S. C. Premaratne, D. D. Karunaratna and K. P. Hewagamage
University of Colombo School of Computing, Sri Lanka

The focus of this paper is on video based educational material where presenters deliver educational content. We employ a set of tools developed by us to segment video clips semantically into shots by using low level features. Then we identify those segments where presenters appear and extract the relevant information in key frames. This information is then encoded and compared with a database of similarly encoded key frames. The feature information in video frames of a face is represented as an eigenvector which is considered as a profile of a particular person. In our research, we have designed a multimodal multimedia database system to support content-based indexing, archiving, retrieval and on-demand delivery of audiovisual content in an e-learning. In this system, a feature selection and a feature extraction sub-system have been used to construct presenter profiles. The feature extraction process transforms the video key-frame data into a multidimensional feature space as feature vectors. These profiles are then used to construct an index over the video clips to support efficient retrieval of video shots.

Once the profiles for the presenters are created, semantic annotation process is used to annotate meta-data with the video shots. Majority of metadata authorization procedures reported in the literature are based on the video’s physical features such as colour, motion, or brightness data. However the system uses profiles to annotate semantics to video clips automatically. The system also provides features to extend the metadata associated with profiles later at any time as they become available. The annotated metadata is saved in a XML database. We use XML databases for metadata because it allows both multimedia educational objects and metadata to be stored and handled uniformly by using the same techniques.

We address one of the main problems identified in profile construction and propose a novel approach to create the profiles by introducing a profile normalization algorithm. In particular, this method places more effort on solving the profile overlapping problem by using certain parameters. The effectiveness of the normalizing algorithm was tested by comparing Total Error Rate (TER) when the normalizing process is avoided versus together with the normalizing method. The results show that the insertion of profile normalizing method reduces TER by 38% to 19%. Improving these techniques for lecture videos has significant educational and social benefits.

Keywords: eigenfaces, eigenvectors, face recognition, image normalization, principal component analysis, e-learning.

Download FULL PAPER

Back to Contents