Visage SDK
| Visage SDK | |
|---|---|
.png?lang=en){kind=logo} | |
| Developer(s) | Visage Technologies AB |
| Stable release | 7.3.1860
/ 31 July 2015 |
| Platform | |
| Type | Software development kit |
| Website | www.visagetechnologies.com |
visage|SDK is a multiplatform software development kit (SDK) created by Visage Technologies AB. visage|SDK allows software programmers to build a wide variety of face and head tracking and eye tracking applications for various operating systems, mobile and tablet environments, and embedded systems, using computer vision and machine learning algorithms.
Technology
FaceTrack[1] reliably tracks 3D head pose, full facial features and eyes/gaze for multiple faces in video coming from a camera, video file or other sources. FaceTrack is a fully-configurable package that includes: face tracking, face and facial landmarks/features detection, head tracking, and eye tracking. FaceTrack Tracks multiple faces and facial features in input video, images or in real time. Returns 2D and 3D head pose, the coordinates of facial feature points (e.g. chin tip, nose tip, lip corners, mouth contour, chin pose, eyebrow contours), fitted 3D face model, and eye closure and eye rotation (gaze direction).
FaceAnalysis[2] includes cutting-edge machine learning algorithms to estimate gender, emotion detection and age detection. FaceAnalysis works with FaceTrack to find/track faces in images or video, and then uses state-of-the-art techniques to accurately provide the user with gender, emotions and age for the faces in roughly frontal position.
FaceRecognition[3] is used to identify or verify a person from a digital image or a video source using a stored face database. visage|SDK face recognition algorithm is capable of measuring similarity between people and recognizing a person’s identity from frontal facial image (yaw angle approximately from -20 to 20 degrees) by comparing it to faces previously stored in a gallery.
History
The development of Visage|SDK started in 2002 when Visage Technologies AB was founded in Linköping, Sweden. The founders were among the contributors to the MPEG-4 Face and Body Animation International Standard.[4][5]
Features
- For each processed video frame, returns detailed facial information,[6] such as:
- Fully automatic operation and instantaneous initialization
- Reinitialization if a new person appears in front of the camera
- Recovers from any losses due to occlusions, face turning away, tracked person coming and going etc.
- Tracks from webcam or AVI video files
- Raw image interface allows tracking from any video source
- Tracks in color or grayscale video (internal processing performed on grayscale), and in near-infrared video
- Minimal size of the face in the video image is approx. 80 pixels wide, minimum input video resolution is approximately 320×240, while higher resolutions (e.g. 640×480, 800×600) give better results
- Head rotation is tracked up to approximately 50 degrees.
See also
- Biometrics
- Computer vision
- Emotion recognition
- Eye tracking
- Face detection
- Facial recognition system
- Marketing research
- Three-dimensional face recognition
References
- ^ Visage Technologies: FaceTrack
- ^ Visage Technologies: FaceAnalysis
- ^ Visage Technologies: FaceRecognition
- ^ Pandžić, Igor and Robert Forchheimer (2002): "The origins of the MPEG-4 Facial Animation standard", in: MPEG-4 Facial Animation - The standard, implementations and applications (eds. Igor S. Pandžić and Robert Forchheimer). Chichester: John Wiley & Sons (ISBN 0-470-84465-5).
- ^ Pandžić, Igor and Robert Forchheimer (2002): "MPEG-4 Facial Animation Framework for the Web and Mobile Platforms", in: MPEG-4 Facial Animation - The standard, implementations and applications (eds. Igor S. Pandžić and Robert Forchheimer). Chichester: John Wiley & Sons (ISBN 0-470-84465-5)
- ^ Visage Technologies: Products and main features