Abstract | ||
---|---|---|
This paper presents efficient methods to address the problem of discriminating between five facial orientations. We present the most efficient methods for this task to date, which can accurately discriminate between five facial orientations with approximately 92% accuracy using fewer than 30 pixel comparisons and greater than 99% accuracy using 150 pixel comparisons. We achieve these rates by using a boosting method to select from a large set of extremely simple features. Comparisons to other methods are given. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1109/ICIP.2004.1418823 | Image Processing, 2004. ICIP '04. 2004 International Conference |
Keywords | Field | DocType |
face recognition,image classification,learning (artificial intelligence),boosting method,classifier training,face detection,face orientation discrimination,image classification,live facial orientation,pixel comparisons | Facial recognition system,Computer vision,Pattern recognition,Three-dimensional face recognition,Computer science,Boosting (machine learning),Artificial intelligence,Pixel,Simple Features,Face detection,Contextual image classification | Conference |
Volume | ISSN | ISBN |
1 | 1522-4880 | 0-7803-8554-3 |
Citations | PageRank | References |
22 | 1.82 | 5 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shumeet Baluja | 1 | 4053 | 728.83 |
Mehran Sahami | 2 | 4138 | 556.74 |
Henry A. Rowley | 3 | 2724 | 479.65 |