Systematic evaluation of face detection algorithms on news videos [Yüz bulma yöntemlerinin haber videolari i̇çin sistematik karşilaştirilmasi]
View/
Date Issued
2007Journal Title
2007 IEEE 15th Signal Processing and Communications Applications, SIU
Language
Turkish
Type
Conference Paper
Please cite this item using this persistent URL
http://hdl.handle.net/11693/27067Abstract
People are the most important subjects in news videos and for proper retrieval of people images; face detection is a very crucial step. However, face detection and recognition in news videos is a very challenging task due to the huge irregularities and high noise level in the data. In addition to that, with different face detection algorithms, the number and the type of the faces may differ. In this study, in order to get the best performance from existing methods, systematic evaluation of these methods is performed. In the experiments, news videos from TRECVID 2006 data set are used and for evaluation four different face detection methods are chosen.
Published as
http://dx.doi.org/10.1109/SIU.2007.4298778Collections
- Conference Paper [2294]
Related items
Showing items related by title, author, creator and subject.
-
A multi-modal video analysis approach for car park fire detection
(2013)In this paper a novel multi-modal flame and smoke detector is proposed for the detection of fire in large open spaces such as car parks. The flame detector is based on the visual and amplitude image of a time-of-flight ... -
Centralized and decentralized detection with cost-constrained measurements
(Elsevier B.V., 2017)Optimal detection performance of centralized and decentralized detection systems is investigated in the presence of cost constrained measurements. For the evaluation of detection performance, Bayesian, Neyman–Pearson and ... -
Content-based video copy detection based on motion vectors estimated using a lower frame rate
(Springer-Verlag London Ltd, 2014)We propose a motion vector-based video content-based copy detection method. One of the signatures of a given video is motion vectors extracted from image sequences. However, when consecutive image frames are used, the ...
