isrjournals
User Sign in    Editor Sign in

segmentation of degraded document text by local threshold method

A.Anees Fathima,T.N. Sudhashree

Published in International Journal of Advanced Research in Electronics, Communication & Instrumentation Engineering and Development

ISSN: 2347 -7210          Impact Factor:1.9         Volume:2         Issue:1         Year: 15 May,2014         Pages:29-35

International Journal of Advanced Research in Electronics, Communication & Instrumentation Engineering and Development

Abstract

Restoration plays a very important role in enhancing the degraded image. This paper proposes a novel document image binarization technique that addresses the issues by using adaptive image contrast. The adaptive image is the combination of local image contrast and local image gradient. For a degraded input image, adaptive image contrast is first constructed. The contrast map is then binarized and combined with canny’s edge map to identify the text stroke edge pixels. The local threshold segments the document text that is estimated based on the intensities of detected text stroke edge pixels. Post processing techniques are applied to the image and the restored document is obtained.

Kewords

Image Contrast, document analysis, image processing, degraded document, pixel classification.

Reference

[1] J.sauvola, M.pietikainen, page segmentation and classification using fast feature extraction and connectivity analysis, international conference on document analysis and recognition, ICDAR ’95, Montreal, Canada, 1995,pp 1127-1131 [2] B.Gatos, K. Ntirogiannis, and I.Pratikakis, ‘ICDAR 2009 docunent image binarization contest(DIBCO 2009).’in proc .Int.Conf.Document Anal.Recogniy.,Jul.2009,pp. 1375-1382. [3] I.Pratikakis, B.Gatos, and K.Ntirogiannis, “ICDAR 2011 document image binarizationcontest (DIBCO 2011),’ in proc,Int,Conf.Document Anal.Recognit., sep.2011,pp, 1506-1510 [4] S.Lu,B.Su, and C.L. Tan, “Document Image binarization using background estimation and stroke edge,’Int.J.Document Anal. Recognit vol. 14, no. 4,pp. 303-314, Dec. 2010 [5] B.Su, S.Lu, and C.L.Tan, “Binarization of historical handwritten document images using local maximum and minimum filter,’ in proc.Int.Workshop Document Anal.Syst.,Jun.2010, pp. 159-166 [6] G.Leedham, C.Ya, K.Taru, J.Hadi,N.Tan, and L.Mian, “comparison of some thresholding algorithm for text/background segmentation in difficult document images,” in proc. Int. Conf.Document Anal.Recognit., vol. 13.2003, pp. 859-864. [7] M.Sezgin and B.Sankur, “survey over image thresholding techniques and quantitative performance evaluation,” J.Electron.Imag.,vol13,no. 1,pp, 146-165, Jan. 2004. [8] O.D. Trier and A.K. Jain, “Goal-directed evalution of binarization methods,”IEEE Trans.pattern Anal.Mach.Intell., vol. 17, no. 12, pp. 1191-1201, Dec. 1995. [9] O.D. Trier and T. Taxt, “Evaluation of binarizaton methods for document images,” IEEE Trans.Pattern Anal.Mach.Intelll., vol 17, no 3,pp. 312-315,Mar.1995. [10] J.Sauvol and M.Pitikaien,’Adaptive document image binarization,’Pattern Recognit., vol.33, no. 2,pp. 225-236,2000. [11] W.Niblack, An Introducion to Digital Image Proessing, Englewood Cliffs,NJ: Prentice Hall, 1986 [12] J.Bersen, ‘Dynamic thresholding of gray-level images,’ in Proc, Int.Conf.Pattern Recogniy., aoct 1986, pp.1251-1255 [13] M.van Herk, “A fast algorithm for local minimum and maximum filters on rectangular and octagonal kernels,” Pattern Recognit. Lett., vol.13, no. 7,pp.517-521, Jul.1992