Abstract
Many 2D face processing algorithms can perform better using frontal or near frontal faces. In this paper, we present a robust frontal view search method based on manifold learning, with the assumption that with the pose being the only variable, face images should lie in a smooth and low-dimensional manifold. In 2D embedding, we find that manifold geometry of face images with varying poses has the shape of a parabola with the frontal view in the vertex. However, background clutter and illumination variations make frontal view deviate from the vertex. To address this problem, we propose a pairwise K-nearest neighbor protocol to extend manifold learning. In addition, we present an illumination-robust localized edge orientation histogram to represent face image in the extended manifold learning. The experimental results show that the extended algorithms have higher search accuracy, even under varying illuminations.
Original language | English (US) |
---|---|
Pages (from-to) | 1147-1154 |
Number of pages | 8 |
Journal | Journal of Visual Communication and Image Representation |
Volume | 24 |
Issue number | 7 |
DOIs | |
State | Published - 2013 |
Keywords
- Frontal face
- Frontal view
- Frontal view search
- K-nearest neighbor protocol
- Laplacian eigenmaps
- Localized edge orientation histogram
- Locally linear embedding
- Manifold learning
- Pairwise
- Pose estimation
ASJC Scopus subject areas
- Signal Processing
- Media Technology
- Computer Vision and Pattern Recognition
- Electrical and Electronic Engineering