Documentation for Face Intellect 7.3. Documentation for other versions of Intellect is available too.
Previous page Next page
Use of high-resolution video surveillance cameras is recommended for correct performance of Face Intellect software package. Video surveillance cameras used with Face Intellect software package must support color video.
For proper face recognition using Face Intellect software package it’s necessary to install and configure video cameras in such a way that the following requirements will be fulfilled:
- Frame rate must not be less than 12fps and not less than 6 fps for face recognition at turnstiles.
- Maximum deviation of received face photos from the frontal angle is not to exceed +/-15°.
- Distance between pupils on the received photos of the captured face must correspond to the requirements of the used recognition module:
- Cognitec: not less than 96 pixels;
- Tevian: not less than 50 pixels;
- VisionLabs: not less than 50 pixels.
- Mutual occulting of the captured faces must be minimized.
- The captured faces are to be uniformly illuminated. Directional side illumination is not allowed.
- Photos of the captured faces received from video cameras are to be clear. Image blurring caused by motion is not allowed.
- Sharpness of the captured faces on the received photos must be over 64 grayscale. Deficient or exceeding illumination is not allowed.
Note
Distance from camera to the captured face is not restricted. The matter of distance selection is solved by choice the lens with required focal distance.
Note
For VisionLabs recognition module the size of the photo added to the database is configured in the CascadeDetector::SizeHint settings section of the config.xml file located in the <Intellect installation directory>\Modules\FaceRecognition\VisionLabs\data.