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
LIU Qing-yan1,2,LIU Yuan1,2
Received:
Revised:
Online:
Published:
Contact:
刘清艳1,2,刘 渊1,2
通讯作者:
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:
TP391.4
LIU Qing-yan1,2,LIU Yuan1,2. Research on improved active shape models[J]. Computer Engineering and Applications, 2009, 45(35): 192-195.
刘清艳1,2,刘 渊1,2. 一种改进主动形状模型的研究[J]. 计算机工程与应用, 2009, 45(35): 192-195.
0 / Recommend
Add to citation manager EndNote|Ris|BibTeX
URL: http://cea.ceaj.org/EN/10.3778/j.issn.1002-8331.2009.35.058
http://cea.ceaj.org/EN/Y2009/V45/I35/192