Abstract | ||
---|---|---|
A class of sparse regularization functions is considered for the developing sparse classifiers for determining facial gender. The sparse classification method aims to both select the most important features and maximize the classification margin, in a manner similar to support vector machines. An efficient process for directly calculating the complete set of optimal, sparse classifiers is developed. A single classification hyper-plane, which maximizes posterior probability of describing training data, is then efficiently selected. The classifier is tested on a Japanese gender-divided ensemble, described via a collection of appearance models. Performance is comparable with a linear SVM, and allows effective manipulation of apparent gender. |
Year | DOI | Venue |
---|---|---|
2004 | 10.1109/AFGR.2004.1301531 | FGR |
Keywords | Field | DocType |
support vector machine,support vector machines,robustness,face recognition,image processing,training data,computer vision,control engineering,posterior probability,testing,mathematics,probability,image classification,parameter estimation | Structured support vector machine,Bag-of-words model in computer vision,Pattern recognition,Computer science,Sparse approximation,Support vector machine,Posterior probability,Artificial intelligence,Relevance vector machine,Contextual image classification,Linear classifier,Machine learning | Conference |
ISBN | Citations | PageRank |
0-7695-2122-3 | 14 | 1.01 |
References | Authors | |
9 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nicholas Costen | 1 | 228 | 28.42 |
Martin Brown | 2 | 14 | 1.01 |
Shigeru Akamatsu | 3 | 1623 | 138.71 |