Share

Neurotechnology Releases SentiMask 2.0 SDK for 3D Face Tracking, Masking and Animation Control

SentiMask 2.0 SDK can be used to emanate a accumulation of interactive and party applications, from mapping a textured facade or an charcterised avatar on a user’s face to determining a facial expressions of a 3D character.

Using Sentimask. Image credit: NeurotechnologyUsing Sentimask. Image credit: Neurotechnology

Using a SentiMask. Image credit: Neurotechnology

Neurotechnology, a provider of deep-learning-based solutions, robotics and high-precision biometric marker technologies, currently announced a recover of a second chronicle of a SentiMask Software Development Kit (SDK) for real-time face tracking and masking, 3D digital impression control and other applications. The SentiMask 2.0 algorithm can detect and lane a face in genuine time from a unchanging video stream, such as a webcam, or within a video file, and does not need abyss sensors or other special hardware.

SentiMask 2.0 SDK now includes 4 opposite 3D, morphable models of a tellurian face, one of that represents a whole conduct with a additional 3 face models varying between opposite forms of topologies and resolutions.

The SentiMask algorithm establishes a user-specific practical face representation, wise a models by showing and tracking of specific facial points (landmarks). The determined indication can be used as an charcterised avatar, with a 3D face filigree and user-provided textures that respond to, and pierce in unison with, a user’s facial expressions. Additionally, a indication can be simply protracted with 3D accessories (assets) such as glasses, hats, etc.

SentiMask 2.0 will also now detect and commend attributes such as a user’s gender or age and can settle either a chairman is wearing eyeglasses or a shawl or has a brave or a mustache. The rescued attributes can be used in a far-reaching operation of scenarios, from targeted promotion to statistical calculation.

“With a recover of SentiMask 2.0 we wanted to dilate a list of options developers have to select from,” pronounced Dr. Vilius Matiukas, SentiMask plan lead for Neurotechnology. “We combined several opposite 3D face models as good as additional charge detection. These new facilities will enhance a series of applications and uses to that SentiMask can contribute.”

In further to mapping textures onto a person’s face, SentiMask SDK allows users to control a digital characters’ facial expressions, mouth movements and conduct orientation.

The primary facilities of SentiMask 2.0 SDK include:

  • Real-time face showing and tracking
  • Attribute marker and detection:
    • Age detection
    • Gender detection
    • Glasses detection
    • Hat detection
    • Beard detection
    • Mustache detection
  • 3D facial poise detection
  • 2D facial landmark detection
  • 3D facial figure and countenance generation, formulating a user-specific representation
  • 3D facial filigree output
    • Four opposite models accessible in opposite resolutions and topologies, including a full conduct model
  • Facial countenance research (left/right eye closed, left/right eyebrow adult or down, jaw relocating left or right, etc.). A sum of twenty-three expressions can be identified.

SentiMask SDK can be used to emanate a accumulation of interactive and party scenarios, from augmented reality applications that map textured masks or charcterised avatars on a user’s face to controlling 3D character’s facial expressions, mouth movements and conduct orientation.

The new SentiMask 2.0 now also detects and recognizes attributes such as a user’s gender or age and can settle either a chairman is wearing glasses or a hat or has a beard or a mustache. Also a record can perform facial countenance analysis – 23 opposite expressions can be identified formed on open/closed eyes, eyebrows position, jaw transformation etc.

SentiMask 2.0 SDK supports C++ growth environments underneath Windows, Linux and Mac platforms as good as Android OS and iOS.

SentiMask 2.0 SDK and a whole line of Neurotechnology products for AI, robotics, intent approval and biometric marker are accessible by Neurotechnology or from distributors worldwide. For some-more information, go to: www.neurotechnology.com.

About Neurotechnology

Neurotechnology is a developer of high-precision algorithms and program formed on low neural networks and other AI-related technologies. The association was launched in 1990 in Vilnius, Lithuania, with a pivotal thought of regulating neural networks for several applications, such as biometric chairman identification, mechanism vision, robotics and synthetic intelligence. Since a initial recover of a fingerprint marker complement in 1991, a association has delivered some-more than 200 products and chronicle upgrades. More than 3,000 complement integrators, confidence companies and hardware providers in some-more than 140 countries confederate Neurotechnology’s algorithms into their products. The company’s algorithms have achieved tip formula in eccentric record evaluations, including NIST MINEX, PFT, FRVT, IREX and FVC-onGoing.


<!–

Comment this news or article

–>