2018/04/27 by Adam Słucki, Słucki, Adam, Tomasz Trzcinski +6
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #Digital Media Forensic Detection #FOS: Computer and information sciences #Handwritten Text Recognition Techniques #Music and Audio Processing #Video Analysis and Summarization #cs.CV
paper · pdf · doi:10.48550/arxiv.1804.10687
International Conference on Computer Vision and Graphics (ICCVG) 2018
openalex publication_date 2018/04/27 · arxiv created 2018/05/01 · arxiv updated 2018/05/02 · openalex created_date 2022/10/02 · openalex updated_date 2026/07/28
Textual overlays are often used in social media videos as people who watch them without the sound would otherwise miss essential information conveyed in the audio stream. This is why extraction of those overlays can serve as an important meta-data source, e.g. for content classification or retrieval tasks. In this work, we present a robust method for extracting textual overlays from videos that builds up on multiple neural network architectures. The proposed solution relies on several processing steps: keyframe extraction, text detection and text recognition. The main component of our system, i.e. the text recognition module, is inspired by a convolutional recurrent neural network architecture and we improve its performance using synthetically generated dataset of over 600,000 images with text prepared by authors specifically for this task. We also develop a filtering method that reduces the amount of overlapping text phrases using Levenshtein distance and further boosts system's performance. The final accuracy of our solution reaches over 80A% and is au pair with state-of-the-art methods.