Cursive Caption Text Detection in Videos

TL;DR

This paper introduces a deep learning-based system for detecting cursive Urdu text in videos, combining text detection and script identification into an end-to-end trainable model with high accuracy.

Contribution

It presents a novel end-to-end trainable system specifically designed for cursive Urdu text detection in videos, integrating script identification with text detection.

Findings

Achieved an F-measure of 0.91 on a large video frame dataset.

Successfully distinguished cursive Urdu text from Latin script.

Demonstrated robustness in multi-script video content detection.

Abstract

Textual content appearing in videos represents an interesting index for semantic retrieval of videos (from archives), generation of alerts (live streams) as well as high level applications like opinion mining and content summarization. One of the key components of such systems is the detection of textual content in video frames and the same makes the subject of our present study. This paper presents a robust technique for detection of textual content appearing in video frames. More specifically we target text in cursive script taking Urdu text as a case study. Detection of textual regions in video frames is carried out by fine-tuning object detectors based on deep convolutional neural networks for the specific case of text detection. Since it is common to have videos with caption text in multiple-scripts, cursive text is distinguished from Latin text using a script-identification module. Finally, detection and script identification are combined in a single end-to-end trainable system. Experiments on a comprehensive dataset of around 11,000 video frames report an F-measure of 0.91.