Text tracking and multi-frame reinforcing method in video

Abstract

The invention relates to a method for tracing text and strengthening multi-frame in a video. The texts in the video are mostly laminated in a complicated background, and if the texts are directly delivered into OCR (Optical Character Recognition) software for recognition, the recognition rate is low, therefore, the text strengthening operations are required to separate the texts from the background. The texts in the video mostly last for tens of frames, and even hundreds of frames, and in the adjacent frames, the colour of the texts are basically invariable but the background changes dynamically, accordingly, abundant complementary information between the multi-frames can be used for strengthening the texts. The method of the invention eliminates the influence of background edge pixel through the text stroke's characteristic of possession of edge pair, then uses Hausdorff distance measurement method for tracing the location of the texts at the adjacent frame, after obtaining a plurality of copies of the text images at the adjacent frame, makes use of minimum pixel searching method to remove the background in order to acquire binary text image including the clean background, greatly improving the rate of OCR software in identifying the video texts.

Description

field of invention [0001] The present invention relates to the technical field of content-based multimedia retrieval, and more specifically, the present invention relates to text recognition in videos. The invention utilizes the feature that the text line in the video scene has a large amount of complementary information between multiple frames, and proposes a text tracking and multi-frame enhancement method in the video. The method of the invention can eliminate the background and improve the optical character recognition (OCR, Optical Character Recognition) recognition rate of the video text. Background of the invention [0002] The text in the video provides information highly related to the video content, such as scene location, event time, and sports scores, player names and other information, but compared with the text in the document image, the text recognition in the video faces the following difficulties : (1) Due to the reason of TV standard, video transmission an...

AI Technical Summary

Problems solved by technology

At this time, the SSD-based method will generate a large matching value when matching, and eventually cannot correctly track the position of the text in adjacent frames

In addition, the M-estimated template matching method itself has high computational complexity. Although it can track horizontal or oblique texts with translation, reduction, enlargement, rotation, fade in and fade out, and partial occlusion, the position of the text in adjacent frames can be tracked. It is mainly used to enhance the quality of text in multiple frames, using the temporal features of the text area to eliminate the background, and when the text is occluded or zoomed in, the spatial information of the tracked text pixel itself has become incomplete. quality, it doesn't make much sense to get a high-quality text binary image

Images