25 February 2014 Probabilistic person identification in TV news programs using image web database
Author Affiliations +
Abstract
The automatic labeling of faces in TV broadcasting is still a challenging problem. The high variability in view points, facial expressions, general appearance, and lighting conditions, as well as occlusions, rapid shot changes, and camera motions, produce significant variations in image appearance. The application of automatic tools for face recognition is not yet fully established and the human intervention is needed. In this paper, we deal with the automatic face recognition in TV broadcasting programs. The target of the proposed method is to identify the presence of a specific person in a video by means of a set of images downloaded from Web using a specific search key.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
F. Battisti, F. Battisti, M. Carli, M. Carli, M. Leo, M. Leo, A. Neri, A. Neri, } "Probabilistic person identification in TV news programs using image web database", Proc. SPIE 9019, Image Processing: Algorithms and Systems XII, 90190D (25 February 2014); doi: 10.1117/12.2042087; https://doi.org/10.1117/12.2042087
PROCEEDINGS
8 PAGES


SHARE
RELATED CONTENT

Open source database of images DEIMOS extension for large...
Proceedings of SPIE (September 23 2014)
Tracking faces of arbitrary views for video annotation
Proceedings of SPIE (December 29 2000)
Real-time gender classification
Proceedings of SPIE (September 25 2003)
Interactive TV on parliament session
Proceedings of SPIE (September 17 2007)

Back to Top