LWSINet: A deep learning-based approach towards video script identification

Videos – a high volume of texts – broadcast via different media, such as television and the internet. Since Optical Character Recognition (OCR) engines are script-dependent, script identification is a precursor. Other than that, video script identification is not trivial as we have difficult issues, such as low resolution, complex background, noise, and blur effects. In this work, a deep learning-based system, which we call LWSINet: LightWeight Script Identification Network (6-layered CNN) is proposed to identify video scripts. For validation, we used a publicly available dataset named CVSI-15. Besides, the effects of three common noises namely, Salt & pepper, Gaussian and Poisson were considered on the scripts along with their hybridized metamorphosis. In our test results, we observed that the proposed CNN is coherent and robust enough to identify scripts in both scenarios, with and without noise. Further, we also employed other well-known handcrafted feature-based and deep learning approaches for a comparison.