An approach for behavior analysis using correlation spectral embedding method
文献类型:期刊论文
作者 | Jain, Deepak Kumar1; Jain, Neha2; Kumar, Shishir2; Kumar, Amit2; Kumar, Raj3; Wang, Haoxiang4,5 |
刊名 | JOURNAL OF COMPUTATIONAL SCIENCE
![]() |
出版日期 | 2018-03-01 |
卷号 | 25页码:397-405 |
关键词 | Correlation Encoding Embedding approach |
ISSN号 | 1877-7503 |
DOI | 10.1016/j.jocs.2017.07.011 |
通讯作者 | Jain, Deepak Kumar(deepak@cripac.ia.ac.cn) |
英文摘要 | Automatic identification of various facial movements and expressions with high recognition value is important for human computer interaction as the facial behavior of a human can be treated as an important factor for information representation as well as communication. A high deviation of human appearance and existence of noisy contextual background makes the human pose analysis is hard to achieve. A number of basic factors such as cluttered background, occlusion, and camera movement and illumination variations degrade the image quality resulting in poor performance for identifying different facial expressions. Moreover, the identification of the automatic feature detection in facial behavior requires high degree of correlation between the training and test images. Our proposed work tries to address the mentioned problems and resolve to some extent. In this methodology, a Decision-based Spectral Embedding approach combining appearance and geometry based features for head pose estimation and facial expression recognition by minimizing the objective function which leads to selection of optimal set of fiducial points. The method preserves the local information from different facial views for mapping neighboring input to its corresponding output, resulting in low dimensional representation for encoding the relationships of the data. The proposed methodology is validated with benchmark datasets for analyzing the performance of recognition of facial behavior. (C) 2017 Elsevier B.V. All rights reserved. |
WOS关键词 | ACTION RECOGNITION |
WOS研究方向 | Computer Science |
语种 | 英语 |
WOS记录号 | WOS:000431933300037 |
出版者 | ELSEVIER SCIENCE BV |
源URL | [http://ir.ia.ac.cn/handle/173211/28166] ![]() |
专题 | 离退休人员 |
通讯作者 | Jain, Deepak Kumar |
作者单位 | 1.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 2.Jaypee Univ Engn & Technol, Dept Comp Sci & Engn, Guna, India 3.GGSIPU, SGTBIM&IT, Delhi, India 4.Cornell Univ, Dept ECE, Ithaca, NY 14853 USA 5.GoPercept Lab, R&D Ctr, Ithaca, NY USA |
推荐引用方式 GB/T 7714 | Jain, Deepak Kumar,Jain, Neha,Kumar, Shishir,et al. An approach for behavior analysis using correlation spectral embedding method[J]. JOURNAL OF COMPUTATIONAL SCIENCE,2018,25:397-405. |
APA | Jain, Deepak Kumar,Jain, Neha,Kumar, Shishir,Kumar, Amit,Kumar, Raj,&Wang, Haoxiang.(2018).An approach for behavior analysis using correlation spectral embedding method.JOURNAL OF COMPUTATIONAL SCIENCE,25,397-405. |
MLA | Jain, Deepak Kumar,et al."An approach for behavior analysis using correlation spectral embedding method".JOURNAL OF COMPUTATIONAL SCIENCE 25(2018):397-405. |
入库方式: OAI收割
来源: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。