Abstract:
Use of video clips for e-learning is very limited due to the
high usage of band width. The ability to select and
retrieve relevant video clips using semantics addresses
this problem. This paper presents a Profile based Feature
Identification system for multimedia database systems
which is designed to support the use of video clips for elearning. This system is capable of storing educational
video clips with their semantics and retrieving required
video clip segments efficiently on their semantics. The
system creates profiles of presenters appearing in the
video clips based on their facial features and uses these
profiles to partition similar video clips into logical
meaningful segments. The face recognition algorithm
used by the system is based on the Principal Components
Analysis (PCA) approach. However PCA algorithm has
been modified to cope with the face recognition in video
key frames. Several improvements have been proposed to
increase the face recognition rate and the overall
performance of the system.