Neurotechnology Introduces SentiMask SDK for 3D Face Tracking, Masking and Animation Control
SentiMask SDK can be used to create a variety of interactive and entertainment applications, such as mapping an animated avatar on a user's face or controlling the facial expressions of 3D digital characters.
Vilnius, Lithuania – December 4, 2017 – Neurotechnology, a provider of high-precision biometric, robotics, AI and computer vision technologies, today introduced the SentiMask Software Development Kit (SDK) for real-time face tracking and masking, 3D digital character control and other applications. The SentiMask algorithm can detect and track the user's face, in real time from a regular video stream, such as a webcam, or in a video file, and it does not require depth sensors or any other special hardware.
The output from SentiMask is in the form of 2D and 3D coordinates that represent certain facial feature points, also known as landmarks. These landmarks can be used to construct a face mesh and various textures can be applied onto that mesh. When used as an animated avatar or mask, for example, the mesh and textures respond to – and move in concert with – the user's facial expressions.
"For many years Neurotechnology has been known as one of the top companies in the person identification market for its high quality, precision biometric algorithms," said Dr. Vilius Matiukas, SentiMask project lead for Neurotechnology. "Our decades of experience in biometric facial recognition has enabled us to create our new SentiMask SDK product, which uses our latest facial image processing technologies in a non-biometric way. With SentiMask, our customers can easily incorporate face detection and tracking capabilities into their own solutions, such as entertainment or interactive marketing applications," Dr. Matiukas added.
With SentiMask SDK, users can not only map textures onto a person's face but also control digital characters' facial expressions. Using 3D facial landmark estimates, the SentiMask SDK can be used to control facial bones in 3D modeling applications and even estimate certain facial expressions and convert them into events. Such events can be used to animate digital avatars as well, using blend shapes (or shape keys in some applications like Blender 3D). SentiMask SDK works with regular hardware, such as webcams, and no depth sensors or special cameras are required. It can be integrated with 3D modeling software and 3D game engines and provides easy integration for custom projects. Other main features of SentiMask SDK include:
- Real-time face detection and tracking
- 2D & 3D facial landmark estimation
- 3D facial pose, shape and expression estimation
- 3D facial mesh output
- Facial expression analysis (left, right eye closed; left, right eyebrow up or down; jaw moving left or right; left, right lip corners moving up or down, left or right)
SentiMask SDK supports development environments under PC platforms (Windows and Linux) as well as the mobile Android platform.
SentiMask SDK is the latest offering in Neurotechnology's "Senti" line of AI and robotics products, including the SentiBotics mobile robotics development kit, SentiSight SDK for development of computer and robotic vision applications, SentiSculpt SDK for development of 3D models using standard 2D images and SentiVeillance SDK and SentiVeillance Server for face identification and movement tracking in video surveillance systems.
SentiMask SDK and the entire line of Neurotechnology products for AI, robotics, object recognition and biometric identification are available from Neurotechnology or distributors worldwide. For more information and trial version, go to: www.neurotechnology.com.
Neurotechnology is a developer of high-precision algorithms and software based on deep neural network (DNN) and other AI-related technologies. The company offers a range of products for biometric fingerprint, face, iris, palmprint and voice identification as well as AI, computer vision, object recognition and robotics. Drawing from years of academic research in the fields of neuroinformatics, image processing and pattern recognition, Neurotechnology was founded in 1990 in Vilnius, Lithuania and released its first fingerprint identification system in 1991. Since that time the company has released more than 130 products and version upgrades. More than 3000 system integrators, security companies and hardware providers integrate Neurotechnology's algorithms into their products, with millions of customer installations worldwide. Neurotechnology's algorithms also achieved top results in independent technology evaluations including NIST MINEX and IREX.
Jennifer Allen Newton
Bluehouse Consulting Group, Inc.
jennifer (at) bluehousecg (dot) com