Introducing improved face detection model, more robust to various challenging conditions such as faces with high variability in scale, illumination, pose and occlusion.
Introducing new VNN algorithm fast mode which significantly improves performance at the cost of feature points precision while keeping the same precision of head pose.
VNN tracking algorithm now works with higher FPS, with significant improvements on devices such as high-end mobile and desktop devices
New VNN tracking models now work with less tracking jitter.
Optimized for running neural networks and significantly improving the performance of visage|SDK algorithms.
Introducing a smaller, faster, and more accurate face recognition model that completely replaces the old model that will no longer be distributed.
The model is available for desktop platforms and on mobile platforms.
The new algorithm minimizes jitter, increases tracking accuracy and robustness but reduces tracking performance (speed). It is demonstrated in ShowcaseDemo and FaceTracker2 samples via new Ultra tracking configuration.
Significantly improves the performance of age estimation, face recognition and face tracking with VNN algorithm on Intel 64-bit processors.
OpenVINO is a trademark of Intel Corporation or its subsidiaries.
Additional 24 feature points on ears are now tracked (12 points per ear). Ear tracking is configurable through the tracker configuration file or API.
Face data from tracker and detector now includes information about iris diameter.
It is now possible to modify specific tracker configuration parameters via an interface during tracking.
Smoothing of feature points is performed using multiple filters. For still face, higher amount of smoothing is applied while fast movements are less smoothed in order to avoid noticeable delay. Increased stability of feature points and head position especially in profile and half-profile pose.
The core tracking loop was re-implemented to make the tracking frame rate less dependent on the size of the face in the image. This fixes performance drops in cases where the face takes up a small portion of the frame. Additionally, noise introduced by resizing of higher-resolution frames is reduced which results in more stable tracking.
API for fetching tracking data has been modified to return typed arrays. Improves performance and simplifies memory management of tracked data.