SentiMask 2.0 SDK can be used to create a variety of interactive and entertainment applications, from mapping a textured mask or an animated avatar upon a user’s face to controlling the facial expressions of a 3D character.
Neurotechnology, a provider of deep-learning-based solutions, robotics and high-precision biometric identification technologies, today announced the release of the second version of its SentiMask Software Development Kit (SDK) for real-time face tracking and masking, 3D digital character control and other applications. The SentiMask 2.0 algorithm can detect and track a face in real time from a regular video stream, such as a webcam, or within a video file, and does not require depth sensors or other special hardware.
SentiMask 2.0 SDK now includes four different 3D, morphable models of a human face, one of which represents the entire head with the additional three face models varying between different types of topologies and resolutions.
The SentiMask algorithm establishes a user-specific virtual face representation, fitting the models through detection and tracking of specific facial points (landmarks). The established model can be used as an animated avatar, with a 3D face mesh and user-provided textures that respond to, and move in concert with, the user’s facial expressions. Additionally, the model can be easily augmented with 3D accessories (assets) such as glasses, hats, etc.
SentiMask 2.0 will also now detect and recognize attributes such as a user’s gender or age and can establish whether a person is wearing glasses or a hat or has a beard or a mustache. The detected attributes can be used in a wide range of scenarios, from targeted advertising to statistical calculation.
“With the release of SentiMask 2.0 we wanted to widen the list of options developers have to choose from,” said Dr. Vilius Matiukas, SentiMask project lead for Neurotechnology. “We added several different 3D face models as well as additional attribute detection. These new features will expand the number of applications and uses to which SentiMask can contribute.”
In addition to mapping textures onto a person’s face, SentiMask SDK allows users to control the digital characters’ facial expressions, lip movements and head orientation.
The primary features of SentiMask 2.0 SDK include:
- Real-time face detection and tracking
- Attribute identification and detection:
- Age detection
- Gender detection
- Glasses detection
- Hat detection
- Beard detection
- Mustache detection
- 3D facial pose detection
- 2D facial landmark detection
- 3D facial shape and expression generation, creating a user-specific representation
- 3D facial mesh output
- Four different models available in different resolutions and topologies, including a full head model
- Facial expression analysis (left/right eye closed, left/right eyebrow up or down, jaw moving left or right, etc.). A total of twenty-three expressions can be identified.
SentiMask SDK can be used to create a variety of interactive and entertainment scenarios, from augmented reality applications which map textured masks or animated avatars upon a user’s face to controlling 3D character’s facial expressions, lip movements and head orientation.
The new SentiMask 2.0 now also detects and recognizes attributes such as a user’s gender or age and can establish whether a person is wearing glasses or a hat or has a beard or a mustache. Also the technology can perform facial expression analysis – 23 different expressions can be identified based on open/closed eyes, eyebrows position, jaw movement etc.
SentiMask 2.0 SDK supports C++ development environments under Windows, Linux and Mac platforms as well as Android OS and iOS.
SentiMask 2.0 SDK and the entire line of Neurotechnology products for AI, robotics, object recognition and biometric identification are available through Neurotechnology or from distributors worldwide. For more information, go to: www.neurotechnology.com.
Neurotechnology is a developer of high-precision algorithms and software based on deep neural networks and other AI-related technologies. The company was launched in 1990 in Vilnius, Lithuania, with the key idea of using neural networks for various applications, such as biometric person identification, computer vision, robotics and artificial intelligence. Since the first release of its fingerprint identification system in 1991, the company has delivered more than 200 products and version upgrades. More than 3,000 system integrators, security companies and hardware providers in more than 140 countries integrate Neurotechnology’s algorithms into their products. The company’s algorithms have achieved top results in independent technology evaluations, including NIST MINEX, PFT, FRVT, IREX and FVC-onGoing.