首页 | 本学科首页   官方微博 | 高级检索  
     

服装人台建模中的视觉图像人体轮廓细化提取
引用本文:刘正东,王颖,高鹏.服装人台建模中的视觉图像人体轮廓细化提取[J].计算机工程与应用,2007,43(16):246-248.
作者姓名:刘正东  王颖  高鹏
作者单位:1.北京服装学院 计算机中心,北京 100029 2.新疆哈密水文水资源勘测局,新疆 哈密 839000
基金项目:北京市人才强校计划项目
摘    要:在个性化的服装人体三维图像测量技术中,人体边界识别需要得到准确的单像素级细化轮廓。在综合采用多尺度小波变换进行图像灰度的阶跃型突变点检测基础上,对小波模极大值的直方图均化处理以自适应地选取双阈值,通过抑制非极大值点对边缘线细化,并利用双阈值跟踪连接边缘点,从而得到单像素级的人体轮廓图像。对人台图像的实验证明了算法的可行性和有效性。

关 键 词:小波变换  边缘检测  服装人体建模
文章编号:1002-8331(2007)16-0246-03
修稿时间:2006-10

Single pixel figure detection method for garment model measurement
LIU Zheng-dong,WANG Ying,GAO Peng.Single pixel figure detection method for garment model measurement[J].Computer Engineering and Applications,2007,43(16):246-248.
Authors:LIU Zheng-dong  WANG Ying  GAO Peng
Affiliation:1.Computer Center,Beijing University of Clothing Technology,Beijing 100029,China 2.Hami Survey Bureau of Hydrology and Water Resource,Hami,Sinkiang 839000,China
Abstract:Single pixel edges or figure are needed for border recognition in the field of 3D garment human body modeling.Integration of multi-scale plays an important role in step-form edge detection used by wavelet transform.In this paper,a method was applied to determine the double thresholds adaptively based on the histogram of the local maxima.Then, by restraint of local nomaxima to further edge thinning,and linking edge points to attack edge discontinuity using the double thresholds,the suitable human figure image can be detected.The experimental results showed this algorithm is feasible and effective.
Keywords:wavelet transform  edge detection  garment human body modeling
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《计算机工程与应用》浏览原始摘要信息
点击此处可从《计算机工程与应用》下载全文
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