首页 | 本学科首页   官方微博 | 高级检索  
     

基于Canny算法与几何性质的三维人脸分割方法
引用本文:林增刚,张艳宁,郭哲. 基于Canny算法与几何性质的三维人脸分割方法[J]. 中国体视学与图像分析, 2009, 0(2): 192-196
作者姓名:林增刚  张艳宁  郭哲
作者单位:西北工业大学计算机学院,陕西省语音与图像信息处理重点实验室,陕西西安710072
摘    要:
三维人脸分割技术具有重要的实用意义,其结果直接影响到后续的配准、识别等处理结果的精度。本文采用映射图像边缘检测技术、曲面空间几何性质以及人脸生理特性相结合的方法进行三维人脸分割,取得了较好的效果。在实际三维人脸数据库上的实验结果证明了本文的有效性和高效性。

关 键 词:Canny算子  三维映射  自然连接  三维分割

3D face segmentation method based on Canny algorithm and geometry properties
LIN Zenggang,ZHANG Yanning,GUO Zhe. 3D face segmentation method based on Canny algorithm and geometry properties[J]. Chinese Journal of Stereology and Image Analysis, 2009, 0(2): 192-196
Authors:LIN Zenggang  ZHANG Yanning  GUO Zhe
Affiliation:(Shaanxi Key Laboratory of Speech and Image Information Processing, College of Computer Science, Northwestern Polytechnical University, Xi' An 710072, China)
Abstract:
It is important to develop a 3D face segment modal, since its result affects the accuracy of reg- istration and recognition in 3D information processing. This paper offers a method, using the image edge detection technique, 3D surface geometry properties and physiological characteristics for parting 3D face model. The Experimental results in practice of this actual 3D face database demonstrate the availability and efficiency of this method.
Keywords:Canny algorithm  3D mapping  natural connection  3D segmentation  human face
本文献已被 维普 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号