基于HASM的口形特征点定位  

Oral Features Localization Based on HASM

作　　者：孙艳丰[1] 陈贺[1] 贾熹滨[1] 李敬华[1] 

机构地区：[1]北京工业大学多媒体与智能软件技术北京市重点实验室,北京100022

出　　处：《北京工业大学学报》2007年第7期726-730,共5页Journal of Beijing University of Technology

基　　金：国家自然科学基金(60375007);北京市自然科学基金(40410031).

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．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 %.

关 键 词：特征点定位 主动形状模型 局部纹理模型 马氏距离 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]