Abstract | ||
---|---|---|
Facial feature detection is a well-studied field. Efficient facial feature detection is significant in face analysis based applications, especially on mobile devices. Balance between accuracy and time efficiency is a practical problem in real time applications. This paper aims at proposing a real-time and accurate algorithm for facial feature detection. It is based on the assumption that classifiers may improve performance by limiting searching region. We propose a simplified Active Shape Model (ASM) to speed up such searching process. To ensure accuracy, several facial feature detectors are compared, such as the Adaboost classifiers with the Haar-feature, and the random forest classifiers. Since the simplified ASM provides a good constraint to different facial features, the detected results are promoted as well. We also design multiple experiments to verify our hypothesis by varying searching region. Experiments on MBGC databases prove the effect of the proposed simplified ASM model (sASM). © Springer International Publishing 2013. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1007/978-3-319-02961-0_11 | CCBR |
Keywords | Field | DocType |
adaboost,asm,facial feature detection,random forest | Active shape model,AdaBoost,Feature detection,Pattern recognition,Computer science,Mobile device,Artificial intelligence,Random forest,Limiting,Face analysis,Speedup | Conference |
Volume | Issue | ISSN |
8232 LNCS | null | 16113349 |
Citations | PageRank | References |
0 | 0.34 | 15 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wei Jiang | 1 | 220 | 22.56 |
Yuchun Fang | 2 | 139 | 21.90 |
Yonghua Zhu | 3 | 6 | 4.15 |