Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (35): 192-195.DOI: 10.3778/j.issn.1002-8331.2009.35.058

• 图形、图像、模式识别 • Previous Articles     Next Articles

Research on improved active shape models

LIU Qing-yan1,2,LIU Yuan1,2   

  1. 1.School of Information Technology,Jiangnan University,Wuxi,Jiangsu 214122,China
    2.Creative Digital Media Center,Jiangnan University,Wuxi,Jiangsu 214122,China
  • Received:2008-07-20 Revised:2008-11-17 Online:2009-12-11 Published:2009-12-11
  • Contact: LIU Qing-yan

一种改进主动形状模型的研究

刘清艳1,2,刘 渊1,2   

  1. 1.江南大学 信息工程学院,江苏 无锡 214122
    2.江南大学 数字媒体创意中心,江苏 无锡 214122
  • 通讯作者: 刘清艳

Abstract: Active Shape Model(ASM) is one of powerful tools for feature extraction.A new method to construct local appearance model is developed using the information of neighbour landmark points.This improved method is evaluated on ORL and JAFFE face database,and the experimental results show that the improved ASM improves the accuracy of facial features extraction.

摘要: 主动形状模型(Active Shape Model,ASM)是一种较为流行的用于特征定位的统计学形状模型,主要应用于灰度图像中物体的跟踪与定位。在传统主动形状模型基础上,研究了一种构建局部纹理模型的新方法。该模型充分利用特征点之间的联系,构建加权模型。在ORL人脸数据库、JAFFE人脸数据库中进行特征定位实验,并进行了ASM性能分析。结果表明,改进ASM方法提高了搜索速度与特征点定位的精度。

CLC Number: