Robust head pose estimation via Convex Regularized Sparse Regression

Ji, Hao; Liu, Risheng; Su, Fei; Su, Zhixun; Tian, Yan

doi:10.1109/icip.2011.6116500

Cited by 21 publications

(10 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Table 3, we show the F-Score of classification for each frame size (w=5, 6,7,8,9,10,15,20,25,35,45, 55 and 64) and with different alphabet size (a=5, 6, 7, 8, 64, 128). We classified the poses using K-means algorithm into three main classes: class of frontal pose, class of the left view, and class of the right view that group poses in quarter profile (left or right) at full profile.…”

Section: Experiments and Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Local Patterns and Big Time Series Data for Facial Poses Classification

Mekami¹

2018

JCP

View full text Add to dashboard Cite

The problem of identifying and analyzing faces in images is a fundamental task in computer vision. Though great progress has been achieved in face detection, it is still difficult to obtain the pose estimation. In this paper we propose a pose estimation approach that is based on time series representation. We have converted input images of faces into big time series datasets, and we then used a dimensionality reduction method to convert the original series to a symbolic representation. Classification algorithms are then applied using the distances between the symbolic sequences of time series. Since external conditions when capturing images are not always optimal, pose estimation can become a challenge. In order to overcome such problems, we propose to use the gradient image and the Local Binary Pattern (LBP) combined with dynamic morphological quotient image (DMQI-LBP), where these descriptors are robust to changes in illumination. Classification algorithms such as K-means, SVM and KNN were evaluated to classify frontal vs profile faces poses, and the obtained experimental results show that the proposed method is very efficient.

show abstract

Section: Experiments and Resultsmentioning

confidence: 99%

“…Different regressors have been suggested. Li et al [5] used Support Vector Regressors (SVRs), Gaussian Progress Regression (GPR) [6] and Convex Regularized Sparse Regression (CRSR) [7].…”

Section: Related Workmentioning

confidence: 99%

Local Patterns and Big Time Series Data for Facial Poses Classification

Mekami¹

2018

JCP

View full text Add to dashboard Cite

show abstract

“…MAE (Balasubramanian et al, 2007) Biased Isomap 5.02°B iased LLE 2.11°B iased LE 1.44° ( Liu et al, 2010) Manifold clustering 3.16° ( Ji et al, 2011) Regression 6.1° ( Dahmane et al, 2014) Symmetry classification 3.14° ( Narayanan et al, 2014) CE 5.55°C enter CE 5.26°B oundary CE 5.28°P roposed Method HYE1 5.2°H YE2 4.8°I…”

Section: Methodsmentioning

confidence: 99%

“…Reco. rates (Stiefelhagen, 2004) 9.5°52% (Gourier et al, 2007) Human Performance 11.8°40.7% Associative Memories 10.1°50.0% (Tu et al, 2007) High-order SVD 12.9°49.25% PCA 14.11°55.20% LEA 15.88°45.16% (Ji et al, 2011) Regression 8.6°- (Narayanan et al, 2014) CE 7.2°-Center CE 6.82°-Boundary CE 6.9°-Proposed Method HYE1 6.96°63.81% HYE2 7.15°59.05%…”

Section: Methods Maementioning

confidence: 99%

See 1 more Smart Citation

Head Yaw Estimation using Frontal Face Detector

Mennesson

Dahmane

Danışman

et al. 2016

Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

View full text Add to dashboard Cite

Detecting accurately head orientation is an important task in systems relying on face analysis. The estimation of the horizontal rotation of the head (yaw rotation) is a key step in detecting the orientation of the face. The purpose of this paper is to use a well-known frontal face detector in order to estimate head yaw angle. Our approach consists in simulating 3D head rotations and detecting face using a frontal face detector. Indeed, head yaw angle can be estimated by determining the angle at which the 3D head must be rotated to be frontal. This approach is model-free and unsupervised (except the generic learning step of VJ algorithm). The method is experimented and compared with the state-of-the-art approaches using continuous and discrete protocols on two well-known databases : FacePix and Pointing04.

show abstract