Extraction of Hidden Text from Images using DWT

  • Authors

    • V. Beslin Geo
    • K. Sakthidasan @ Sankaran
    • P. Archana
    • M. Umarani
    2018-12-09
    https://doi.org/10.14419/ijet.v7i4.36.23908
  • Compression of Digital images, Filters, Text segmentation, Thresholding.

  • Extraction of hidden text in web images, computer screen images, news, games and e-learning is a very important task in image processing. Compression of digital images leads to poor visual quality of background and text images. Digital images are significantly considered and segmented using DWT into text and background blocks. Huffman coding is used to perform the lossless compression process in the compressed text pixels and the SPIHT algorithm in employed to the compress the background pixels. The result of DWT segmentation shows fringes in the segmented text image. The proposed method uses connected region and edge detection approach which provides a segmented text from digital video stills. The segmented text is converted to binary image using luminance thresholding which leads to fine quality of extracted text. 

  • References

    1. [1] Efficient block prediction-based coding of computer screen images with precise block classification , Ebenezer Juliet, S., JemiFlorinabel, D., IT Dept., Dr.SivanthiAditanar Eng. Coll., Tiruchendur, India. Institution of Engineering and Technology 2011.

      [2] Li, X., Lei, S.: ‘Block-based segmentation and adaptive coding for visually lossless compression of scanned documents’. Proc. Int. Conf. on Image Processing, 2001.

      [3] Keslassy, I., Kalman, M., Wang, D., Girod, B.: ‘Classification of compound images based on transform coefficient likelihood’. Proc. Int. Conf. on Image Processing, October 2001.

      [4] Lin, T., Hao, P.: ‘Compound image compression for real-time computer screen image transmission’, IEEE Trans. Image Process., 2005.

      [5] Optimizing Block-Thresholding Segmentation for Multilayer Compression of Compound Images Ricardo L. de Queiroz, Senior Member, IEEE, Zhigang Fan, Member, IEEE, and Trac D. Tran, IEEE TRANSACTIONS ON IMAGE PROCESSING, VOL. 9, NO. 9, SEPTEMBER 2000.

      [6] Gonzalez, R.C., Woods, R.E., Eddins, S.L.: ‘Digital image processingusing MATLAB’ (Prentice-Hall, Upper Saddle River, NJ, 2004).

      [7] Li, D. Doermann and O. Kia. Automatic Text Detection and Tracking in Digital Video. IEEE Transactions on Image Processing. Vol. 9, No. 1, pp. 147-156, Jan. 2000.

      [8] Rainer Lienhart and Frank Stuber. Automatic Text Recognition in Digital Videos. Proc. SPIE 2666: Image and Video Processing IV, pp. 180-188, 1996.

      [9] Rainer Lienhart and Axel Wernicke. Localizing and Segmenting Text in Images, Videos and Web Pages. IEEE Transactions on Circuits and Systems for Video Technology, Vol.12, No. 4, pp. 256 -268, April 2002.

      [10] V. Wu, R. Manmatha, E.M. Riseman. Textfinder: An Automatic System to Detect and Recognize Text in Images. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 21, Issue 11, pp. 1224-1229, Nov. 1999.

      [11] Xiaochuan Chen, Yunhong Wang, Tieniu Tan and Lei Guo, “Blind ImageSteganalysis Based on Statistical Analysis of Empirical Matrix Pattern Recognitionâ€, 18th International Conference on Pattern Recognition, Vol.3,pp. 1107 – 1110, 2006

      [12] Yuan Liu, Li Huang, Ping Wang, and Guodong Wang, “A blind imagesteganalysis based on features from three domainsâ€, Proceedings of Controland Decision Conference (CCDC), pp. 2933-2936, 2008.

      [13] XiangyangLuo, Fenlin Liu, Jianming Chen and Yining Zhang, “Imageuniversal steganalysis based on wavelet packet transform, Multimedia SignalProcessingâ€, IEEE 10th Workshop on Digital, pp. 780 – 784, 2008.

      [14] YuanluTu, and Shengrong Gong, “Universal steganalysis Using ColormCorrelation and Feature Fusionâ€, International Symposium on InformationScience and Engineering, Vol.1, pp. 107 – 111, 2008.

      [15] JingQu Lin and ShangPingZhong, “JPEG Image Steganalysis Method Basedon Binary Similarity Measuresâ€, Proceedings of Eighth InternationalConference on Machine Learning and Cybernetics, Baoding, pp. 2238-2243,2009.

      [16] ZhiMin He, W. Wing Y NG, P. K. Patrick Chan and S. Daniel Yeung, “BlindSteganalysis with High Generalization Capability for different ImageDatabasesâ€, Proceedings of the International Conference on MachineLearning and Cybernetics, Guilin, pp. 1690-1695, 2011.

      [17] Mansour Sheikhan, M. ShahramMoin, and MansourehPezhmanpour, “BlindImage Steganalysis via Joint Cooccurrence Matrix and Statistical Moments ofContourlet Transformâ€, 10th International Conference on Intelligent SystemsDesign and Applications, IEEE, 2010.

      [18] W. N. Lie, G. S. Lin and C. L. Wu, “Robust image watermarking on the DCTdomainâ€, In Proceedings of IEEE International Symposium on Circuits andSystems, Geneva, Switzerland, vol.1, pp. 228–231, 2000.

      [19] Y. Q. Shi, G. R. Xuan and D. K. Zou, “Image Steganalysis Based on Momentof Characteristic Function Using Wavelet Decomposition, redictionErrorImage, and Neural Networkâ€, IEEE International Conference on Multimediaand Expo, IEEE press, Amsterdam, Netherlands, pp. 269-272, 2005

  • Downloads

  • How to Cite

    Beslin Geo, V., Sakthidasan @ Sankaran, K., Archana, P., & Umarani, M. (2018). Extraction of Hidden Text from Images using DWT. International Journal of Engineering & Technology, 7(4.36), 419-423. https://doi.org/10.14419/ijet.v7i4.36.23908