Title :
A Parametric Spectral-Based Method for Verification of Text in Videos
Author :
Papavassiliou, Vassilis ; Stafylakis, Themos ; Katsouros, Vassilis
Author_Institution :
Commun. & Knowledge Technol., Athens
Abstract :
A new method for verifying text areas detected in video streams is proposed. The algorithm explores the spectral properties of the horizontal projection of candidate text regions in order to reduce the high amount of false alarms that most text detection algorithms suffer from. The full algorithm (text localization followed by verification and temporal redundancy module) has been tested on newscast video sequences (MPEG-1-720 x 576 resolution-184 minutes). The detection module produced 94.82% recall rate but only 51.84% precision rate. The addition of the verification module increased the precision rate to 78.93% keeping the recall rate almost unaffected.
Keywords :
image sequences; object detection; spectral analysis; text analysis; video streaming; parametric spectral-based method; temporal redundancy module; text detection algorithm; text localization; text verification module; video sequences; video streams; Communications technology; Data mining; Indexing; Natural languages; Pixel; Probability; Speech processing; Technological innovation; Text recognition; Video sequences;
Conference_Titel :
Document Analysis and Recognition, 2007. ICDAR 2007. Ninth International Conference on
Conference_Location :
Parana
Print_ISBN :
978-0-7695-2822-9
DOI :
10.1109/ICDAR.2007.4377041
