Loading...
Please wait, while we are loading the content...
Similar Documents
Extracting age information from locally spatially flexible patches
| Content Provider | CiteSeerX |
|---|---|
| Author | Yan, Shuicheng Liu, Ming Huang, Thomas S. |
| Description | In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP Motivated by the fact that age information can often be observed from local evidence on the human face, we con-tribute to the age estimation problem in two aspects. On the one hand, we present a new feature descriptor, called spa-tially flexible patch (SFP), which encodes the local appear-ance and position information simultaneously. SFP has the potential to alleviate the problem of insufficient samples ow-ing to that SFPs similar in appearance yet slightly different in position can still provide similar confidence for age estima-tion. One the other hand, the SFP associated with age label is modeled with Gaussian Mixture Model, and then age es-timation is conducted by maximizing the sum of likelihoods from all the SFPs associated with the hypothetic age. Exper-iments are conducted on the YAMAHA database with 8,000 face images and ages ranging from 0 to 93. Compared with the latest reported results, our new algorithm brings encour-aging reduction in mean absolute error for age estimation. |
| File Format | |
| Language | English |
| Access Restriction | Open |
| Subject Keyword | Local Appear-ance Gaussian Mixture Model Encour-aging Reduction Insufficient Sample Age Estimation Problem Similar Confidence Face Image New Feature Descriptor Mean Absolute Error Age Estimation Hypothetic Age Age Information Human Face Age Label Local Evidence Reported Result Age Estima-tion Yamaha Database Position Information Age Es-timation Flexible Patch |
| Content Type | Text |
| Resource Type | Article |
