A Comparative Study of Video Splitting Techniques

Abstract

The overall goal of our research is to extract the scrolling Arabic text from news videos. This paper presents our preliminary work on splitting the videos into frames without loss of scrolling textual information. This work is a part of large project aimed at developing a system for moving Arabic video text extraction for efficient content based indexing and searching. We compare the efficiency of our technique against FFmpeg and VLC which are the most widely used techniques for splitting the videos into frames in-terms of image difference and peak signal to noise ratio (PSNR). To our knowledge, our research is the primary in providing a comparative study with other techniques used in video splitting. © Springer International Publishing Switzerland 2015.