文章基本信息

标题：Joint Subtitle Extraction and Frame Inpainting for Videos with Burned-In Subtitles
本地全文：下载
作者：Haoran Xu ; Yanbai He ; Xinya Li 等
期刊名称：Information
电子版ISSN：2078-2489
出版年度：2021
卷号：12
期号：6
页码：233
DOI：10.3390/info12060233
出版社：MDPI Publishing
摘要：Subtitles are crucial for video content understanding. However, a large amount of videos have only burned-in, hardcoded subtitles that prevent video re-editing, translation, etc. In this paper, we construct a deep-learning-based system for the inverse conversion of a burned-in subtitle video to a subtitle file and an inpainted video, by coupling three deep neural networks (CTPN, CRNN, and EdgeConnect). We evaluated the performance of the proposed method and found that the deep learning method achieved high-precision separation of the subtitles and video frames and significantly improved the video inpainting results compared to the existing methods. This research fills a gap in the application of deep learning to burned-in subtitle video reconstruction and is expected to be widely applied in the reconstruction and re-editing of videos with subtitles, advertisements, logos, and other occlusions.
关键词：subtitle extraction; burned-in subtitles; image inpainting; text region detection; text recognition subtitle extraction ; burned-in subtitles ; image inpainting ; text region detection ; text recognition