Morphological filtering enhancement-based maximally stable extremal region (MSER) video text detection method

Abstract

The invention belongs to the technical field of video retrieval, relates to related image processing knowledge, and in particular relates to a video text detection method. The video text detection method is characterized by extracting video subtitles from a video to be detected and being used for recognition and video retrieval. The video text detection method comprises the steps of: firstly enhancing the text boundary of an input image by utilizing a gradient amplitude map (GAM); secondly, filtering partial background interference by using morphological filtering in two directions and enhancing the contrast of text and background; thirdly, detecting the saliency map of video text by using a maximally stable extremal region (MSER) detector, and acquiring the optimal segmentation of the text by utilizing Graph Cuts; and finally, connecting the texts to a text row by utilizing the geometrical distribution feature of the texts, and removing non-text regions by using multiframe confirmation and a certain starting education method. The detection method has the effects and benefits that the sensitive technical difficulties of blur text boundary, low contrast and complicated background and the like in text detection are overcome, and the detection results can be directly used for character recognition.

Description

technical field [0001] The invention belongs to the field of video retrieval, relates to relevant knowledge of image processing, and in particular relates to a video text detection method. Background technique [0002] Since the 1990s, video retrieval technology based on video subtitle information has attracted much attention from researchers, and many excellent technologies and methods have emerged. The research hotspots mainly focus on video image text detection and positioning. The representative articles and patents published successively since 2005 are described below. [0003] In "A comprehensive method for multilingual video text detection, localization, and extraction.In T-CSVT, 2005", Lyu, M.R et al. analyzed the sobel edge density of the text to locate the position of the text. In the article "A New Approach for Overlay Text Detection and Extraction From Complex Video Scene.In TIP, 2009" by Wonjun Kim et al., the color transition map is used to locate the position...

AI Technical Summary

Problems solved by technology

[0007] The technical problem to be solved by the present invention is: in the case where video lossy compression causes blurred text boundaries, when the contrast between the video background and the video text is relatively low, and the video contains complex backgrounds that are very similar to the texture and color of subtitles, For example: in the case of panes, fences, leaves, etc., extract two-color text in the video, and the extracted video text can be directly used for recognition

Images