| 基于改进的ASM和AAM的面部特征定位算法 |
| |
| 引用本文： | 李鹏. 基于改进的ASM和AAM的面部特征定位算法[J]. 电子技术, 2009, 0(10): 66-67 |
| |
| 作者姓名： | 李鹏 |
| |
| 作者单位： | 中国科学技术大学,模式识别与智能系统实验室;中国科学技术大学,自动化系 |
| |
| 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。
|
| 关 键 词： | 主动形状模型 主动外观模型 特征点定位 |
Facial Feature Localization Algorithm Based on Improved ASM and AAM |
| |
| Li Peng. Facial Feature Localization Algorithm Based on Improved ASM and AAM[J]. Electronic Technology, 2009, 0(10): 66-67 |
| |
| Authors: | Li Peng |
| |
| Affiliation: | Li Peng1,2 (1. Lab of Pattern Recognition and Intelligent System,University of Science and Technology of China. 2. Department of Automation,University of Science and Technology of China) |
| |
| Abstract: | 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 ca... |
| |
| Keywords: | Active Shape Model Active Appearance Model feature points location |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
