Extraction method of an interest region for multimedia mobile users
Disclosed is a method for extracting a region-of-interest of a user in a multimedia mobile terminal. The method includes: setting a search region in an input picture input to the multimedia mobile terminal on a screen picture-to-screen picture basis, and extracting a group of boundary of a region-of-interest based on a brightness difference between the set search region and an environment around the set search region; determining boundary coordinates of the region-of-interest through learning during a predetermined frame among the extracted group of boundary coordinate candidates; and enlarging the region-of-interest having the determined boundary coordinates, and displaying the enlarged region-of-interest. As a result, a region the user is most interested in or pays more attention to than other regions on a screen is automatically extracted. Accordingly, it is possible for users to view pictures in such an efficient manner as to provide the users with an even better experience and understanding during viewing.
1. A method for extracting a region-of-interest of a user in a multimedia mobile terminal, the method comprising the steps of:
setting a search region in an input picture input to the multimedia mobile terminal on a screen picture-to-screen picture basis, and extracting a group of boundary coordinate candidates of a region-of-interest based on a brightness difference between the set search region and an environment around the set search region;
determining, from the extracted group of boundary coordinate candidates, boundary coordinates of the region-of-interest through learning during a predetermined number of frames; and
enlarging the region-of-interest having the determined boundary coordinates, and displaying the enlarged region-of-interest.
2. The method as claimed in claim 1 , wherein the step of extracting group of boundary of a region-of-interest comprises the sub-steps of:
computing first brightness differences among each pixel and pixels close to each pixel by each column and row so as to extract x and y coordinates of a left upper end of the search region, and adding absolute values of the computed first brightness differences;
computing second brightness differences among each pixel and pixels close to each pixel by each column and row so as to extract x and y coordinates of a right lower end of the search region, and adding absolute values of the computed second brightness differences; and
extracting, as the boundary of the region-of-interest, x and y coordinates at a moment when a difference of the added absolute values of the computed first and second brightness differences (i.e., a Difference of the Sum of Pixel Differences (DSPD)) is larger than a threshold value set regarding brightness difference.
3. The method as claimed in claim 2 , wherein DSPD values for horizontal and vertical sides of the search region is computed by equations defined by
DSPD
v
(
y
)
=
SPD
v
(
y
)
-
SPD
v
(
y
+
1
)
(
0
≤
y
<
height
3
)
DSPD
h
(
x
)
=
SPD
h
(
x
)
-
SPD
h
(
x
+
1
)
(
0
≤
x
<
width
2
)
.
4. The method as claimed in claim 2 , wherein, in the step of extracting, an accuracy of the extraction of the region-of-interest is measured by equations defined by
Recall=(the number of pixels belonging to an actual score region among extracted score regions)/(the number of pixels belonging to an actual region)×100% and
Precision=(the number of pixels belonging to an actual score region among extracted score regions)/(the number of all pixels belonging to an extracted region)×100%.
5. The method as claimed in claim 1 , wherein the step of determining boundary coordinates of the region-of-interest comprises the sub-steps of:
comparing boundary coordinates of a region-of-interest extracted from a current frame with boundary coordinates of a previous frame during a predetermined frame period;
determining a coordinate value of a left upper end of the region-of-interest to be a coordinate value having larger x and y values than x and y values of the boundary coordinates of the previous frame; and
determining a coordinate value of a right lower end of the region-of-interest to be a coordinate value having smaller x and y values than x and y values of the boundary coordinates of the previous frame.
6. The method as claimed in claim 1 , wherein the step of displaying the enlarged region-of-interest comprises a step of, if boundary coordinates of a region-of-interest previously displayed and stored is larger than a threshold value set regarding a brightness the stored region-of-interest.
7. The method as claimed in claim 1 , wherein the learning comprises comparing the extracted group of boundary coordinate candidates for each frame in the predetermined number of frames.