Abstract
A new extension to the aperture filter is proposed to sharpen document images. The aperture filter is a nonlinear filter applied within a window having both domain and range constraints. The proposed aperture filter incorporates an adaptation to the original design by utilizing gradient directions of the input document images. Results demonstrate that the performance of the new approach is superior to that of both the aperture filter and alternative sharpening methods.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
Abbreviations
- \({\bf{\Psi}}\) :
-
signal filter
- A :
-
aperture filter
- D(i, j) :
-
edge vector, where D(i, j) = (d x i, j , d y i, j )
- dz :
-
four-dimensional feature vector, where d z = (d x1, dx2, dy1, dy2)
- E[Y|X]:
-
conditional probability of Y given X
- E i :
-
Euclidean distance
- I :
-
ideal signal
- I*:
-
clipped ideal signal
- [ − k, k]:
-
amplitude range of the aperture filter
- K x , K y :
-
two convolution kernels (5 × 5 masks) of Sobel operators
- q :
-
number of clusters
- T :
-
predefined threshold in the proposed aperture filter
- [ − w, w]:
-
window domain of the aperture filter
- X :
-
observed signal, X = (x 0, x 1, x 2, . . .)
- X*:
-
clipped observed signal, \({X^{\ast}{=}({x}_{0}^{\ast}, x_{1}^{\ast}, x_{2}^{\ast}, {\ldots}}\)
- x(i, j):
-
an image pixel
- Y :
-
estimation of the true signal
References
Taylor, M.J., Dance, C.R.: Enhancement of document images from cameras. Proc IS&T/SPIE EIDR V, pp. 230–241 (1998)
Jacobs, C., Simard, P.Y., Viola, P., Rinker, J.: Text recognition of low-resolution document images. Presented at the 8th int. conf. document analysis and recognition ICDAR, Seoul, Korea, 29 Aug–1 Sept 2005
Lin, X.: Quality assurance in high volume document digitization: a survey. Presented at the 2nd int. conf. document image analysis for libraries DIAL, Lyon, France, 27–28 Apr 2006
Doermann, D., Liang, J., Li, H.: Progress in camera-based document image analysis. Presented at the 7th int. conf. document analysis and recognition ICDAR, Edinburgh, Scotland, 3–6 Aug 2003
Tonazzini, A., Bedini, L.: Character segmentation in highly blurred ancient printed documents. Presented at the 10th int. conf. image analysis and processing ICIAP, Venice, Italy, 27–29 Sept 1999
Yang Y., Yan H.: An adaptive logical method for binarization of degraded document images. Pattern Recognit. 33, 787–807 (2000)
Trier O.D., Taxt T.: Evaluation of binarization methods for document images. IEEE Trans. Pattern Anal. Mach. Intell. 17(3), 312–315 (1995)
Niblack W.: An Introduction to Digital Image Processing. Prentice Hall, Englewood Cliffs (1986)
Marosi, I., Toth, L.: OCR voting methods for recognizing low contrast printed documents. Presented at the 2nd int. conf. document image analysis for libraries DIAL, Lyon, France, 27–28 Apr 2006
Hirata R. Jr, Dougherty E.R., Barrera J.: Aperture filters. Signal Process. 80(4), 697–721 (2000)
Hirata, R. Jr., Barrera, J., Dougherty, E.R.: Design of grey-scale nonlinear filters via multiresolution apertures. In: Proc. EUSIPCO, Tampere, Finland, 4–8 Sept 2000
Brun M., Hirata R. Jr, Barrera J., Dougherty E.R.: Nonlinear filter design using envelopes. J. Math. Imaging Vis. 21(1), 81–97 (2004)
Green A.C., Marshall S., Greenhalgh D., Dougherty E.R.: Design of multi-mask aperture filters. Signal Process. 83(9), 1961–1971 (2003)
Hirata, R. Jr., Brun, M., Barrera, J., Dougherty, E.R.: Aperture filters: theory, application and multiresolution analysis. In: Marshall, S., Sicuranza, G.L. (eds.) Advances in Nonlinear Signal and Image Processing, chap. 2, pp. 15–45. Hindawi Publishing Corporation (2006)
Green A.C., Dougherty E.R., Marshall S., Greenhalgh D.: Optimal filters with multiresolution apertures. J. Math. Imaging Vis. 20(3), 237–250 (2004)
Sharifi, M., Fathy, M., Mahmoudi, M.T.: A classified and comparative study of edge detection algorithms. Presented at the int. symposium information technology: coding and computing ITCC, Las Vegas, Nevada, USA, 8–10 Apr 2002
Russ J.C.: The Image Processing Handbook. CRC Press, Boca Raton (2002)
Pan F., Lin X., Rahardja S., Lim K.P., Li Z.G., Wu D., Wu S.: Fast mode decision algorithm for intraprediction in H.264/AVC video coding. IEEE Trans. Circuits Syst. Video Technol. 15(7), 813–821 (2005)
Kang C., Wang W.: A novel edge detection method based on the maximizing objective function. Pattern Recognit. 40, 609–618 (2007)
Liang L.R., Looney C.G.: Competitive fuzzy edge detection. Appl. Soft Comput. 3, 123–137 (2003)
Chen, G., Yang, C., Po, L.M., Xie, S.L.: Edge-based structural similarity for image quality assessment. Presented at the int. conf. acoustics, speech and signal processing ICASSP, Toulouse, France, 15–19 May 2006
Fischer M., Paredes J.L., Arce G.R.: Weighted median image sharpeners for the world wide web. IEEE Trans. Image Process. 11(7), 717–727 (2002)
Aysal T.C., Barner K.E.: Quadratic weighted median filters for edge enhancement of noisy images. IEEE Trans. Image Process. 15(11), 3294–3310 (2006)
Wang Z., Bovik A.C., Sheihk H.R., Simoncelli E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mahmoud, T.A., Marshall, S. Document image sharpening using a new extension of the aperture filter. SIViP 3, 403–419 (2009). https://doi.org/10.1007/s11760-008-0090-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-008-0090-3