Name
Title | ||
|---|---|---|
A Failure-Aware Explicit Shape Regression Model for Facial Landmark Detection in Video |
Abstract | ||
|---|---|---|
Facial landmark detection is fundamental for various face-related applications such as interactive avatars on mobile devices. Awareness of detection failure is critical for practical applications because even occasional failures to detect facial landmarks lead to bad user experience. This letter proposes a fast and robust AdaBoost Based Cascade Detector (ABCD) for discerning failures from shape regression in video on mobile devices. A vector of randomly sampled pixel intensities near facial landmarks is taken as the input feature for AdaBoost classifiers. Several AdaBoost classifiers are cascaded together for robustness, computational efficiency and to augment the theoretical number of false samples in training. With this failure detector, the correctly estimated shape of the previous frame can be utilized in the next frame for initialization, which not only improves the regression accuracy but also saves on face searching time. ABCD is incorporated into a recently proposed facial landmark detection algorithm Face Alignment by Explicit Shape Regression (FAESR). Experiments on videos show that failure awareness powered FAESR yields an accurate and automatic facial landmark detection with very low computational costs, which is suitable for real time application on mobile devices. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/LSP.2013.2295231 | IEEE Signal Process. Lett. |
Keywords | Field | DocType |
mobile devices,facial landmark detection,video signal processing,face recognition,failure detection,learning (artificial intelligence),regression analysis,computational efficiency,vector,pixel intensities,adaboost based cascade detector,faesr,facial landmark detection algorithm,failure analysis,very low costs,real time application,face alignment by explicit shape regression,abcd,failure-aware explicit shape regression model,interactive avatars,learning artificial intelligence | Computer vision,Facial recognition system,AdaBoost,Pattern recognition,Computer science,Robustness (computer science),Mobile device,Artificial intelligence,Pixel,Initialization,Landmark,Detector | Journal |
Volume | Issue | ISSN |
21 | 2 | 1070-9908 |
Citations | PageRank | References |
0 | 0.34 | 8 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Mei-qing Zhang | 1 | 4 | 2.14 |
| Linmi Tao | 2 | 190 | 21.54 |
| Yin Zheng | 3 | 139 | 13.14 |
| Yangzhou Du | 4 | 169 | 13.85 |