Title :
Real-time Detection of Semi-transparent Watermarks in Decompressed Video
Author :
Seeber, Balint ; Yager, Neil ; Amin, Adnan
Author_Institution :
Sydney Univ., NSW
Abstract :
Semi-transparent watermarks (logos) are a prominent feature of modern television programs. They are employed to label broadcasted programs, but not commercials, and therefore their absence can be exploited to filter out advertisements. A real-time template-based pixel matching algorithm for detecting known logos in video is presented. The logo detector achieves a high degree of precision (99.53%) and recall (97.23%) despite significant spatial variations inherent in the decompressed source video. When combined with other feature detectors, it forms the foundation of a live commercial detection system with applications in video archiving and embedded environments
Keywords :
feature extraction; image matching; object detection; television; video coding; watermarking; logo detection; pixel matching algorithm; real-time detection; semitransparent watermark detection; television programs; video archiving; video decompression; Animation; Application software; Computer vision; Detectors; Filtering; Image edge detection; Multimedia communication; Streaming media; TV; Watermarking;
Conference_Titel :
Applications of Computer Vision, 2007. WACV '07. IEEE Workshop on
Conference_Location :
Austin, TX
Print_ISBN :
0-7695-2794-9
Electronic_ISBN :
1550-5790
DOI :
10.1109/WACV.2007.53
