Video caption text extraction and identification method

Abstract

The invention discloses a video caption text extraction and identification method which comprises the following steps of: inputting an image of a caption area in a video; converting the input image into a grayscale; judging the arrangement direction of characters in the caption area; counterclockwise rotating the caption area in which vertical arrangement is adopted 90 degrees to obtain a horizontal caption area; lining the caption area to obtain single-line caption images; automatically judging foreground colors of the single-line caption images to obtain binary single-line caption images; over-segmenting the binary single-line caption images to obtain character segment sequences; and performing text line identification on the over-segmented binary single-line caption images. By utilizing the method, horizontal and vertical video caption text lines can be effectively segmented, the foreground colors of the characters can be accurately judged, noises can be filtered, and accurate character segmentation and identification results can be obtained; and the method can be applicable to a plurality of purposes such as video and image content editing, indexing, retrieving and the like.

Description

technical field [0001] The invention belongs to the field of pattern recognition and computer vision, in particular to a processing method for text detection and recognition in video images. Background technique [0002] As one of the most popular forms of media, video is widely disseminated through the Internet and television. In order to make users find the video content they are interested in more conveniently and quickly, video retrieval and classification has gradually become a research hotspot in the field of pattern recognition and computer vision. Among them, the text information in the video, especially the subtitle information, has the most significant effect on video retrieval and classification. This is because: (1) the text information in the video is closely related to the current content of the video; (2) the characters in the video have very obvious visual features, which are easy to extract; (3) character recognition (OCR) technology is relatively Recognit...

AI Technical Summary

Problems solved by technology

In general, the existing video subtitle text extraction and recognition technology is not perfect, mainly reflected in: for complex and changeable backgrounds, especially those with similar or even the same color as the foreground cannot be processed; for changeable fonts, Such as: Song, Hei, Kai, etc. are not very adaptable; character recognition adopts the conventional OCR method, and the character segmentation, character image noise, and low resolution are not considered enough

Images