Realistic Smile Expression Recognition Using Biologically Inspired Features
| 详细信息 | 推荐本文 | |
- 作者：Cong He (1) riverho1015@gmail.com
Huiyun Mao (1)
Lianwen Jin (1) Lianwen.jin@gmail.com - 关键词：Facial expression classification – ; smile recognition – ; biologically inspired model
- 刊名：Lecture Notes in Computer Science
- 出版时间：2011
- 出版年：2011
- 期刊代码：99_0302-9743
- 类别：cp
- 卷：7106
- 期：1
- 页码：590-599
- 数据来源：sp
摘要
A robust smile recognition system could be widely used for many real-world applications. In this paper, we introduce biologically inspired model (BIM) into the building of realistic smile classification system for solving challenging realistic tasks. To improve the performance of BIM, we develop a modified BIM (MBIM), which utilizes a more efficient pooling operation and boosting feature selection. Experiments demonstrate the effectiveness of themodifications and adjustments of BIM. By testing on the challenging realistic database, GENKI, our method is proved to be superior to some other state-of-the-art smile classification algorithms.