Extraction of Key Frame from News Video Using Face Recognition

With the advent of the information age and an explosion in the availability of multimedia data, news video production and its usage is growing extremely. But these require more memory and space. So in order to save space and time we need to summarize video. For this we need to perform key frame extraction into the video. This project compares with each other, the combinations of existing approaches of dimensionality reduction and different methods of clustering on face images detected from a TV news broadcast clip to perform face recognition. Key Frame extraction aims at reducing the amount of data that must be examined in order to retrieve a particular piece of information from the large database of information. The overall process includes frames extraction, removal of non-face areas, projection of the faces into a subspace and various algorithms for the subspace projection and clustering are carried out on it