 360 degrees of head roll. Head pitch can be up to 15 degrees in each direction from the frontal position. Head yaw can be up to 45 degrees in each direction from the frontal position. See technical specifications for more details.
• Multiple samples of the same face. Biometric template record can contain multiple face samples belonging to the same person. These samples can be enrolled from different sources and at different times, thus allowing improvement in matching quality. For example a person might be enrolled with eyeglasses and without, or with different types of eyeglasses; with and without beard or moustache, etc.
• Identification capability. VeriLook Embedded functions can be used in 1-to-1 matching (verification), as well as 1-to-many mode (identification).
• Small face features template. A face features template can be only 4 Kilobytes, thus VeriLook Embedded based applications can handle large face databases. Larger templates can be used to increase matching reliability. See technical specifications for more details.
• Features generalization mode. This 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.

Go to VeriLook Embedded contents

Technical Specifications

640 x 480 pixels is the recommended minimal image size for faces' detection. Face template extraction and matching is not dependent on the image size.

50 pixels is the minimal distance between eyes for a face on image or video stream to perform face template extraction. 75 pixels or more recommended for better template extraction results.

All face templates should be loaded into RAM before identification, thus the maximum face template database size is limited by the amount of available RAM.

VeriLook Embedded 1.1 has certain tolerance to face posture that assures face enrollment convenience:

• head roll (tilt) – ±180 degrees (configurable);
  ±15 degrees default value is the fastest setting which is usually sufficient for most near-frontal face images.
• head pitch (nod) – ±15 degrees from frontal position.
• head yaw (bobble) – ±45 degrees from frontal position (configurable).
  ±15 degrees default value is the fastest setting which is usually sufficient for most near-frontal face images.

See also the whole list of recommendations and constraints for facial recognition.

A Java application based on VeriLook Embedded 1.1 technology is able to process a face image in less than 1 second.

Facial record size in a template can be chosen from three values: 4 kilobytes, 20 kilobytes and 36 kilobytes. Several facial records can be stored in the template.

Go to VeriLook Embedded contents

Reliability Tests

We present the testing results to show practical VeriLook Embedded 1.1 algorithm reliability evaluations. Face images from FRGC database were used for testing, thus the testing results can be compared with testing results of other algorithms.

Experiment 1 and Experiment 2 were performed according to FRGC protocol:

• Experiment 1 measures performance on the recognition from frontal facial images taken under controlled illumination. The biometric samples in the target and query sets consist of a single controlled still image in high resolution.
• Experiment 2 is designed to examine the effect of multiple still images on performance. The biometric samples in the target and query sets are composed of the 4 controlled images of each person from a subject.

See Overview of the Face Recognition Grand Challenge (PDF) for more details on FRGC experiments protocol.

Each experiment was performed 2 times to test different scenarios:

• Test 1 maximized matching accuracy. VeriLook Embedded 1.1 algorithm reliability in this test is shown on the ROC charts as blue curves for Experiment 1 and cyan curves for Experiment 2.
• Test 2 minimized template size. VeriLook Embedded 1.1 algorithm reliability in this test is shown on the ROC charts as red curves for Experiment 1 and magenta curves for Experiment 2.

These sets of ROC curves were calculated using sertain subsets of FRGC database for each experiment and test according to FRGC protocol:

• ROC I – gallery and probe photos were taken within half of the year.
• ROC II – gallery and probe photos were taken within one year.
• ROC III – gallery and probe photos were taken with time lapse of at least half of the year but within 1.5 year.

Notes:

• VeriLook Embedded 1.1 face template matching engine is a port of VeriLook 5.2 PC-based engine for ARM-based processors, thus the reliability testing results and the ROC curves for both engines are the same.
• Part of images in the FRGC database is 1600 x 1200 pixels, and the other part is 2272 x 1704 pixels, as the images for this database were obtained with digital photo camera. The technical specifications above are given for 640 x 480 pixels images that are common for webcams.
• Head roll, pitch and yaw were set to ±15° during all experiments and tests.
• No score normalization techniques were applied while calculating these ROC curves, although FRGC protocol allowed to use score normalization.

ROC I Click to zoom

ROC II Click to zoom

ROC III Click to zoom

Go to VeriLook Embedded contents