Name
Title | ||
|---|---|---|
Facial model fitting based on perturbation learning and it's evaluation on challenging real-world diversities images |
Abstract | ||
|---|---|---|
We present a robust and efficient framework for facial shape model fitting. Traditional model fitting approaches are sensitive to noise resulting from scene variations due to lighting, facial expressions, poses, etc., and tend to spend substantial computational effort due to heuristic searching algorithms. Our work distinguishes itself from conventional approaches by employing (a) non-uniform sampling features unified by the shape model that affords robustness, and (b) regression analysis between observed features and underlying shape parameters that allow for efficient model update. We demonstrate the effectiveness of our framework by evaluating its performance on several new and existing datasets including challenging real-world diversities. Significantly higher localization accuracy and speedup factors of 15 have been observed comparing with the traditional approach. |
Year | DOI | Venue |
|---|---|---|
2012 | 10.1007/978-3-642-33863-2_16 | ECCV Workshops (1) |
Keywords | Field | DocType |
traditional approach,shape model,underlying shape parameter,facial shape model fitting,observed feature,facial expression,efficient model update,fitting approach,efficient framework,traditional model,real-world diversities image,perturbation learning,facial model fitting | Search algorithm,Computer science,Canonical correlation,Robustness (computer science),Artificial intelligence,Speedup,Computer vision,Heuristic,Pattern recognition,Facial expression,Sampling (statistics),Relevance vector machine,Machine learning | Conference |
Volume | ISSN | Citations |
7583 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 15 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Koichi Kinoshita | 1 | 25 | 2.82 |
| Yoshinori Konishi | 2 | 18 | 1.55 |
| Masato Kawade | 3 | 492 | 41.38 |
| Hiroshi Murase | 4 | 1927 | 523.30 |