Method and apparatus for providing image contents
Disclosed herein is a method for providing image contents. The method for providing image contents includes: dividing the image contents into a plurality of scenes, each scene including a plurality of shots; classifying image frames for each scene depending on each of a plurality of characters appearing in the image contents; receiving a user input for selecting any one of the plurality of characters; and displaying a scene corresponding to the character selected depending on the user input.
1. A method for providing image contents, comprising:
dividing image contents into a plurality of scenes, each scene including a plurality of shots;
classifying image frames for each scene depending on at least one of a plurality of characters appearing in the image contents;
receiving a user input for selecting any one of the plurality of characters;
generating for display a scene corresponding to the character selected;
comparing feature values for a scene node included in a character node with feature values for the character node in determining a similarity value; and
deleting the scene node from the character node based on the similarity value.
2. The method for providing image contents as claimed in claim 1 , wherein dividing of the image contents into the plurality of scenes comprises:
determining an image difference feature vector indicating an image difference between adjacent frames;
detecting a shot boundary based on the image difference feature vector; and
dividing the image contents into the plurality of shots based on the detected shot boundary.
3. The method for providing image contents as claimed in claim 2 , wherein in the detecting of the shot boundary, the shot boundary is detected using a machine studying algorithm.
4. The method for providing image contents as claimed in claim 2 , wherein dividing of the image contents into the plurality of shots comprises:
generating shot feature vectors including at least one of a shot start time information indicating start time information of each of the plurality of shots, image feature values of a plurality of image frames included in one shot, and audio feature values of the plurality of image frames included in one shot with respect to each of the plurality of shots; and
grouping the plurality of shots into one scene based on a similarity of the generated shot feature vectors.
5. The method for providing image contents as claimed in claim 4 , wherein said grouping comprises all shots from a first shot to an n-th shot being grouped into the same scene when a similarity between a first shot feature vector and an n-th shot feature vector is greater than or equal to a preset value.
6. The method for providing image contents as claimed in claim 1 , wherein the classifying of the image frames comprises:
classifying the image frames depending on body information of the image frames included in a first scene when a scene change from the first scene to a second scene is generated;
extracting face feature information by analyzing face information of the classified image frame;
allocating an ID to the classified image frames based on the extracted face feature information; and
generating image section information to which the ID for the first scene is allocated.
7. The method for providing image contents as claimed in claim 6 , wherein the face feature information includes at least one face feature vector.
8. The method for providing image contents as claimed in claim 6 , wherein said allocating comprises assigning an ID having face feature information matched to the extracted face feature information to the classified image frames.
9. The method for providing image contents as claimed in claim 6 , wherein classifying the image frames comprises further classifying the image frames using audio information.
10. The method for providing image contents as claimed in claim 1 , wherein in the case in which an image representing a face of the character included in the image frames includes a background image, the image frames are classified using image data in which a region corresponding to the background image in an image representing a body of the character is removed.
11. The method for providing image contents as claimed in claim 1 , further comprising:
generating an image in which a region corresponding to a background image in an image representing a body of the character is removed in the case in which an image representing a face of the character included in the image frames includes the background image;
comparing the character included in the generated image and a character of the already classified group to determine a similarity value; and
including the generated image in the already classified group in the case in which the similarity value is greater than or equal to a preset value.
12. The method for providing image contents as claimed in claim 11 , wherein said comparing comprises comparing a color histogram of an image of the character included in the generated image and a color histogram of the character of the already classified group to each other.
13. An apparatus for providing image contents, comprising:
scene configuring circuitry configured to divide the image contents into a plurality of shots, generate a shot feature vector with respect to each of the plurality of shots, and group the plurality of shots into a plurality of scenes based on a similarity of the generated shot feature vectors;
classifying circuitry configured to classify image frames for each scene depending on each of a plurality of characters appearing in the image contents;
input circuitry configured to receive a user input for selecting any one of the plurality of characters; and
a display configured to display a scene corresponding to the selected character.
14. The apparatus for providing image contents as claimed in claim 13 , wherein the scene configuring circuitry is configured to determine an image difference feature vector indicating an image difference between adjacent frames, detect a shot boundary based on the calculated image difference feature vector, and divide the image contents into the plurality of shots based on the detected shot boundary.
15. The apparatus for providing image contents as claimed in claim 14 , wherein the scene configuring circuitry is configured to detect the shot boundary using a machine studying algorithm.
16. The apparatus for providing image contents as claimed in claim 13 , wherein the short feature vector comprises at least one of shot start time information indicating start time information of each of the plurality of shots, image feature values of a plurality of image frames included in one shot, and audio feature values of the plurality of image frames included in one shot.
17. The apparatus for providing image contents as claimed in claim 13 , wherein the scene configuring circuitry is configured to group all shots from a first shot to an n-th shot into the same scene in the case in which a similarity between a first shot feature vector and an n-th shot feature vector is greater than or equal to a preset value.
18. The apparatus for providing image contents as claimed in claim 13 , wherein the classifying circuitry comprises:
body recognizing circuitry configured to classify the image frames depending on body information of the image frames included in a first scene when a scene change from the first scene to a second scene is generated;
face recognizing circuitry configured to analyze face information of the classified image frames to extract face feature information;
ID allocating circuitry configured to assign an ID to the classified image frames based on the extracted face feature information; and
image section information generating circuitry configured to generate image section information to which the ID for the first scene is assigned.
19. The apparatus for providing image contents as claimed in claim 18 , wherein the face feature information includes at least one face feature vector.