Automatic TV logo detection and classification in broadcast videos

In this study
¹
, we present a fully automatic TV logo identification system. TV logos are detected in static regions given by time-averaged edges subjected to post-processing operations. Once the region of interest of a logo candidate is established, TV logos are recognized via their subspace features. Comparative analysis of features has indicated that ICA-II architecture yields the most discriminative with an accuracy of 99.2% in a database of 3040 logo images (152 varieties). Online tests for both detection and recognition on running videos have achieved 96.0% average accuracy. A more reliable logo identifier will be feasible by improving the accuracy of the extracted logo mask.