Abstract | ||
---|---|---|
With millions of users and billions of photos, web-scale face recognition is a challenging task that demands speed, accuracy, and scalability. Most current approaches do not address and do not scale well to Internet-sized scenarios such as tagging friends or finding celebrities. Focusing on web-scale face identification, we gather an 800,000 face dataset from the Facebook social network that models real-world situations where specific faces must be recognized and unknown identities rejected. We propose a novel Linearly Approximated Sparse Representation-based Classification (LASRC) algorithm that uses linear regression to perform sample selection for @?^1-minimization, thus harnessing the speed of least-squares and the robustness of sparse solutions such as SRC. Our efficient LASRC algorithm achieves comparable performance to SRC with a 100-250 times speedup and exhibits similar recall to SVMs with much faster training. Extensive tests demonstrate our proposed approach is competitive on pair-matching verification tasks and outperforms current state-of-the-art algorithms on open-universe identification in uncontrolled, web-scale scenarios. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1016/j.cviu.2013.09.004 | Computer Vision and Image Understanding |
Keywords | Field | DocType |
open-universe identification,demands speed,face dataset,specific face,web-scale datasets,current state-of-the-art algorithm,current approach,efficient lasrc algorithm,web-scale scenario,web-scale face recognition,web-scale face identification | Data mining,Social network,Computer science,Robustness (computer science),Artificial intelligence,Speedup,Facial recognition system,Computer vision,Support vector machine,Sparse approximation,Recall,Machine learning,Scalability | Journal |
Volume | Issue | ISSN |
118, | 1 | 1077-3142 |
Citations | PageRank | References |
34 | 0.98 | 63 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Enrique G. Ortiz | 1 | 180 | 6.15 |
Brian C. Becker | 2 | 106 | 7.81 |