Core Technologies

Based on the foundation of proprietary technologies and a core “brain” built on a deep learning platform, SenseTime has rapidly opened up AI application in multiple vertical scenarios.

Face and Body Analyzing Technology

Face and Body Analyzing Technology

Technical Capabilities

Face Detection and Tracking
Facial Feature Point Positioning
Facial Identity Recognition
Facial Attributes
Face Grouping
Liveness Detection
Portrait Beautification/Make-up
Body Feature Point

Face Detection and Tracking

Face detection and tracking can be achieved at millisecond level on embedded devices, mobile devices, and PCs in common scenarios. The technology can detect faces from different angles under different environments, such as face side-profiles, obscured and blurry facial images, , low light and backlight scenarios, changes in facial expression, and 360° panorama. It also supports various image and video types, including full-color, black-and-white, and near-infrared images and videos.

Facial Feature Point Positioning

Millisecond-level positioning 21, 106 or 240 facial feature key points on eyes, mouths, noses on various accuracy levels. This technology is capable of decoding wide-angle face side-profiles, dramatic changes in facial expressions, partially obscured and blurry images, and changes in light, as well as facial images taken in other environments.

Facial Identity Recognition

The solution determines whether two images are of the same person with over 99% accuracy.

Facial Attributes

The facial attribute solution accurately recognizes more than 10 facial attributes such as gender, facial expressions, accessories, beards and facial motions among others. It can be deployed in targeted advertising or consumer analysis to better understand the audience and the customers.

Face Grouping

The face grouping solution rapidly consolidates hundreds of thousands of faces and is applicable to intelligent photo album management and analysis of group photos on social networks. Not only does it make photo management easier, but it allows social networks to run and operate in a more efficient manner.

Liveness Detection

The liveness detection solution serves as an additional security measure for user verification and prevent spoofing attacks. Together with face verification, it can identify whether the image in front of the camera is a real person or an image manipulation, providing important security services for applications in industries such as finance. The liveness detection solution can effectively differentiate between high-definition photos, photoshopped images, 3D models, face swaps, and other attempts to bypass the system.

Portrait Beautification/Make-up

Based on face detection and recognition technology, beautification solution provides a wide range of smartphone portrait beautification and make-up effects for real-time scenarios.

Body Feature Point

Developed as the first solution to enable the positioning of 14 body feature points on mobile devices, it leverages RGB images to provide real-time recognition of the head, shoulders, limbs and other parts of the body, and can be deployed to detect a wide range of body movements.