Gaussian Mixture Model Mapping in face recognition
文献类型：会议论文
| 作者 | Zhou, Xiang; Zhoe, Xi; Liu, Yanfei |
| 出版日期 | 2013 |
| 会议日期 | October 26, 2013 - October 28, 2013 |
| 会议地点 | Jiuzhai, China |
| DOI | 10.1109/ICCPS.2013.6893566 |
| 页码 | 423-427 |
| 通讯作者 | Zhou, Xiang |
| 英文摘要 | It is difficult to appropriately measure the similarity between human faces under different settings, e.g. pose, illumination, expression and shield. In this paper, a new method called Gaussian Mixture Model Mapping (G3M) is proposed to solve the difficulties. The distribution of faces is divided into many Gaussian functions to cover different settings. A generic identity data set, in which each identity contains multiple images with large intra-personal variation, is adopted to construct the Gaussian mixture model. When considering two faces under significantly different settings, we can judge their feature space distribution by Gaussian mixture model and normalize them into standard space. And then, the normalized faces can be compared by feature in standard space. Finally, we use Multi-pie database to compute the spline functions and test this mode, and LFW is also considered. This method can substantially improve the performance in our test experiment. © 2013 IEEE. |
| 会议录 | 2013 Joint Conference of International Conference on Computational Problem-Solving and International High Speed Intelligent Communication Forum, ICCP and HSIC 2013
 |
| 语种 | 英语 |
| 源URL | [http://119.78.100.138/handle/2HOD01W0/4721]  |
| 专题 | 中国科学院重庆绿色智能技术研究院 |
| 作者单位 | Automated Reasoning and Cognition Key Laboratory of Chongqing, Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences, Chongqing, China |
| 推荐引用方式 GB/T 7714 | Zhou, Xiang,Zhoe, Xi,Liu, Yanfei. Gaussian Mixture Model Mapping in face recognition[C]. 见:. Jiuzhai, China. October 26, 2013 - October 28, 2013. |
入库方式： OAI收割
来源：重庆绿色智能技术研究院
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。