Face Orientation Estimation by Particle Swarm Optimization

Zhang, Yudong; Wu, Lenan; Dong, Zhengchao; Wang, Shuihua; Zhou, Zhengyu

doi:10.1109/isise.2009.10

Cited by 6 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The template subject with 40 poses were photographed and taken as test images, of which the three rotational angles are uniformly distributed within the range [0, 180] in unit of degree. GA [13] and PSO [5] are chosen as the comparison basis.…”

Section: Methodsmentioning

confidence: 99%

“…the camera reference frame, giving some certain measurements of the object in both frames [4]. The image data from which the pose of an object is determined can be either a single image, a stereo image pair, or an image sequence [5]. The objects can be rather general, including a living being or body parts, e.g., the human face [6].…”

Section: Introductionmentioning

confidence: 99%

“…Sattar et al used genetic algorithm (GA) to determine the parameters from the knowledge of a given set of points [13]. Zhang et al proposed a particle swarm optimization (PSO) to get the orientation parameters of two faces [5]. Unfortunately, the estimation errors of both GA and PSOare a bit large.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Application of Time-varying Acceleration Coefficients PSO to Face Pose Estimation

Yu-dong¹,

Wang²,

Ji³

2015

Proceedings of the First International Conference on Information Sciences, Machinery, Materials and Energy

Self Cite

View full text Add to dashboard Cite

This study focuses on the problem of human face pose estimation based on single image. Traditional methods for 2D-3D feature based pose estimation problem require two inputs, and they cannot work well due to lack of correspondences of input images. We transfer the problem into an optimization problem via six-point template, and solve the problem by time-varying acceleration coefficients particle swarm optimization (TVAC-PSO). Experiments on 40 different poses demonstrate that the TVAC-PSO is superior to either GA or PSO in terms of accuracy.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of Time-varying Acceleration Coefficients PSO to Face Pose Estimation

Yu-dong¹,

Wang²,

Ji³

2015

Proceedings of the First International Conference on Information Sciences, Machinery, Materials and Energy

Self Cite

View full text Add to dashboard Cite

show abstract

“…They were used in solving discrete and numerical optimization problems as well as practical applications, e.g., in [7,11,13,[17][18][19]. According to the NFL theorem [16], average performances of different algorithm families are the same when they are applied to all classes of problems.…”

Section: Introductionmentioning

confidence: 99%

Population Size Reduction in Particle Swarm Optimization Using Product Graphs

Fister

Tepeh

Brest

2015

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Purpose of this paper is to introduce a population size reduction in particle swarm optimization algorithm, where the reduction is performed by selecting two particles (also donor particles) randomly and replacing these by a new particle with elements determined from a set of pair values obtained by the Cartesian product of both donor particles for each particular element randomly. Average values of each pair values from the donor particles are calculated for corresponding elements of the new particle. The proposed PSOGP was applied on a benchmark function suite consisted of four well-known functions and compared with the original PSO algorithm. The results are very promising and show the potential of the proposed idea.

show abstract

“…This method includes feature based method which constructs a model with geometrical structure or geometrical body such as plane [11] and cone [12], ASM method [15], template based method [7] and etc. Commonly positions of eyes, nose and mouth are used as feature point of face.…”

Section: Introductionmentioning

confidence: 99%

Face pose estimation based on EHMM and SVM

Kim¹,

2011

2011 International Conference on Computer Science and Service System (CSSS)

View full text Add to dashboard Cite

Estimating pose of human face plays important role in lip reading. Mouth shape varies on face pose variation. Therefore, pose estimation will be front end of lip reading system. Embedded HMM can be successfully applied in estimating pose of human face. Advantage of EHMM based pose estimation method is non-sensitive in parallel shift and scale varying. On the other side, SVM is the classifier which has strong discrimination ability. This paper suggests EHMM and SVM based human face pose estimation method. It was experimented on CubiC FacePix database and was estimated with several range of angle. Experiment proved validity of this algorithm.

show abstract

Face Orientation Estimation by Particle Swarm Optimization

Cited by 6 publications

References 8 publications

Application of Time-varying Acceleration Coefficients PSO to Face Pose Estimation

Application of Time-varying Acceleration Coefficients PSO to Face Pose Estimation

Population Size Reduction in Particle Swarm Optimization Using Product Graphs

Face pose estimation based on EHMM and SVM

Contact Info

Product

Resources

About