Detecting Text from Natural Scenes 

We work, live, and play in a so-called information society where we communicate with people and information systems through diverse media in increasingly varied environments. A wealth of information is embedded in natural scenes. Signs are good examples of objects in natural environments that have high information content. Automatic detection and recognition of text from natural scenes is a very difficult task. The primary challenge lies in the variety of text: it can vary in font, size, orientation, and position. Text can also be blurred from motion or occluded by other objects. As signs exist in three-dimensional space, text on signs in scene images can be distorted by slant, tilt, and shape of objects on which they are found. Our current work focuses on text detection from video.The following is example of detecting text on road signs from video.

Related Publications:

• W. Wu, X. Chen, J. Yang, Detection of Text on Road Signs from Video, IEEE Transactions on Intelligent Transportation Systems, Vol 6, No. 4, pp. 378-390, 2005.
• W. Wu, D. Chen and J. Yang, Integrating Co-Training and Recognition for Text Detection, Proceedings of IEEE International Conference on Multimedia & Expo 2005 (ICME 2005), pp. 1166 - 1169, 2005.
• W. Wu, X. Chen, J. Yang, Incremental Detection of Text on Road Signs from Video with Application to a Driving Assistant System, Proceedings of ACM Multimedia 2004 (MM2004), pp. 852 - 859 2004.
• X. Chen, J. Yang, J. Zhang, A. Waibel, Automatic detection and recognition of signs from natural scenes, IEEE Transactions on Image Processing, Vol. 13, No. 1, pp. 87-99, 2004.
• J. Yang, X. Chen, J. Zhang, Y. Zhang, A. Waibel, "Automatic detection and translation of text from natural scenes," Proceedings of ICASSP 2002, Orlando, Fl., May, 2002.
• X. Chen, J. Yang, J. Zhang, and A. Waibel, Automatic detection of signs with affine transformation, Proceedings of WACV 2002, Orlando, Fl. December, 2002.
• J. Zhang, X. Chen, J. Yang, and A. Waibel, "A PDA-based Sign Translator," Proceedings of ICMI 2002, Pittsburgh, PA., October, 2002.
• J. Gao and J. Yang, "An Adaptive Algorithm for Text Detection from Natural Scenes," Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR2001), Hawaii, December 9-14, 2001