Name
Abstract | ||
|---|---|---|
Computer vision based gender classification is an interesting and challenging research topic in visual surveillance and human-computer interaction systems. In this paper, based on the results of psychophysics and neurophysiology studies that both local and global information is crucial for the image perception, we present an effective global-local features fusion (GLFF) method for gender classification. First, the global features are extracted based on active appearance models (AAM) and the local features are extracted by LBP operator. Second, the global features and local features are fused by sequent selection for gender classification. Third, gender is predicted based on the selected features via support vector machines (SVM). The experimental results show that the proposed local-global information combination scheme could significantly improve the gender classification accuracy obtained by either local or global features, leading to promising performance. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1007/978-3-642-25449-9_27 | CCBR |
Keywords | Field | DocType |
global information,gender classification,global-local features fusion,global feature,computer vision,lbp operator,active appearance model,proposed local-global information combination,gender classification accuracy,challenging research topic,local feature | Interaction systems,Pattern recognition,Computer science,Support vector machine,Fusion,Active appearance model,Operator (computer programming),Artificial intelligence,Sequent,Psychophysics,Perception | Conference |
Volume | ISSN | Citations |
7098 | 0302-9743 | 6 |
PageRank | References | Authors |
0.43 | 19 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Wankou Yang | 1 | 535 | 34.68 |
| Cuixian Chen | 2 | 53 | 6.38 |
| Karl Ricanek | 3 | 165 | 18.65 |
| Changyin Sun | 4 | 2002 | 157.17 |