Accurate human face pose recovery from single image through generic shape regularization
| Autor: | Chaoqun Hong, Xiaosi Zhan, Rui Sun, Jian Zhang |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
business.industry
Orthographic projection Pattern recognition Image plane 3D pose estimation Regularization (mathematics) Image (mathematics) symbols.namesake Control and Systems Engineering Face (geometry) Signal Processing symbols Computer vision Computer Vision and Pattern Recognition Artificial intelligence Electrical and Electronic Engineering Projection (set theory) business Newton's method Software Mathematics |
| Zdroj: | Signal Processing. 110:5-14 |
| ISSN: | 0165-1684 |
| DOI: | 10.1016/j.sigpro.2014.08.001 |
| Popis: | In this paper, we propose a novel approach to recovering face pose from a single face image. The projection from 3D space to image plane is modeled by a scaled orthogonal projection, which contains the unknown pose parameters and face shape. To remove the ambiguity, the projection is regularized by prior information about generic face shape. Given a set of image features and a set of 3D features selected from a generic face, we can solve the unknown pose parameters conveniently through a Newton method. Owing to the shape regularization, the efficiency and accuracy of the proposed method precede the existed approach. HighlightsThe solution of this approach is very close to the globally optimized solution.The approach does not need any training sample.The computational efficiency of the approach is very high. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect