DocumentCode
697815
Title
Automatic TV logo detection and classification in broadcast videos
Author
Ozay, Nedret ; Sankur, Bulent
Author_Institution
Bogazici Univ., Istanbul, Turkey
fYear
2009
fDate
24-28 Aug. 2009
Firstpage
839
Lastpage
843
Abstract
In this study1, 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.
Keywords
image classification; object detection; television broadcasting; ICA-II architecture yields; automatic TV logo classification; automatic TV logo detection; broadcast videos; logo identification system; Accuracy; Image edge detection; Principal component analysis; Support vector machines; TV; Vectors; Videos;
fLanguage
English
Publisher
ieee
Conference_Titel
Signal Processing Conference, 2009 17th European
Conference_Location
Glasgow
Print_ISBN
978-161-7388-76-7
Type
conf
Filename
7077387
Link To Document