^{1, 2}

^{3}

^{1, 2}

^{1}

^{1}

^{2}

^{3}

It is an important task to locate facial feature points due to the widespread application of 3D human face models in medical fields. In this paper, we propose a 3D facial feature point localization method that combines the relative angle histograms with multiscale constraints. Firstly, the relative angle histogram of each vertex in a 3D point distribution model is calculated; then the cluster set of the facial feature points is determined using the cluster algorithm. Finally, the feature points are located precisely according to multiscale integral features. The experimental results show that the feature point localization accuracy of this algorithm is better than that of the localization method using the relative angle histograms.

With the development of 3D information acquisition technology, the research of 3D facial feature has gained more and more extensive attention. The automatic localization of the facial feature points is a study hotspot in the field of medical computer vision, which is a precondition for face recognition, face animation, face tracking, and 3D face reconstruction. At present, the 3D facial feature point localization algorithms have not been researched in depth though the 2D facial feature point localization algorithms have matured. Wang et al. [

In order to solve these problems, we put forward a 3D facial feature point localization method based on the relative angle histograms and multiscale constraints. The cluster point set of the facial features is created firstly, and then the multiscale integral characteristics are used to locate the feature points accurately. As a result, the accuracy of the feature point localization is improved.

CT (computed tomography) images are acquired from living samples in a hospital, whose contour lines are extracted using the method of combining the improved snake algorithm with the ray method [

A face model

The point set

According to the related knowledge of algebra,

The coordinate system of a model.

The feature points of a 3D face must have connotations and lie in a cognizable key position. In the same sample the feature points are distinct from their neighbor points on geometrical characteristics, while in different samples the features of the same feature points are similar. To meet the experimental requirements, a total of 39 feature points covering the front half face are defined according to the knowledge of anthropology, anatomy, and the feature points defined by MPEG4 expert group [

Feature points of the single layer face model.

After the face model is unified into a uniform coordinate system, the next step is to calculate the relative angle histograms of points in the face model. According to Feng et al. [

The relative angles of the point in the face model describe a spatial relationship between every point, which possesses rotation, translation, and scaling invariance and better noise robustness. Any point of the model has

Calculate the

The relative angle distribution of the feature points. (a) The feature points of the forehead center: the left is the relative angle distribution of forehead center feature points and the right is the relative angle distribution of superimposed forehead center feature points. (b) The feature points of the right mouth corner: the left is the relative angle distribution of right mouth corner feature points and the right is the relative angle distribution of superimposed right mouth corner feature points.

There are 39 feature points in a standard face model

According to the prior knowledge, the representative points are selected as the initial cluster center

Calculate the similarity between

Select the maximum similarity

Figure

The result of the point cluster.

The nasal tip

The forehead center

The volume integral features are defined as multiscale feature values, which could weaken the noise influence with bigger robustness than the differential values, and measure the concave-convex level of the model surface.

The volume integral invariant of a surface point

2D representation of the volume integral invariant.

Equation (

From (

Concave-convex is a relative concept. Concave-convex level will transform with the scale change. As is shown in Figure

Multiscale theory.

Multiscale geometrical feature extraction [

Multiscale feature extraction.

We calculate the integral features of cluster points

We design a feature point of 3D face localization system (FaceLS) according to the proposed feature point localization algorithm. Forty sets of 3D point distribution face model data are selected randomly from a monolayer face sample library, which belongs to the North West University, and are taken as the face samples of the feature points which will be located. The algorithm is tested and compared with the localization method of Feng et al. [

The evaluation method of the feature point localization is as follows: given a distance threshold value

The steps of our method are as follows.

According to the prior knowledge, the representative points are selected as the initial cluster center

Calculate the similarity between

Select maximum similarity

We calculate the integral features of cluster points

Given a distance threshold value

Figure

The mean accuracy rates of two feature point localization methods.

Method | The mean accuracy rate/% | |||
---|---|---|---|---|

Nose | Left eye | Right eye | Mouth | |

Feng et al. [ |
62.0 | 78.3 | 77.6 | 63.8 |

Our method | 89.2 | 84.5 | 85.6 | 71.3 |

Result comparison of two feature point localization methods.

Our method

Relative angle histogram method

Comparison of the accuracy rate for two feature point localization methods.

The feature point cluster set is determined firstly by the cluster algorithm and the relative angle histogram algorithm, and then the feature points are located accurately by the steady multiscale integral features, so the accuracy rate of localization is improved greatly. The localization method based on relative angle histograms has limitations, because it locates feature points to a smaller range through comparing the similarity of relative angle histograms and this method is suitable for conspicuous feature points, while the accuracy will be decreased for the inconspicuous feature points.

In this work we propose a method that combines the relative angle histograms with the multiscale constraints for localization of the feature points in a 3D face. The feature point cluster set is determined through the cluster algorithm and the relative angle histograms, and then feature points are located accurately by the multiscale integral features, which could avoid many wrong matches in the result caused by the precision and similarity of the local geometrical characteristic. Experimental results show that this method performs well and the accuracy rate of localization is improved. But the accuracy rate of localization is nonideal under the condition of feature points on smooth part of a face, so this should be the next research direction.

The authors declare that there is no conflict of interests regarding the publication of this paper.

This research is supported by the National Natural Science Foundation of China (Grant no. U1261114), the Key Technologies R&D Program of Henan Province (no. 142102210637), and the Xi’an University of Science and Technology Cultivation Foundation Project (2014032). The authors would like to thank the anonymous reviewers for their valuable comments and suggestions.