Automatic Caption Localization in Compressed Video
IEEE Transactions on Pattern Analysis and Machine Intelligence
Caption processing for MPEG video in MC-DCT compressed domain
MULTIMEDIA '00 Proceedings of the eighth ACM international conference on Multimedia
On face detection in the compressed domain
MULTIMEDIA '00 Proceedings of the eighth ACM international conference on Multimedia
Detection of text captions in compressed domain video
MULTIMEDIA '00 Proceedings of the 2000 ACM workshops on Multimedia
MPEG Video Compression Standard
MPEG Video Compression Standard
Text Area Detection from Video Frames
PCM '01 Proceedings of the Second IEEE Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Fast scene change detection using direct feature extraction fromMPEG compressed videos
IEEE Transactions on Multimedia
A highly efficient system for automatic face region detection in MPEG video
IEEE Transactions on Circuits and Systems for Video Technology
Fast rotation-invariant video caption detection based on visual rhythm
CIARP'11 Proceedings of the 16th Iberoamerican Congress conference on Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
| Hi-index | 0.00 |
In this paper, a novel approach of automatic closed caption detection and font size differentiation among localized text regions in I-frames of MPEG videos is proposed. The approach consists of five modules: video segmentation, shot selection, caption frame detection, caption localization and font size differentiation. Rather than directly examines scene cut frame by frame, the module of video segmentation first verifies video streams GOP by GOP and then finds out the actual scene boundaries in the frame level. Tennis videos are selected as the case study and the module of shot selection is designed to automatically select specific type of shot for further closed caption detection. The noise of potential captions is filtered out based on its long-term consistency over consecutive frames. While the general closed captions are localized, we select the specific caption that is discriminated utilizing the module of font size differentiation. The detected closed captions can support video structuring, video browsing, high-level video indexing and video content description in MPEG-7. Experimental results show the effectiveness and the feasibility of the proposed scheme.