Learning the Spherical Harmonic Features for 3-D Face Recognition

Abstract

In this paper, a competitive method for 3-D face recognition (FR) using spherical harmonic features (SHF) is proposed. With this solution, 3-D face models are characterized by the energies contained in spherical harmonics with different frequencies, thereby enabling the capture of both gross shape and fine surface details of a 3-D facial surface. This is in clear contrast to most 3-D FR techniques which are either holistic or feature based, using local features extracted from distinctive points. First, 3-D face models are represented in a canonical representation, namely, spherical depth map, by which SHF can be calculated. Then, considering the predictive contribution of each SHF feature, especially in the presence of facial expression and occlusion, feature selection methods are used to improve the predictive performance and provide faster and more cost-effective predictors. Experiments have been carried out on three public 3-D face datasets, SHREC2007, FRGC v2.0, and Bosphorus, with increasing difficulties in terms of facial expression, pose, and occlusion, and which demonstrate the effectiveness of the proposed method.

WCTFR : Wrapping Curvelet Transform Based Face Recognition

“…Rotation-invariant multi-scale local surface descriptors are built around the identified key points to extract distinctive facial features for robust feature matching. The proposed algorithm is robust and accurate for varying illumination and facial expressions with a better verification rate than [2], [3], [4] and [5].…”

“…Compared to wavelet transforms, the curvelet transform has better directional and edge representation abilities; hence the face image is decomposed to get low frequency coefficients by curvelet transform. (2D) 2 PCA with an exponential decay factor is applied on these selected coefficients to extract feature vectors and thus achieves reduction in dimension. The nearest neighbor classifier is adopted for classification.…”

Interactive Three-Dimensional Model Reconstruction of Ultrasonography

“…The neural efficiency could thus be assessed from magnetic and electric fields without having to measure the brain activities on the entire cortical surface. Learning spherical harmonic features (SHF) for 3D face recognition was proposed in (16) .…”

3D Face Analysis: Advances and Perspectives

“…Compared with other keypoints, the nose tip is the most widely needed, and relatively easy and efficient to localize, by adopting e.g. curvature analysis [128], profile analysis [18], and Spherical Depth Map (SDM) fitting [130], etc. Current 3D landmarking techniques can be roughly categorized into two streams, i.e.…”