• 综合性科技类中文核心期刊
    • 中国科技论文统计源期刊
    • 中国科学引文数据库来源期刊
    • 中国学术期刊文摘数据库(核心版)来源期刊
    • 中国学术期刊综合评价数据库来源期刊

基于HASM的口形特征点定位

孙艳丰, 陈贺, 贾熹滨, 李敬华

孙艳丰, 陈贺, 贾熹滨, 李敬华. 基于HASM的口形特征点定位[J]. 北京工业大学学报, 2007, 33(7): 726-730.
引用本文: 孙艳丰, 陈贺, 贾熹滨, 李敬华. 基于HASM的口形特征点定位[J]. 北京工业大学学报, 2007, 33(7): 726-730.
SUN Yan-feng, CHEN He, JIA Xi-bin, LI Jing-hua. Oral Features Localization Based on HASM[J]. Journal of Beijing University of Technology, 2007, 33(7): 726-730.
Citation: SUN Yan-feng, CHEN He, JIA Xi-bin, LI Jing-hua. Oral Features Localization Based on HASM[J]. Journal of Beijing University of Technology, 2007, 33(7): 726-730.

基于HASM的口形特征点定位

基金项目: 

国家自然科学基金(60375007)

北京市自然科学基金(40410031).

详细信息
    作者简介:

    孙艳丰(1964—),女,黑龙江齐齐哈尔人,教授.

  • 中图分类号: TP391

Oral Features Localization Based on HASM

  • 摘要: 针对口形特征点定位的准确性问题,提出一种基于HASM(hierarchical active shape model)的口形轮廓定位方法,采用不等步长、不等角度建模策略和口形聚类策略,构建局部纹理模型作为特征点搜索依据,并利用马氏距离选取最佳定位点.试验结果表明,HASM模型的口形特征点定位方法使内唇定位和闭口口形定位的准确率达到90%以上.
    Abstract: The principal idea of this research for visual speech synthesis realism is that oral features localization provides the precise geometrical information for oral images of speech sound. In this research, Hierarchical Active Shape Model (HASM) is used as local texture model. In the structuring local texture model, the local texture model is the main clue. The optimal oral features localizations are decided by Mahalanobis distance. This research utilizes variable step strategy, variable angle strategy and oral images clustering strategy to greatly improve the accuracy and efficiency of inter lip localization and special lip shape. The result shows that the accuracy and efficiency are up to 90 %.
计量
  • 文章访问数:  11
  • HTML全文浏览量:  0
  • PDF下载量:  8
  • 被引次数: 0
出版历程
  • 收稿日期:  2006-03-01
  • 网络出版日期:  2022-12-29

目录

    /

    返回文章
    返回