计算机应用 ›› 2011, Vol. 31 ›› Issue (12): 3392-3394.

• 图形图像技术 • 上一篇    下一篇

基于主动形状模型算法的局部灰度模型的加权改进方法

韩玉峰1,2,王小林1   

  1. 1. 安徽工业大学 计算机学院,安徽 马鞍山 243002
    2. 安徽工业大学 数理学院,安徽 马鞍山 243002
  • 收稿日期:2011-05-23 修回日期:2011-07-20 发布日期:2011-12-12 出版日期:2011-12-01
  • 通讯作者: 韩玉峰
  • 基金资助:
    2011年安徽高校省级自然科学研究项目重点项目(人脸特征点定位方法的研究)

Weighted improvement method based on local gray-level model of active shape model

HAN Yu-feng1,2,WANG Xiao-lin1   

  1. 1. School of Computer Science, Anhui University of Technology, Ma’anshan Anhui 243002,China
    2. School of Mathematics and Physics, Anhui University of Technology, Ma’anshan Anhui 243002,China
  • Received:2011-05-23 Revised:2011-07-20 Online:2011-12-12 Published:2011-12-01
  • Contact: HAN Yu-feng

摘要: 主动形状模型(ASM)算法在对目标点搜索的过程中,只采用了标定点周围的局部灰度信息,这样往往会使灰度相似但其实微观纹理细节差别很大的两个点混为一谈,最终使算法的定位不够精确。为此,提出一种基于主动形状模型算法的局部灰度模型的加权改进方法,该算法采用一系列服从离散高斯分布的加权系数依次表示标定点法线方向上两侧的候选点是真实特征点的可能性,从而建立局部加权灰度模型。通过实验结果表明,改进算法比传统算法精度提高了6%。

关键词: 人脸特征点定位, 主动形状模型, 局部灰度模型, 高斯分布

Abstract: In the searching of ASM algorithm for target point, only surrounding local gray-level information of fixed point is adopted. Then, two points is often confused, which have both similar gray-level and widely different texture details. Consequently, the accuracy of positioning is not ensured. The paper suggests that the real feature point probability of bilateral candidate points in the normal direction decreases in turn, so Gaussian distribution is brought in to represent the probability. Thus, better candidate points in the target image can be searched and the accuracy of positioning is improved.

Key words: facial feature point positioning, Active Shape Model (ASM), local gray-level model, Gaussian distribution

中图分类号: