METHOD OF EXTRACTING SCROLLING TEXT FROM A SEQUENCE OF MOVING IMAGES

摘要

A method of extracting scrolling text from a sequence of moving images includes obtaining video input data representative of a sequence of image frames(8-10) representing the sequence of moving images.Atleast one region(11,12) containing text within the images of the sequence is detected.For each of at least one of the at least one detected region a displacement of the region(11) fromimage to image is estimated, the images are registered in accordance with the estimated displacement,such that the region(11) is generallystatic from one registered image to the next, and at least parts of image frames representing multiple registered images are caused to be used as input in a method of segmentingtext from background,based on multiple images so as to generate an image of the text filtered from these.