Demographic classification using image components

摘要: The present invention includes a system and method for automatically extracting the demographic information from images. detects face in an image, locates different components, extracts component features, then classifies components to identify age, gender, or ethnicity of person(s) image. Using classification gives better results as compared currently known techniques. Moreover, described technique can be used extract more robust manner than methods, environments where high degree variability size, shape, color, texture, pose, occlusion exists. This also performs classifier fusion using Data Level Multi-level fusing various classifiers. Besides use automated data collection wherein given necessary facial data, category person is determined automatically, could targeting advertisements, surveillance, human computer interaction, security enhancements, immersive games improving user interfaces based on information.