Abstract | ||
---|---|---|
For applications such as video surveillance and human computer interfaces, we propose an efficiently integrated method to detect and track faces. Various visual cues are combined with the algorithm: motion, skin color, global appearance and facial pattern detection. The ICA (independent component analysis)-SVM (support vector machine) based pattern detection is performed on the candidate region extracted by motion, color and global appearance information. Simultaneous execution of detection and short-term tracking also increases the rate and accuracy of detection. Experimental results show that our detection rate is 91% with very few false alarms running at about 4 frames per second for 640 by 480 pixel images on a Pentium IV 1 GHz. |
Year | DOI | Venue |
---|---|---|
2002 | 10.1109/ICPR.2002.1048322 | ICPR (2) |
Keywords | Field | DocType |
video signal processing,307200 pixel,learning automata,kalman filters,face recognition,integrated approach,480 pixel,640 pixel,human computer interface,motion,image segmentation,skin color,pattern matching,global appearance,facial pattern detection,independent component analysis,faces tracking,feature extraction,support vector machine,image sequences,detection rate,visual cues,ica,pattern detection,faces detection,probability,multiple face detection,video surveillance,application software,face detection,pattern analysis,skin,information analysis,frames per second,support vector | Computer vision,Facial recognition system,Object-class detection,Pattern recognition,Computer science,Feature extraction,Image segmentation,Frame rate,Artificial intelligence,Pixel,Face detection,Pattern matching | Conference |
Volume | ISSN | Citations |
2 | 1051-4651 | 10 |
PageRank | References | Authors |
0.74 | 6 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tae-Kyun Kim | 1 | 1987 | 129.30 |
Sung-uk Lee | 2 | 35 | 4.57 |
Jong Ha Lee | 3 | 33 | 3.94 |
Seok-cheol Kee | 4 | 129 | 13.94 |
Sang Ryong Kim | 5 | 143 | 12.08 |