Program Classification in a Stream TV Using Deep Learning
Mounira Hmayda, Ridha Ejbali, Mourad Zaied · 2017
Automatic identification of television programs in the TV stream is an important task for operating archives and represent a principal source of multimedia information.. The goal of the proposed approach is to enable a better exploitation of this source of video by multimedia services (i.e., TV-On-Demand, catch-up TV), social community, and video-sharing pla forms (Vimeo, Youtube, Facebook...) This paper presents a new spatio-temporal approach to identify the programs in TV stream using deep learning in two main steps. A database for video of visual jingles is constructed for training. In the test we use same jingles program type in order to identify the various program types in the TV stream. The main idea of identification process consists in using the principal of auto-encoder. After presenting the proposed approach, the paper overviews the encouraging experimental results on several streams extracted from different channels and composed of several programs. Comparison experiments to similar works have been carried out on the TRECVID 2017 database. We show significant improvements to TV programs identification exceed 95 %.