Name
Abstract | ||
|---|---|---|
We present a machine learning framework that automatically generates a model set of landmarks for some class of registered 3D objects: here we use human faces. The aim is to replace heuristically-designed landmark models by something that is learned from training data. The value of this automatically generated model is an expected improvement in robustness and precision of learning-based 3D landmarking systems. Simultaneously, our framework outputs optimal detectors, derived from a prescribed pool of surface descriptors, for each landmark in the model. The model and detectors can then be used as key components of a landmark-localization system for the set of meshes belonging to that object class. Automatic models have some intrinsic advantages; for example, the fact that repetitive shapes are automatically detected and that local surface shapes are ordered by their degree of saliency in a quantitative way. We compare our automatically generated face landmark model with a manually designed model, employed in existing literature. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1109/CVPRW.2012.6238915 | CVPR Workshops |
Keywords | Field | DocType |
computational modeling,solid modeling,learning artificial intelligence,detectors,shape,image registration,measurement | Computer vision,Polygon mesh,Pattern recognition,Computer science,Salience (neuroscience),Robustness (computer science),Object Class,Artificial intelligence,Solid modeling,Landmark,Detector,Image registration | Conference |
Volume | Issue | ISSN |
2012 | 1 | 2160-7508 |
Citations | PageRank | References |
4 | 0.45 | 11 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Clement Creusot | 1 | 72 | 3.79 |
| Nick Pears | 2 | 410 | 30.57 |
| Jim Austin | 3 | 1167 | 66.82 |