Anthropocentric semantic information extraction from movies

Abstract

In this chapter we will describe new methods for anthropocentric semantic video analysis, and will concentrate our efforts to provide a uniform framework by which media analysis can be rendered more useful for retrieval applications as well as for human-computer interaction based application. The main idea behind anthropocentric video analysis is that a film is to be viewed as an artwork and not as a mere of frames following each others. We will show that this kind of analysis which is a straightforward approach of human perception of a movie can finally produce some interesting results of the overall annotation of a video content. "Anthropos" which is the greek word for "human" show the intent of our proposition to concentrate in humans in a movie. Humans are the most essential part of a movie and thus we track down all important features that we can get from low-level and mid-level feature algorithms such as face detection, face tracking, eye detection, visual speech recognition, 3D face reconstruction, face clustering, face verification and facial expressions extraction. All these algorithms produce results which are stored in an MPEG-7 inspired description scheme set which implements the way humans are connecting those features. Therefore as a results we have a structured information of all features that can be found for a specific human (e.g. actor). As it will be shown in this chapter this approach as a straightforward approach of human perception provides a new way of media analysis in the semantic level. © 2008 Springer-Verlag Berlin Heidelberg.