Overlay text extraction from TV news broadcast

Abstract

The text data present in overlaid bands convey brief descriptions of news events in broadcast videos. The process of text extraction becomes challenging as overlay text is presented in widely varying formats and often with animation effects. We note that existing edge density based methods are well suited for our application on account of their simplicity and speed of operation. However, these methods are sensitive to thresholds and have high false positive rates. In this paper, we present a contrast enhancement based preprocessing stage for overlay text detection and a parameter free edge density based scheme for efficient text band detection. The second contribution of this paper is a novel approach for multiple text region tracking with a formal identification of all possible detection failure cases. The tracking stage enables us to establish the temporal presence of text bands and their linking over time. The third contribution is the adoption of Tesseract OCR for the specific task of overlay text recognition using web news articles. The proposed approach is tested and found superior on news videos acquired from three Indian English television news channels along with benchmark datasets.

Extracting Textual Overlays from Social Media Videos Using Neural Networks

“…Inspired by this approach, we also generate part of our training data synthetically, however, we use the resulting dataset to improve the performance of several of our system's mod-ules and not a Tesseract engine. Furthermore, contrary to the results presented in [7], our text recognition engine that relies on a convolutional recurrent neural network architecture [1] significantly outperforms the competing methods, including the baseline Tesseract method.…”

“…Detecting and recognizing blocks of text in videos has also gained significant attention from the research community [5,6,7]. In [5], Sato et al present an approach based on extracting and classifying hand-crafted features using a computer vision method.…”

“…The problem of video overlay extraction is also tackled in [7], where Kannao and Guha propose to detect entire lines of text instead of single words. To decrease the computational cost of detection and recognition, they use temporal tracking across multiple frames.…”

A Workstation for Real-Time Processing of Multi-Channel TV

“…The recent trends for parallel computing, advances in real-time image processing, machine learning and artificial intelligence, embedded and hardware solutions, make possible the design of systems for real-time video analysis. This could offer a wide range of applications for TV industry and users as the video-based soccer analysis [1] or the advertising, logo and text detection [2][3][4].…”