Learning long term face aging patterns from partially dense aging databases | |
Suo, Jinli ; Chen, Xilin ; Shan, Shiguang ; Gao, Wen | |
2009 | |
英文摘要 | Studies on face aging are handicapped by lack of long term dense aging sequences for model training. To handle this problem, we propose a new face aging model, which learns long term face aging patterns from partially dense aging databases. The learning strategy is based on two assumptions: (i) short term face aging pattern is relatively simple and is possible to be learned from currently available databases; (ii) long term face aging is a continuous and smoothMarkov process. Adopting a compositional face representation, our aging algorithmlearns a function-based short term aging model from real aging sequences to infer facial parameters within a short age span. Based on the predefined smoothness criteria between two overlapping short term aging patterns, we concatenate these learned short term aging patterns to build the long term aging patterns. Both the subjective assessment and objective evaluations of synthetic aging sequences validate the effectiveness of the proposed model. ?2009 IEEE.; EI; 0 |
语种 | 英语 |
DOI标识 | 10.1109/ICCV.2009.5459181 |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/263087] ![]() |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Suo, Jinli,Chen, Xilin,Shan, Shiguang,et al. Learning long term face aging patterns from partially dense aging databases. 2009-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论