Appeal No. 2002-1550
Application No. 09/158,884
subwindows and the valley counts of the valleys within the subwindows” and this would
include a classification indirectly based and/or not exclusively based on the greatest
of the peak and valley counts. Clearly, as pointed out by the examiner, since a
parameter Pi is assigned to each subwindow, indicative of the larger number of either
peak counts or valley counts within that subwindow (referring to column 6, lines 4-27,
column 8, lines 10-20, column 18, lines 15-31, column 19, lines 8-22 and column 20,
lines 39-52), and the classification of an object pixel is determined by counting the
number of subwindows which satisfy P>Pth is greater than a predetermined threshold
Bth (column 7, lines 9-16), the largest value P is used in some manner to determine the
number of subwindows and, therefore, the classification of the pixel since all Pi of the
subwindows are compared to the threshold Pth to find the number of the subwindows
satisfying the threshold (answer-page 5). Thus, Ohuchi discloses a classification
device that determines a class of the pixel under consideration based on the greatest of
the peak counts of the peaks within the subwindows and the valley counts of the valleys
within the subwindows, as claimed.
While appellants argue, at page 12 of the principal brief, that Ohuchi’s
classification device does not base the classification on the peak and valley count
“of any particular block” when it classifies that pixel, we do not find such language in
claim 1. Accordingly, the argument is immaterial. Similarly, because the language of
5
Page: Previous 1 2 3 4 5 6 7 8 9 Next
Last modified: November 3, 2007