EIGENBODY: ANALYSIS OF BODY SHAPE FOR GENDER FROM NOISY IMAGES

摘要

We present an analysis of full body images for gender classification using Principal Component Analysis (PCA). This has been widely used in the past for gender classification of faces and we show that similar techniques can be applied to the full body domain. Using Linear Discriminate Analysis (LDA) we are able to identify the key PCA components which encode information related to gender. The paper confirms that intuitive thoughts about what properties of the human body are important for gender classification, can be effectively represented in a small number of key components and that eigenpeople reproduced using just these key components can be visually classified by gender to a large extent.