Rome, Italy -- (ReleaseWire) -- 11/19/2015 --Dasha Face Detector is a premium quality tracker that allows users the opportunity to show 66 landmarks to use for many applications such as draw, gestures recognition, and 2D/ 3D animation on Android, IOs and Desktop. This proposed tracker is based on the 'Constrained Local Model' or 'CLM.'
The 'Constrained Local Model' is able to register a non-rigid object through the application of an ensemble of region experts to local search regions within the source image being registered. The response surfaces from these local regions are employed within a joint optimization process to estimate the global non- rigid shape of the object.
Some of the major advantages of 'CLM' over conventional non-rigid registration methods are
- Discriminative and generalizes well to unseen appearance variation.
- Greater invariance to global illumination variation and occlusion.
- Models the non-rigid object as an ensemble of low dimensional independent patch experts.
Performance related parameters of Dasha Face Detector:
- 50 fps average speed (competitors are under 25fps) ON MOBILE PHONE
- Rotations on 3 axes (x,y,x)
- Awesome performance with critical light's changes
- Custom render for any final codec
- Opportunity to engage video call flow
- Augmented Reality's Engine
CEO and Founder of Dasha Face Detector Marco Oliva has recently started a crowdfunding campaign via AngelList. Funds raised via this campaign will be used for the market launch of Dasha Face Detector.
To find out more about this campaign, please visit http://bit.ly/1FPPALx
The website of Dasha Face Detector is http://www.nga.mobi/dasha/
About Dasha Face Detector
Dasha Face Detector is a premium quality tracker that allows users the opportunity to show 66 landmarks to use for many applications such as draw, gestures recognition, and 2D/ 3D animation on Android, IOs and Desktop. This proposed tracker is based upon the 'Constrained Local Model' or 'CLM.'
