Chung-Wei Liang and Po-Yueh Chen* Department of Computer Science and Information Engineering, Chaoyang University of Technology, Wufeng, Taichung county 413, Taiwan, R.O.C.
Download Citation:
|
Download PDF
This paper presents an efficient yet simple method to extract text regions from static images or video sequences. The operation speed of Haar discrete wavelet transform (DWT) operates the fastest among all wavelets because its coefficients are either 1 or -1. This is one of the reasons we employ Haar DWT to detect edges of candidate text regions. The resulted detail component sub-bands contain both text edges and non-text edges. However, the intensity of the text edges is different from that of the non-text edges. Therefore, we can apply thresholding to preliminary remove the non-text edges. Text regions are composed of vertical edges, horizontal edges and diagonal edges. Morphological dilation operators are applied to connect isolated text edges of each detail component sub-band in a transformed binary image. According to the experiment results, real text regions are the overlapped portion of three kinds of dilated edges. Hence, we can apply the logical AND operator to three kinds of dilated edges and obtain the final text regions correctly.ABSTRACT
Keywords:
text extraction; Haar DWT; Thresholding; Morphological operator; Logical AND operator.
Share this article with your colleagues
[1] Park, J., Moon, K. A., Oh, Weon-Geun, and Choi, H. M. 2000. An efficient of character string positions using morph-ological operator. IEEE International Coanference on Systems, Man, and Cybernetics, 3, 8-11: 1616-1620.REFERENCES
[2] Zhong, Yu., Karu, K., and Jain, A.K. Locating text in complex color images. Proceedings of the Third International Conference on Document Analysis and Recognition, 1, 14-16: 146-149.
[3] Chen, Datong, Bourlard, H., and Thiran J. P., Text identification in complex background using SVM. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Proceedings of the 2001, 2, 8-14: 621-626.
[4] Lam, S. W., Wang, D., and Srihari, S. N., 1990. Reading newspaper text. International Conference on Pattern Recognition Proceedings, 10th. I, 16-21: 703-705.
[5] Williams, P. S. and Alder, M. D. 1996. Generic texture analysis applied to newspaper segmentation. IEEE International Conference on Neural Networks, 3, 3-6: 1664-1669.
[6] Zhong, Yu., Zhang, Hongjiang., and Jain, A. K. 2000. Automatic caption localization in compressed video. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22, 4: 385 –392.
[7] Acharyya, M. and Kundu, M. K. 2002. Document image segmentation using wavelet scale-space features. IEEE Transactions on Circuits and Systems for Video Technology, 12, 12: 1117 –1127.
[8] Mallat, S. G. 1989. A theory for multiresolution signal decomposition: the wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11, 7: 674-693.
[9] Acharya, Tinku., Chen, Po-Yueh. 1998. VLSI implementation of a DWT architecture. Proceedings of the IEEE International Symposium on Circuits and Systems, 2: 272-275.
[10] Grochening, K. and Madych, W. R. 1992. Multiresoultion analysis, Haar bases, and self-similar tilings of Rn . IEEE Transactions on Information Theory, 38, 2.
[11] Fujii, Masafumi., Wolfgang, J. R., and Hoefer. 2001. Filed-Singularity correction in 2-D time-domain Haar-wavelet modeling of waveguide components. IEEE Transactions on Microwave Theory and Techniques, 49, 4.
[12] Chen, P. Y. and Liao, E. C. 2002. A new algorithm for Haar discrete wavelet transform. IEEE International Symposium on Intelligent Signal Processing and Communication Systems, 21, 24: 453-457.
[13] Hasan, M. Y. and Lina J, Y. K. Morphological text extraction from image. IEEE Transactions on Image Processing, 9, 11: 1978 -1983.
ARTICLE INFORMATION
Accepted:
2004-02-20
Available Online:
2004-03-02
Liang , C.-W., Chen, P.-Y. 2004. DWT based text localization, International Journal of Applied Science and Engineering, 2, 105–116. https://doi.org/10.6703/IJASE.2004.2(1).105
Cite this article:
