Abstract | ||
---|---|---|
We consider the problem of automatic identification of faces in videos such as movies, given a dictionary of known faces from a public or an alternate database. This has applications in video indexing, content based search, surveillance, and real time recognition on wearable computers. We propose a two stage approach for this problem. First, we recognize the faces in a video using a sparse representation framework using l1-minimization and select a few key-frames based on a robust confidence measure. We then use transductive learning to propagate the labels from the key-frames to the remaining frames by incorporating constraints simultaneously in temporal and feature spaces. This is in contrast to some of the previous approaches where every test frame/track is identified independently, ignoring the correlation between the faces in video tracks. Having a few key frames belonging to few subjects for label propagation rather than a large dictionary of actors reduces the amount of confusion. We evaluate the performance of our algorithm on Movie Trailer face dataset and five movie clips, and achieve a significant improvement in labeling accuracy compared to previous approaches. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/ICPR.2014.61 | Pattern Recognition |
Keywords | Field | DocType |
face recognition,image representation,minimisation,video databases,video signal processing,Movie Trailer face dataset,alternate database,automatic identification,content based search,face recognition,feature spaces,key-frames,l1-minimization,label propagation,labeling accuracy,public database,real time recognition,sparse representation framework,surveillance,temporal spaces,two stage approach,video indexing,video tracks,wearable computers | Transduction (machine learning),Facial recognition system,Computer vision,Confusion,Pattern recognition,Label propagation,Computer science,Wearable computer,Sparse approximation,Search engine indexing,Artificial intelligence,Face detection | Conference |
ISSN | Citations | PageRank |
1051-4651 | 2 | 0.37 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Vijay Kumar | 1 | 36 | 3.83 |
Anoop M. Namboodiri | 2 | 255 | 26.36 |
Jawahar, C.V. | 3 | 233 | 21.21 |