About this document
Video Text Detection and Recognition Benchmark by Deep deeper is a document available to read on EtoBox.
This paper addresses the challenges of text detection and recognition in videos, extending existing image-based solutions to the video domain. It introduces a new dataset, ICDAR-VIDEO, and a performance metric based on precision-recall curves to evaluate text recognition in videos. The authors present their methodology, which leverages temporal redundancy and various character detection techniques to improve detection accuracy in video frames.
- Author
- Deep deeper
- Language
- EN