The nature of statistical learning theory
The nature of statistical learning theory
Automatic text recognition for video indexing
MULTIMEDIA '96 Proceedings of the fourth ACM international conference on Multimedia
DL '97 Proceedings of the second ACM international conference on Digital libraries
Video Skimming and Characterization through the Combination of Image and Language Understanding
CAIVD '98 Proceedings of the 1998 International Workshop on Content-Based Access of Image and Video Databases (CAIVD '98)
Hi-index | 0.00 |
Video captions can be used to index large video archives in digital libraries. In this paper, an algorithm for detecting captions in video frames using support vector machine (SVM) is proposed. First, the input video frame is divided into square sub-blocks and a trained SVM is used to identify whether each sub-block is a caption block or not. Second, horizontal projection and vertical projection are performed to locate the candidate caption regions. Finally, false alarms are reduced by caption region verification. Experimental results show that the algorithm has a low missed rate and false alarm rate.