Method and system for facial landmark localization
AssigneeCarnegie Mellon University
InventorsMarios Savvides, Keshav Thirumalai Seshadri
Life of this patent
Estimating the term…
Abstract
This invention describes methods and systems for the automated facial landmark localization. Our approach proceeds from sparse to dense landmarking steps using a set of models to best account for the shape and texture variation manifested by facial landmarks across pose and expression. We also describe the use of an l1-regularized least squares approach that we incorporate into our shape model, which is an improvement over the shape model used by several prior Active Shape Model (ASM) based facial landmark localization algorithms.
Claims19
A system for automatically localizing a set of facial landmarks on a facial image comprising:
- creating M sets of seed landmarks by placing seed landmarks on the facial image using a plurality of pose-specific local detectors, one pose-specific local detector for each one of M discrete yaw angles;
- aligning each set of seed landmarks with a plurality of pose-specific dense shapes comprising a dense set of landmarks;
- evaluating each dense shape for each of the M sets of seed landmarks to determine the best dense shape for each of the M sets of seed landmarks;
- and
- refining each of M best dense shapes and ranking the M best dense shapes to determine the single best dense shape containing dense landmarks best aligned with the facial image.
Dependencies are inferred from the claim text.