Compression of scan-digitized Indian language printed text: a soft pattern matching technique

ABSTRACT

In this paper, a new compression scheme is presented for Indian Language (IL) textual document images. Since OCR technology for IL scripts is not matured enough, transcription of these documents into digital domain needs new techniques that achieve high degree of compression as well as suitable methods to perform various operations like document indexing, retrieval, etc. The proposed method is essentially based on symbolic compression technique, which has been realized with an efficient segmentation-based clustering approach. A soft pattern-matching technique has been implemented using two different feature sets that co-operate each other to build an efficient prototype library. Experiments have been done for documents printed in Devnagari (Hindi) and Bangla scripts, two mostly used script in Indian sub-continent. Test results show that the proposed technique outperforms several standard methods like CCITT Group-4, JBIG, etc. which are frequently used for compression of document images.

REFERENCES

• 1: Chaudhuri, B. B. and Pal, U. A complete printed Bangla OCR system, Pattern Recognition, 31, 1998, 531--549.
• 2: B. B. Chaudhuri , U. Pal, An OCR System to Read Two Indian Language Scripts: Bangla and Devnagari (Hindi), Proceedings of the 4th International Conference on Document Analysis and Recognition, p.1011-1015, August 18-20, 1997
• 3: Bodson, D. Urban, S. Deutermann, A, and Clarke, C. Measurement of data compression in advanced Group 4 facsimile system, in Proc. of the IEEE, Vol. 73, 1985, 731--739.
• 4: W. B. Pennebaker , J. L. Mitchell, Probability estimation for the Q-Coder, IBM Journal of Research and Development, v.32 n.6, p.737-752, November 1988
• 5: Archer, R. and Nagy, G. A means for achieving a high degree of compaction on scan-digitized printed text, IEEE Trans. on Computers, Vol. 23, 1974, 1174--1179.
• 6: O. e. Kia , D. S. Doermann, Structural Compression for Documents Analysis, Proceedings of the International Conference on Pattern Recognition (ICPR '96) Volume III-Volume 7276, p.664, August 25-29, 1996
• 7: Omid Ebrahimi Kia, Document image compression and analysis, University of Maryland at College Park, College Park, MD, 1997
• 8: Zhang, Q. and Danskin, J. Entropy-based pattern matching for document image compression, in Proceedings of the Int'l Conf. on Image Processing (ICPR'96), 1996, 221--224.
• 9: CCITT. 1993. Draft recommendation T.82 & ISO DIS 11544: Coded representation of picture and audio information - progressive bi-level image compression.
• 10: Ian H. Witten , Timothy C. Bell , Alistair Moffat, Managing Gigabytes: Compressing and Indexing Documents and Images, John Wiley & Sons, Inc., New York, NY, 1994
• 11: Anil K. Jain , Bin Yu, Document Representation and Its Application to Page Decomposition, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.20 n.3, p.294-308, March 1998 [doi>10.1109/34.667886]
• 12: B. B. Chaudhuri , U. Pal, Skew Angle Detection of Digitized Indian Script Documents, IEEE Transactions on Pattern Analysis and Machine Intelligence, v.19 n.2, p.182-186, February 1997 [doi>10.1109/34.574803]
• 13: Theo Pavlidis , Jiangying Zhou, Page segmentation and classification, CVGIP: Graphical Models and Image Processing, v.54 n.6, p.484-496, Nov. 1992 [doi>10.1016/1049-9652(92)90068-9]
• 14: Kanungo, T. Haralick, R.M. and Phillips, I.T. Global and local document degradation models, in Proceedings of the Int'l Conf. on Document Analysis and Recognition (ICDAR'93), 1993, 730--734.
• 15: "Lossy/Lossless Coding of Bilevel Images," ITU-T Recommendation T.88, 2000.

INDEX TERMS

Primary Classification:
  E. Data
  E.4 CODING AND INFORMATION THEORY
      Subjects: Data compaction and compression

General Terms:
Design, Experimentation, Performance, Verification

Keywords:
data compression, indian language, pattern matching, textual image