A Bag-of-Feature Model for Video Semantic Annotation

Multimedia data of huge amount gets involved into people's daily life, bringing us a very important issue of efficiently managing video collections. Semantic content based on video retrieval is most effective for finding information and actual application. Of the researches of video retrieval, Bag-of-features (BoF) deriving from local key points has recently appeared promising for visual classification. This paper presents a method of video semantic annotation based on BoF. First, video clips are segmented into shots and shot key frames are extracted. Then it constructs a visual vocabulary to describe BoF through the clustering of key point features. Finally, the key frame is described as a feature vector according to the presence or count of each visual word. The feature vector forms the classifier under Support Vector Machines (SVM) for semantic annotation. We test performance of BoF on movie video and TRECVID-2007 datasets. Our experiment generates competitive performance compared to the state-of-the-art techniques.