BROWSE
Detail
Conference Paper
A Gender Classification Method using the External Features
Cited - time in 
Share 
Share
- Authors
- Ho Sub Yoon, Young Woo Yoon, Jae Yeon Lee
- Issue Date
- 2009-10
- Citation
- International Conference on Ubiquitous Robots and Ambient Intelligence (URAI) 2009, pp.1-4
- Publisher
- IEEE
- Language
- English
- Type
- Conference Paper
- Abstract
- This paper presents a gender classification method using external gender features taken from facial images. There have been a number of studies that have performed gender classification using internal features, such as skin colour, wrinkle textures, shape features and so on, from human faces. Even if internal features have dominant information for gender classification, but for the case of people aged 1-25 years and over 60 years, the hairstyle is an additional feature as external features for gender classification. Often, occlusion from hairstyles, for instance, renders useful information gathering difficult if not impossible. In our approach, we adapt the active appearance model fitting method to precisely detect facial features.The test results indicate that external features are very useful for gender classification.
- KSP Keywords
- 25 years, 60 years, Active Appearance Model(AAM), Classification method, Facial image, Fitting method, Information Gathering, Skin Colour, facial features, gender classification, model fitting