Caption replacement service system and method for interactive service in video on demand

1. A caption replacement service method performed by a computer system, the method comprising:

loading a video to be augmented, wherein the video comprises a series of frames, each frame being a visual image, and the video is not annotated;

automatically identifying, in at least one visual image frame of the video, a location in the visual image containing an image of text that comprises textual information and that is original to the video;

evaluating the image of text with image text cognition to determine a content of the textual information;

determining whether the content of the textual information contains non-current information based on a current context making a meaning of the content outdated, the non-current information being selected from the group consisting of: a news issue, a broadcast schedule, weather information, market information, trademark information, a displayed caption in a human language, and displayed time information;

automatically adding, in response to a determination that the content of the textual information contains non-current information, an augmented virtual object area at the location on the video frame of the textual information, the augmented virtual object area comprising an augmentation overlay that hides the non-current information of the content of the textual information;

dynamically selecting an interactive advertisement based on a profile of a user;

dynamically overlaying the interactive advertisement at the location of the non-current information on top of the augmented virtual object area of the loaded video; and

storing information on the added augmented virtual object area, the stored information being used to identify the augmented virtual object area when playing the video.

2. The method of claim 1 , wherein the loading of the video to be augmented comprises loading the video to be augmented to an augmented reality authoring tool using a uniform resource locator (URL) of a video present on a web, or selecting a video present in a local computer of a user and loading the selected video to the augmented reality authoring tool.

3. The method of claim 1 , wherein the adding of the virtual object area comprises adding the virtual object area by, in response to a selection of a user on a temporal location and a spatial location indicated by the at least one caption, locating the virtual object area to be above the at least one caption based on the temporal location and the spatial location.

4. The method of claim 1 , wherein the adding of the virtual object area comprises generating an information list by extracting information on at least one of a frame, a temporal location, and a spatial location associated with a caption present on the video using an image text cognition technology, and adding the virtual object area at the location of the at least one caption based on information selected by a user from the information list.

5. The method of claim 1 , wherein the interactive advertisement comprises at least one of an advertisement image extracted from a predetermined advertisement pool.

6. The method of claim 5 , wherein the image extracted from the advertisement pool is extracted based on a propensity of the user and a matter of interest of the viewer.

7. The method of claim 1 , wherein information on the virtual object area comprises information on at least one of a start time and an end time for displaying the virtual object area, a size of the virtual object area, a display location of the virtual object area, content of the interactive advertisement to be added to the virtual object area, a URL address of the interactive advertisement, and an event address generated in response to a click on the virtual object area.

8. The method of claim 1 , wherein the storing of the information on the added virtual object area comprises storing information on the virtual object area in a server in a structuralized form or in an ontology-based semantic form.

9. A caption replacement service system configured in a computer, the caption replacement service system comprising:

at least one storage unit configured to store at least one program;

at least one processor configured to process execution of a video loader, a virtual object area adder, an interactive advertisement adder, and an information storage according to a control of the at least one program;

the video loader configured to load a video to be augmented, wherein the video comprises a series of frames, each frame being a visual image, and the video is not annotated;

the virtual object area adder configured to:

automatically identify, in at least one visual image frame of the video, a location in the visual image containing an image of text that comprises textual information and that is original to the video;

evaluate the image of text with image text cognition to determine a content of the textual information;

determine whether the content of the textual information contains non-current information based on a current context making a meaning of the content outdated, the non-current information being selected from the group consisting of: a news issue, a broadcast schedule, weather information, market information, trademark information, a displayed caption in a human language, and displayed time information; and

automatically add, in response to a determination that the content of the textual information contains non-current information, an augmented virtual object area at the location on the video frame of the textual information, the augmented virtual object area comprising an augmentation overlay that hides the non-current information of the content of the textual information;

the interactive advertisement adder configured to:

dynamically select an interactive advertisement based on a profile of a user; and

dynamically overlay the interactive advertisement at the location of the non-current information on top of the augmented virtual object area of the loaded video; and

the information storage configured to store information on the added augmented virtual object area, the stored information being used to identify the augmented virtual object area when playing the video.

10. The caption replacement service system of claim 9 , wherein the virtual object area adder is configured to add the virtual object area by, in response to a selection of a user on a temporal location and a spatial location indicated by the at least one caption, locating the virtual object area to be above the at least one caption based on the temporal location and the spatial location.

11. The caption replacement service system of claim 9 , wherein the virtual object area adder is configured to generate an information list by extracting information on at least one of a frame, a temporal location, and a spatial location associated with a caption present on the video using an image text cognition technology, and to add the virtual object area at the location of the at least one caption based on information selected by a user from the information list.

12. The caption replacement service system of claim 9 , wherein information on the virtual object area comprises information on at least one of a start time and an end time for displaying the virtual object area, a size of the virtual object area, a display location of the virtual object area, content of the interactive advertisement to be added to the virtual object area, a URL address of the interactive advertisement, and an event address generated in response to a click on the virtual object area.