摘要
针对传统的ASM(主动形状模型)与AAM(主动外观模型)方法的缺陷与不足,提出了一种改进的方法。在改进算法中,将局部特征模型和全局纹理模型有机结合,使其融合传统的主动形状局部模型、全局纹理形状约束和参数优化过程。实验结果表明,改进算法的定位能力更加健壮,并具有更高的准确性。
In view of the defects and shortcomings of traditional Active Shape Model (ASM) and Active Appearance Model (AAM) methods this paper proposes an improved algorithm. This improved algorithm combines local feature model with global texture model organically. So that it mixes local ASM, the global texture constrained shape model and the process of parameter optimization together. The experimental results indicate that the improved algorithm has a bigger enhancement in accuracy and robustness of localization capability.
出处
《电子技术(上海)》
2009年第10期66-67,55,共3页
Electronic Technology
关键词
主动形状模型
主动外观模型
特征点定位
Active Shape Model
Active Appearance Model
feature points location