Head pose estimation method based on pose manifold and tensor decomposition

Pose manifold and tensor decomposition are used to represent the nonlinear changes of multi-view faces for pose estimation,which cannot be well handled by principal component analysis or multilinear analysis methods.A pose manifold generation method is introduced to describe the nonlinearity in pose subspace.And a nonlinear kernel based method is used to build a smooth mapping from the low dimensional pose subspace to the high dimensional face image space.Then the tensor decomposition is applied to the nonlinear mapping coefficients to build an accurate multi-pose face model for pose estimation.More importantly,this paper gives a proper distance measurement on the pose manifold space for the nonlinear mapping and pose estimation.Experiments on the identity unseen face images show that the proposed method increases pose estimation rates by 13.8% and 10.9% against principal component analysis and multilinear analysis based methods respectively.Thus,the proposed method can be used to estimate a wide range of head poses.

Multiclass classification based on a deep convolutional network for head pose estimation

Head pose estimation has been considered an important and challenging task in computer vision. In this paper we propose a novel method to estimate head pose based on a deep convolutional neural network （DCNN） for 2D face images. We design an effective and simple method to roughly crop the face from the input image, maintaining the individual-relative facial features ratio. The method can be used in various poses. Then two convolutional neural networks are set up to train the head pose classifier and then compared with each other. The simpler one has six layers. It performs well on seven yaw poses but is somewhat unsatisfactory when mixed in two pitch poses. The other has eight layers and more pixels in input layers. It has better performance on more poses and more training samples. Before training the network, two reasonable strategies including shift and zoom are executed to prepare training samples. Finally, feature extraction filters are optimized together with the weight of the classification component through training, to minimize the classification error. Our method has been evaluated on the CAS-PEAL-R1, CMU PIE, and CUBIC FacePix databases. It has better performance than state-of-the-art methods for head pose estimation.

Unseen head pose prediction using dense multivariate label distribution

Accurate head poses are useful for many face-related tasks such as face recognition, gaze estimation,and emotion analysis. Most existing methods estimate head poses that are included in the training data(i.e.,previously seen head poses). To predict head poses that are not seen in the training data, some regression-based methods have been proposed. However, they focus on estimating continuous head pose angles, and thus do not systematically evaluate the performance on predicting unseen head poses. In this paper, we use a dense multivariate label distribution(MLD) to represent the pose angle of a face image. By incorporating both seen and unseen pose angles into MLD, the head pose predictor can estimate unseen head poses with an accuracy comparable to that of estimating seen head poses. On the Pointing'04 database, the mean absolute errors of results for yaw and pitch are 4.01?and 2.13?, respectively. In addition, experiments on the CAS-PEAL and CMU Multi-PIE databases show that the proposed dense MLD-based head pose estimation method can obtain the state-of-the-art performance when compared to some existing methods.