Text Segmentation in Complex Background Based on Color and Scale Information of Character Strokes

This paper presents a robust approach to segmenting text embedded in complex background. Our approach consists of four steps: smart sampling, unsupervised clustering, the Bayesian decision, post-processing. The experimental results show that it works effectively, and is more efficient in removing complex background residues than the popular K-means method.

[1]  Anil K. Jain,et al.  Automatic text location in images and video frames , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[2]  Wen Gao,et al.  A robust text detection algorithm in images and video frames , 2003, Fourth International Conference on Information, Communications and Signal Processing, 2003 and the Fourth Pacific Rim Conference on Multimedia. Proceedings of the 2003 Joint.

[3]  Bernd Freisleben,et al.  Unsupervised Text Segmentation Using Color and Wavelet Features , 2004, CIVR.

[4]  Jean-Marc Odobez,et al.  Text detection, recognition in images and video frames , 2004, Pattern Recognit..

[5]  Weiqiang Wang,et al.  A Robust Text Segmentation Approach in Complex Background Based on Multiple Constraints , 2005, PCM.

[6]  Edward M. Riseman,et al.  Finding text in images , 1997, DL '97.