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

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

• playing a video present on a web, wherein the video is not annotated and comprises a series of frames, each frame being a visual image;
• identifying automatically a portion of a visual image of a frame of the video that contains an image of text, the image of text containing content that is original to the video;
• evaluating the image of text on the portion of the visual image of the frame with image text cognition to determine a content of the textual information on the portion of the visual image of the frame;
• determining whether the content of the textual information on the portion of the visual image of the frame contains non-current information based on a current context making a meaning of the content outdated;
• searching, in response to the content of the textual information being non-current, for an augmented virtual object area corresponding to the image of text on the portion of the visual image of the frame of the video from metadata associated with the video, the augmented virtual object area comprising an overlay that hides the portion of the visual image of the frame of the video that contains the image of text and being configured to receive a dynamically selected current interactive augmentation;
• dynamically selecting an interactive augmentation based on a profile of a user;
• automatically augmenting the interactive augmentation over the non-current information on top of the virtual object area while the video is playing using the searched for information on the augmented virtual object area;
• and
• providing an interactive service about an event occurring in the augmented virtual object area to the user.