An Automatic System for Smile Recognition Based on CNN and Face Detection
文献类型：会议论文
| 作者 | Song GL(宋国立) ; Zhao XG(赵新刚); Zhao YW(赵忆文); Qu DY(屈丹阳); Gao ZY(高振远); Huang Z(黄钲)
|
| 出版日期 | 2018 |
| 会议日期 | December 12-15, 2018 |
| 会议地点 | Kuala Lumpur, Malaysia |
| 关键词 | CNN Face detection Smile recognition |
| 页码 | 243-247 |
| 英文摘要 | The facial expression recognition has become one of the research focuses in recent years. Since smile is one of the most significant facial expressions, the recognition of smile can contribute to the development of the research of human facial expression recognition. In this paper, an automatic system for smile recognition is proposed. Face areas are firstly extracted from the original images. Meanwhile, on the basis of face extraction, the convolutional neural network (CNN) is trained by different optimizers. The experiments show that the highest accuracy of this system is 93.16% by RMSProp with momentum. And the maximum accuracy for face images is 92.09% by Adam optimizer while it's just 69.53% for original images, which suggests the combination of face detection and CNN can further improve the performance of the classifier. |
| 产权排序 | 1 |
| 会议录 | Proceedings of the 2018 IEEE International Conference on Robotics and Biomimetics
 |
| 会议录出版者 | IEEE |
| 会议录出版地 | New York |
| 语种 | 英语 |
| ISBN号 | 978-1-7281-0376-1 |
| WOS记录号 | WOS:000468772200038 |
| 源URL | [http://ir.sia.cn/handle/173321/24652]  |
| 专题 | 沈阳自动化研究所_机器人学研究室 |
| 通讯作者 | Song GL(宋国立) |
| 作者单位 | State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China |
| 推荐引用方式 GB/T 7714 | Song GL,Zhao XG,Zhao YW,et al. An Automatic System for Smile Recognition Based on CNN and Face Detection[C]. 见:. Kuala Lumpur, Malaysia. December 12-15, 2018. |
入库方式： OAI收割
来源：沈阳自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。