计算机应用 ›› 2010, Vol. 30 ›› Issue (10): 2705-2708.

• 模式识别 • 上一篇    下一篇

三维人脸建模中关键点的自动定位

郭瑞熊1,王成儒2,牛晓霞3,顾广华4   

  1. 1. 河北省秦皇岛市燕山大学
    2. 河北省秦皇岛市燕山大学信息科学与工程学院
    3. 燕山大学信息科学与工程学院
    4.
  • 收稿日期:2010-01-13 修回日期:2010-06-17 发布日期:2010-09-21 出版日期:2010-10-01
  • 通讯作者: 郭瑞熊
  • 基金资助:
    河北省科学技术研究与发展指导计划项目

Automatic localization of facial key-points for 3D face modeling

  • Received:2010-01-13 Revised:2010-06-17 Online:2010-09-21 Published:2010-10-01
  • Contact: Guo RuiXiong

摘要: 针对3D人脸建模形变方法中关键点的获取问题,提出一种关键点自动定位的方法。首先根据需求,确定关键点位置并进行分类;接着利用HSI空间S分量实现头部检测;再采用Harris角点检测技术,结合人脸结构特征和颜色信息,实现特征部位的提取;然后分别在正、侧面照片各特征部位,对不同类别的关键点采用不同的方法,提取相应的2D坐标;将两个角度上提取的2D坐标组合,最终得到关键点的3D坐标。实验结果表明,所提出的关键点定位方法在速度和准确性方面具有良好性能。

关键词: 3D人脸建模, 人头检测, 特征点定位, 形变模型

Abstract: In view of the key-points acquirement problem in morphable way of 3D face modeling, an automatic localization method was proposed. First of all, according to the demand, the locations of key-points were determined and classified. Secondly, by using the S component in HIS color space, the head was detected. Thirdly, combined with the structure of face features and texture, the features' parts were extracted. Then, using different methods, the 2D coordinates of the different key-points were gained at the features' parts from frontal and side photos respectively. Finally, merging the 2D coordinates from both views, the 3D coordinates of the key-points were obtained. The experimental results show that the proposed method has good performance in speed and accuracy.

Key words: 3D face modeling, head detection, features localization, morphable model

中图分类号: