DL '97 Proceedings of the second ACM international conference on Digital libraries
Text Area Detection from Video Frames
PCM '01 Proceedings of the Second IEEE Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Character extraction of license plates from video
CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
Automatic text detection and tracking in digital video
IEEE Transactions on Image Processing
Photo Time-Stamp Recognition Based on Particle Swarm Optimization
WI '04 Proceedings of the 2004 IEEE/WIC/ACM International Conference on Web Intelligence
Fast photo time-stamp recognition based on SGNN
ISNN'06 Proceedings of the Third international conference on Advnaces in Neural Networks - Volume Part II
| Hi-index | 0.00 |
This paper addresses the problem of photo time-stampdetection and recognition, which is to determine the timea photo was taken. Since the time-stamp is exposedtogether with the scene, the main challenge comes fromcomplex background and saturation of the time-stamp.An MAP (Maximum a posterior probability) basedtemplate matching method is proposed to detect andrecognize the time-stamp simultaneously from a photo. Akey step of this method is skeleton-matching algorithm forindividual digit, which supports partial matching anddeals with complex background and saturation.Practically, to avoid exhaustive search, a saliencymap is obtained by applying a set of morphologicoperators on a photo. Proposals can be generated fromthe saliency map and the proposed method calculates theprobability for each proposal. An application with strongprior knowledge is also given in which the proposedmethod achieves high accuracy in almost real time.