A methodology for the separation of foreground/background in Arabic historical manuscripts using hybrid methods

ABSTRACT

This paper presents a new color document image segmentation system suitable for historical Arabic manuscripts. Our system is composed of a hybrid method which couple together background light intensity normalization algorithm and k-means clustering with maximum likelihood (ML) estimation, for foreground/background separation.

Firstly, the background normalization algorithm performs separation between foreground and background. This foreground is used in later steps. Secondly, our algorithm proceeds on luminance and distort the contrast. These distortions are corrected with a gamma correction and contrast adjustment. Finally, the new enhanced foreground image is segmented to foreground/background on the basis of ML estimation. The initial parameters for the ML method are estimated by k-means clustering algorithm. The segmented image is used to produce a final restored document image.

The techniques are tested on a set of Arabic historical manuscripts documents from the National Tunisian Library. The performance of the algorithm is demonstrated on by real color manuscripts distorted with show-through effects, uneven background color and localized spot.

REFERENCES

• 1: A. Trémeau, C. Fernandez-Maloigne, P. Bonton, « Image numérique couleur de l'acquisition au traitement », ISBN 2 10 006843 1, Dunod, Paris, 2004.
• 2: C. A. B. Mello and R. D. Lins, "Image segmentation of historical documents," in Visual2000, Mex-ico City, Mexico, September 2000.
• 3: Carlos A.B. Mello , Rafael D. Lins, Generation of images of historical documents by composition, Proceedings of the 2002 ACM symposium on Document engineering, November 08-09, 2002, McLean, Virginia, USA [doi>10.1145/585058.585082]
• 4: Graham Leedham , Saket Varma , Anish Patankar , Venu Govindarayu, Separating Text and Background in Degraded Document Images " A Comparison of Global Threshholding Techniques for Multi-Stage Threshholding, Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition (IWFHR'02), p.244, August 06-08, 2002
• 5: Graham Leedham , Chen Yan , Kalyan Takru , Joie Hadi Nata Tan , Li Mian, Comparison of Some Thresholding Algorithms for Text/Background Segmentation in Difficult Document Images, Proceedings of the Seventh International Conference on Document Analysis and Recognition, p.859, August 03-06, 2003
• 6: H. D. Cheng, X. H. Jiang, Y. Sun, Jingli Wang, «Color image segmentation: advances and prospects», Pattern Recognition 34 (2001) 2259--2281.
• 7: J. Kittler , J. Illingworth, Minimum error thresholding, Pattern Recognition, v.19 n.1, p.41-47, Jan./Feb. 1986 [doi>10.1016/0031-3203(86)90030-0]
• 8: L. Bottou, P. Haffner, and P. G. Howard, "High Quality Document Image Compression with DjVu," Journal of Electronic Imaging, 7(3).
• 9: N. Otsu, "A threshold selection method from gray level histogram," IEEE Transactions in Systems, Man, and Cybernetics, vol. 9, pp. 62--66, 1979.
• 10: P. J. N. Kapur and A. K. C. Wong, "A new method for gray-level picture thresholding using the entropy of the histogram," Computer Vision, Graphics, and Image Processing, vol. 29, pp.273--285, 1985.
• 11: Q. Wang, T. Xia, L. Li, and C. Tan, "Document image enhancement using directional wavelet," in Proceedings of the 2003 IEEE Conference on Computer Vision and Pattern Recognition, Madison, Wisconsin, USA, June 2003.
• 12: U. Garain, Thierry Paquet and Laurent Heutte, "On Foreground-Background Separation in low Quality Color Document Images", in Proceedings of the Eighth International Conference on Document Analysis and Recognition, August 29-September 1, 2005
• 13: Y. Leydier, F. L. Bourgeois, and H. Emptoz, "Serialized K-Means for Adaptive Color Image Segmentation-Application to Document Images and Others", in 6^th International Workshop on Document Analysis systems (DAS), Itay, LNCS vol.3163, 252--263, 2004.
• 14: Zhixin Shi , Venu Govindaraju, Historical Document Image Enhancement Using Background Light Intensity Normalization, Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 1, p.473-476, August 23-26, 2004 [doi>10.1109/ICPR.2004.440]
• 15: Z. Shi, S. Setlur and V. Govindaraju, "Digital Enhancement of Palm Leaf Manuscript", Based Computer Systems, Hyderabad, India, December 19--22, 2004
• 16: Z. Shi, S. Setlur, and V. Govindaraju, "Digital Image Enhancement Using Normalization Techniques and their Application to Palmleaf Manuscripts", SPIE 2005.
• 17: Z. Shi and V. Govindaraju, "Historical Document Image Segmentation Using Background Light Intensity Normalization", SPIE Document Recognition and Retrieval XII, San Jose, California, USA16-20 January 2005.
• 18: http://www.biblotheque.nat.tn.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.6 Segmentation

Additional Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.9 Applications
  I.5 PATTERN RECOGNITION
      I.5.1 Models
          Subjects: Statistical

General Terms:
Algorithms

Keywords:
Arabic historical color manuscript image, foreground/background, k-means, light intensity normalisation, maximum likelihood, restoration, segmentation