Pose determination of human faces by using vanishing points

Wang, Jiangang; Sung, Eric

doi:10.1016/s0031-3203(00)00154-0

Cited by 25 publications

(9 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They have used the corners of the eyes and mouth to derive equation for pose estimation. The proposed method is similar to Ho (1998) and Wang (2001) to some extent. However, it has certain advantages over them.…”

Section: Related Workmentioning

confidence: 88%

See 1 more Smart Citation

Face pose estimation from eyes and mouth

Shafi¹,

Chung²

2010

IJAMECHS

View full text Add to dashboard Cite

Face pose estimation plays an important role in human computer interaction, automatic human behavior analysis, gaze estimation, virtual reality, pose independent face recognition etc. Accuracy and speed are the most desirable features of a face pose estimation system. In this paper, a face pose estimation scheme based on the centers of the eyes and mouth is proposed. The proposed method is simple and is, therefore, very effective in terms of computation because it uses only three points i.e. eyes and mouth centers. The use of only three points increases the pose estimation range and makes the method suitable for real time applications. Tests using the Pointing' 04 database show that the proposed scheme is robust and fast.

show abstract

Section: Related Workmentioning

confidence: 88%

“…Ho and Huang (1998) presented an analytical solution for the pose estimation from monocular image. Wang and Sung (2001) proposed pose determination of human faces by using vanishing points. They have used the corners of the eyes and mouth to derive equation for pose estimation.…”

Section: Related Workmentioning

confidence: 99%

Face pose estimation from eyes and mouth

Shafi¹,

Chung²

2010

IJAMECHS

View full text Add to dashboard Cite

show abstract

“…But the most of traditional approaches always needs two corresponding face images just as the inputs at both sides of equation (1). Therefore, another images are required, such as Jian-Gang Wang and Eric Sung [6] used the ratio of the length of the eye-line segment and the length of the mouth-line segment as a priori knowledge for this ratio is relatively stable from face to face. Qiang Ji [7] employed an ellipse as face template and the ratio of the major axis and minor axis' length is given.…”

Section: Feature-based 2d-3d Pose Estimationmentioning

confidence: 99%

Robust Pose Estimation of Face Using Genetic Algorithm

Zhanga

Feng

Lai

2004

Advances in Biometric Person Authentication

View full text Add to dashboard Cite

Abstract. This paper focuses on the problem of human face pose estimation using single image. Because the traditional approaches for 2D-3D feature-based pose estimation problem requires two inputs, they can not work very well due to lack of correspondences of the input image. In this paper, we propose pose estimation algorithm for human face based on genetic algorithm. The proposed method overcomes the shortcomings by using a general 3D point-feature template as the correspondences and some more constraints onto the optimizing function. The experiments show the proposed method gives good performance in accuracy and robustness.

show abstract

“…Model-based approaches can be tackled from a concise mathematical formulation [15], or if real-time analysis is required, by simplifying the problem using affine transformations [13]. Examples of this class of approaches include the use of vanishing points [39,40], different shape models such as planar [4], cylindrical [7], ellipsoidal [2,10] and deformable ones [21]. In some cases, the problem is tackled from a tracking point of view that can be solved by fusing multiple cues [31] or using infrared light to detect the pupils [17].…”

Section: Introductionmentioning

confidence: 99%

Multi-camera head pose estimation

Muñoz-Salinas

Yeguas-Bolivar

Saffiotti

et al. 2012

Machine Vision and Applications

View full text Add to dashboard Cite

Estimating people's head pose is an important problem, for which many solutions have been proposed. Most existing solutions are based on the use of a single camera and assume that the head is confined in a relatively small region of space. If we need to estimate unintrusively the head pose of persons in a large environment, however, we need to use several cameras to cover the monitored area. In this work, we propose a novel solution to the multi-camera head pose estimation problem that exploits the additional amount of information that provides multi-camera configurations. Our approach uses the probability estimates produced by multiclass support vector machines to calculate the probability distribution of the head pose. The distributions produced by the cameras are fused, resulting in a more precise estimate than the one provided individually. We report experimental results that confirm that the fused distribution provides higher accuracy than the individual classifiers and a high robustness against errors.

show abstract

Pose determination of human faces by using vanishing points

Cited by 25 publications

References 23 publications

Face pose estimation from eyes and mouth

Face pose estimation from eyes and mouth

Robust Pose Estimation of Face Using Genetic Algorithm

Multi-camera head pose estimation

Contact Info

Product

Resources

About