ML p(r)ior | Head Pose Estimation of Occluded Faces using Regularized Regression

Head Pose Estimation of Occluded Faces using Regularized Regression

2016-02-02
This paper presents regression methods for estimation of head pose from occluded 2-D face images. The process primarily involves reconstructing a face from its occluded image, followed by classification. Typical methods for reconstruction assume that the pixel errors of the occluded regions are independent. However, such an assumption is not true in the case of occlusion, because of its inherent contiguous nature. Hence, we use nuclear norm as a metric that can describe well the structure of the error. We also use LASSO Regression based l1 - regularization to improve reconstruction. Next, we implement Nuclear Norm Regularized Regression (NR), and also our proposed method, for reconstruction and subsequent classification. Finally, we compare the performance of the methods in terms of accuracy of head pose estimation of occluded faces.
PDF

Highlights - Most important sentences from the article

Login to like/save this paper, take notes and configure your recommendations

Related Articles

2017-08-03

With the powerfulness of convolution neural networks (CNN), CNN based face reconstruction has recent… show more
PDF

Highlights - Most important sentences from the article

2015-05-08

We review some recent learning approaches in variational imaging, based on bilevel optimisation, and… show more
PDF

Highlights - Most important sentences from the article

2016-05-08

In this paper we propose an iterative method to address the face identification problem with block o… show more
PDF

Highlights - Most important sentences from the article

2019-03-20

Recently, deep learning based 3D face reconstruction methods have shown promising results in both qu… show more
PDF

Highlights - Most important sentences from the article

2015-03-08

In this paper, we propose a novel fitting method that uses local image features to fit a 3D Morphabl… show more
PDF

Highlights - Most important sentences from the article

2017-11-02

A major challenge in X-ray computed tomography (CT) is reducing radiation dose while maintaining hig… show more
PDF

Highlights - Most important sentences from the article

2019-05-16
1905.06505 | cs.CV

3D face reconstruction from a single 2D image is a very important topic in computer vision. However,… show more
PDF

Highlights - Most important sentences from the article

2019-05-25

The methods of extracting image features are the key to many image processing tasks. At present, the… show more
PDF

Highlights - Most important sentences from the article

2019-03-21

The aim of this paper is to discuss some advanced aspects of image reconstruction in single-pixel ca… show more
PDF

Highlights - Most important sentences from the article

2019-01-23
1901.07720 | cs.CV

Nonlocal self-similarity and group sparsity have been widely utilized in image compressive sensing (… show more
PDF

Highlights - Most important sentences from the article

2019-04-04

The field of image reconstruction has undergone four waves of methods. The first wave was analytical… show more
PDF

Highlights - Most important sentences from the article

2019-03-20

Over the past few years, dictionary learning (DL)-based methods have been successfully used in vario… show more
PDF

Highlights - Most important sentences from the article

2019-03-07

Recently, label consistent k-svd (LC-KSVD) algorithm has been successfully applied in image classifi… show more
PDF

Highlights - Most important sentences from the article

2017-11-30

Algorithms for Magnetic Resonance (MR) image reconstruction from undersampled measurements exploit p… show more
PDF

Highlights - Most important sentences from the article

2018-01-23

Recent advances show that two-dimensional linear discriminant analysis (2DLDA) is a successful matri… show more
PDF

Highlights - Most important sentences from the article