Appeal No. 2006-1591
Application No. 09/866,394
column 2, lines 1-24; this is further shown in Figure 3), wherein the representative images
include at least one of the first image in each family histogram, the most meaningful image in
each superhistogram, a randomly chosen image and an image that is closest to the cluster center
(the representative frame image can be taken from the temporally medial scene in the set or from
one of the frames of the longest scene in the set of related scenes) (Wang et al.: column 3, lines
37-66)” (final rejection, page 3). In view of the teachings of Dimitrova and Wang, the examiner
concluded (final rejection, pages 3 and 4) “[i]t would have been obvious to one of ordinary skill
in the art . . . to modify the visual summary controller capable of extracting frame signatures
from keyframes to create superhistograms of Dimitrova et al., to include the further step of
selecting representative keyframes from those superhistograms and using the representative
keyframe images to create a compact visual summary, taught by Wang et al.”
Appellants agree with the examiner’s findings concerning the teachings of Dimitrova
(brief, page 9). On the other hand, appellants disagree with the examiner’s findings concerning
Wang because appellants are of the opinion that Wang describes temporal ordering of frames
whereas the disclosed invention is based on non-temporal ordering of frames (brief, pages 11, 16
and 18). Based upon this difference, appellants argue that Wang fails to describe representative
images that include at least one of “the most meaningful image in each superhistogram” or “an
image that is closest to the cluster center.”
In reply to the appellants’ temporal versus non-temporal argument (answer, page 8), the
4
Page: Previous 1 2 3 4 5 6 7 8 Next
Last modified: November 3, 2007