Title :
A spatial-temporal approach for video caption detection and recognition
Author :
Tang, Xiaoou ; Gao, Xinbo ; Liu, Jianzhuang ; Zhang, Hongjiang
Author_Institution :
Dept. of Inf. Eng., Chinese Univ. of Hong Kong, China
fDate :
7/1/2002 12:00:00 AM
Abstract :
We present a video caption detection and recognition system based on a fuzzy-clustering neural network (FCNN) classifier. Using a novel caption-transition detection scheme we locate both spatial and temporal positions of video captions with high precision and efficiency. Then employing several new character segmentation and binarization techniques, we improve the Chinese video-caption recognition accuracy from 13% to 86% on a set of news video captions. As the first attempt on Chinese video-caption recognition, our experiment results are very encouraging.
Keywords :
database indexing; fuzzy neural nets; image classification; image segmentation; optical character recognition; video databases; binarization techniques; caption-transition detection scheme; character segmentation; experiment; fuzzy-clustering neural network; neural network classifier; news video captions; spatial-temporal approach; video caption detection; video caption recognition; video databases; video indexing; Character recognition; Data mining; Fuzzy neural networks; Gunshot detection systems; Indexing; Layout; Neural networks; Optical character recognition software; Shape measurement; Video compression;
Journal_Title :
Neural Networks, IEEE Transactions on
DOI :
10.1109/TNN.2002.1021896
