Method and system for generating at least one of: comic strips and storyboards from videos

A method for automatically generating a comic strip from a video file, the method comprising:

• extracting audio frames and visual frames from the video file;
• identifying basic units of the video file;
• for each basic unit, extracting key frames, the key frames are extracted based on at least one of:
• audio frames, visual frames and a combination of the audio frames and the visual frames;
• and
• manipulating the key frames and the audio frames to output the comic strip, wherein an audio comic strip is formed when an audio is attached to the key frames and a caption-based comic strip is formed when a text is attached to the key frames, wherein length of the comic strip depends on the content of the video file.

A system for automatically generating a series of still images from a video file, the system comprising:

• an audio and video frames extraction unit for extracting audio frames and video frames from the video file;
• an audio and video processing unit for identifying basic units from the video file and extracting key frames, the key frames are extracted based on at least one of:
• audio frames, video frames and a combination of the audio frames and the video frames;
• and
• an output unit for manipulating the key frames and the audio frames to generate the series of still images.

A computer program product for use with a computer, the computer program product comprising a computer usable medium having a computer readable program code embodied therein for automatically generating a series of still images from a video file, the computer readable program code comprising:

• a program instruction means for extracting audio frames and visual frames from the video file;
• a program instruction means for identifying basic units of the video file;
• for each basic unit, a program instruction means for extracting key frames, the key frames are extracted based on at least one of:
• audio frames, visual frames and a combination of the audio frames and the visual frames;
• and
• a program instruction means for manipulating the key frames and the audio frames to output the series of still images, wherein length of the series of still images depends on the content of the video file.