of the art lecture recording system such as tele-Teaching Anywhere
Solution Kit(tele-TASK).1
Fig. 1b illustrates an example of such a system which
delivers two main parts of the lecture: the main scene of lecturers
which is recorded by using a video camera and the
second which captures the desktop of the speaker’s computer
(his presentations) during the lecture through a frame
grabber tool. The key benefits of the latter one for a lecturer
is the flexibility. For the indexing, no extra synchronization
between video and slide files is required, and we do not
need to take care of the slide format. The main drawback is
that the video analysis methods may introduce errors. Our
research work mainly focus on those lecture videos produced
by using the screen grabbing method. Since two videos
are synchronized automatically during the recording
process. Therefore, the temporal scope of a complete unique
slide can be considered as a lecture segment. This way, segmenting
two-scenes lecture videos can be achieved by only
processing slide video streams, which contain most of the
visual text metadata. The extracted slide frames can provide
a visual guideline for video content navigation.