Abstract | ||
---|---|---|
This paper presents a local face recognition algorithm that is based on independent component analysis (ICA) and the nearest feature line (NFL). First, we separate a face image into several facial components. Then, we extract feature through combination of principal component analysis (PCA) and ICA; in the step of recognition, we first get each part of distance by NFL, then we calculate the synthetical distance by combining different parts. Compared with holistic image representation, this method has many advantages, such as a much higher recognition rate, more stable and flexible in practice. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1007/978-3-540-28647-9_155 | ADVANCES IN NEURAL NETWORKS - ISNN 2004, PT 1 |
Keywords | Field | DocType |
face recognition,principal component analysis,independent component analysis | Facial recognition system,Eigenface,Pattern recognition,Computer science,Image representation,Speech recognition,Artificial intelligence,Independent component analysis,Machine learning,Principal component analysis | Conference |
Volume | ISSN | Citations |
3173 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 7 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yisong Ye | 1 | 0 | 0.34 |
Yan Wu | 2 | 20 | 4.50 |
Mingliang Sun | 3 | 9 | 1.05 |
Mingxi Jin | 4 | 0 | 0.68 |