arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0912.0600cs.CV
收藏

基于序列聚类的人脸特征提取正交视图模型自动生成方法

Sequential Clustering based Facial Feature Extraction Method for Automatic Creation of Facial Models from Orthogonal Views

Alireza Ghahari, Reza Aghaeizadeh Zoroofi

摘要:

多视点三维人脸建模技术近年来受到越来越多的关注,并已成为未来视频系统的潜在途径之一。我们的目标是使更可靠和强大的自动特征提取和自然的三维特征建设从一对正面和侧面视图人脸图像上检测到的二维特征。我们提出了几种启发式算法,以尽量减少可能的错误引入普遍的非完美正交条件和非相干亮度。在我们的方法中,我们首先提取在两个视图中对两个相机可见的2D特征。然后,我们估计的基础上,在两个正交视图中提取的可见特征的隐藏的轮廓视图中的特征的坐标。最后,基于提取的特征的坐标,我们变形的3D通用模型执行所需的3D克隆建模。目前的研究证明了范围的实际应用,如人脸识别和面部动画的面部模型。

英文摘要:

Multiview 3D face modeling has attracted increasing attention recently and has become one of the potential avenues in future video systems. We aim to make more reliable and robust automatic feature extraction and natural 3D feature construction from 2D features detected on a pair of frontal and profile view face images. We propose several heuristic algorithms to minimize possible errors introduced by prevalent nonperfect orthogonal condition and noncoherent luminance. In our approach, we first extract the 2D features that are visible to both cameras in both views. Then, we estimate the coordinates of the features in the hidden profile view based on the visible features extracted in the two orthogonal views. Finally, based on the coordinates of the extracted features, we deform a 3D generic model to perform the desired 3D clone modeling. Present study proves the scope of resulted facial models for practical applications like face recognition and facial animation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑