Screenshots
Go to NVeiler Video Filter contents
Plug-in Features
-
Automatic face detection –
The plug-in's internal engine is able to detect faces in a frame.
All detected faces will be pixelated.
Users can configure face detection parameters or disable it.
-
Manual face selection –
Users can select faces by hand if the automatic face detection is disabled.
The selected faces will be hidden whereas non-selected faces will remain visible.
-
Face part or non-face objects hiding –
The plug-in allows to select and hide a part of a face by choosing a corresponding rectangular region in a frame.
Also this method allows to choose non-face objects to be hidden (i.e. car license plates, logos, etc.)
-
Automatic tracking –
Users do not have to deal with all selected frames as each detected face or selected object will be tracked and obscured in all subsequent frames automatically until it will disappear.
Go to NVeiler Video Filter contents
Technical details
-
Configurable automatic face detection –
Users can adjust three parameters to improve face detection quality: face confidence threshold, smallest distance between eyes and largest face roll angle.
See the plug-in's documentation for more information on these parameters and their values.
-
Supported video resolution –
There are no general limitations on video size or aspect ratio.
However we recommend to provide video files with at least 640 x 480 pixels (or at least 0.3 MegaPixels for other aspect ratios) resolution for confident face detection and subsequent tracking.
-
Frame processing performance –
An HD video (1280 x 720 pixels) file with several faces in a frame and 15 degrees face roll tolerance is processed at a speed of about 12 frames per second on a PC with Intel Core 2 processor running at 2.66 GHz.
The performance is mostly dependent on a frame size and the chosen face detection parameters.
The number of faces in a frame has no significant influence on the performance.
-
Technology background –
The plug-in is based on VeriLook biometric face recognition technology and SentiSight object recognition and tracking technology.
The VeriLook-based biometric products have more than a million deployments worldwide including access control, identity verification and other security-related applications.
The SentiSight is intended for computer vision applications that are able to find the required objects in videos or still images.
Go to NVeiler Video Filter contents
System Requirements
The following system requirements are provided for comfortable processing of video files with about 1280 x 720 pixels native resolution:
-
A 2.66 GHz x86 32- or 64-bit processor (or better) is recommended for comfortable HD video processing with multiple faces in a frame.
Less powerful processors will also do the job, but at the cost of time.
-
Microsoft Windows XP / Vista / 7.
-
VirtualDub 1.9.11 (stable), 32-bit (x86) version or newer stable version.
The newest version can be downloaded at virtualdub.sourceforge.net
Videos with bigger resolution or dozens of faces in a frame will be still successfuly processed on the same hardware, but will require more time.
Go to NVeiler Video Filter contents
|
