Skip to main content
Erschienen in: International Journal on Document Analysis and Recognition (IJDAR) 2/2019

05.04.2019 | Original Paper

Bleed-through cancellation in non-rigidly misaligned recto–verso archival manuscripts based on local registration

verfasst von: Pasquale Savino, Anna Tonazzini, Luigi Bedini

Erschienen in: International Journal on Document Analysis and Recognition (IJDAR) | Ausgabe 2/2019

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Ancient manuscripts written on both pages of the sheet are frequently affected by ink bleeding from the reverse side. This phenomenon produces a significant degradation of both the foreground text and the general appearance of the manuscript. Effective digital image restoration techniques may require the use of the content of both document sides, thus needing their perfect alignment. Although often available, recto and verso are usually not aligned, either for rigid misalignments occurring during acquisition, or for non-rigid deformations of the sheet. In this paper, we propose a novel method to restore color recto–verso manuscript images in a piecewise manner, without the need of a preliminary, global registration of the two sides. We assume that at the local level any deformation can be approximated by a displacement and subdivide the two images into small patches of same size. For each pair of patches at the same location, their relative shift is estimated by cross-correlation, thus allowing their straightforward alignment. A bleed-through removal algorithm is then applied to the registered patches. By spanning the entire images, this procedure returns free-of-interferences versions of the images in their original acquisition layout. The experiments show that the restoration results so obtained are better than those obtained with the classical approach that first registers the whole recto–verso pair and then performs restoration. Further advantages are a much lower computational cost, the possibility to manage non-global and non-rigid deformations, and the unaltered geometry and color appearance of the two restored images.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Sun, B., Li, S., Zhang, X.P., Sun, J.: Blind bleed-through removal for scanned historical document image with conditional random fields. IEEE Trans. Image Process. 25(12), 5702–5712 (2016)MathSciNetCrossRefMATH Sun, B., Li, S., Zhang, X.P., Sun, J.: Blind bleed-through removal for scanned historical document image with conditional random fields. IEEE Trans. Image Process. 25(12), 5702–5712 (2016)MathSciNetCrossRefMATH
2.
Zurück zum Zitat Tonazzini, A., Salerno, E., Bedini, L.: Fast correction of bleed-through distortion in grayscale documents by a blind source separation technique. Int. J. Doc. Anal. Recognit. 10, 17–25 (2007)CrossRef Tonazzini, A., Salerno, E., Bedini, L.: Fast correction of bleed-through distortion in grayscale documents by a blind source separation technique. Int. J. Doc. Anal. Recognit. 10, 17–25 (2007)CrossRef
3.
Zurück zum Zitat Hanasusanto, G.A., Wu, Z., Brown, M.S. : Ink-bleed reduction using functional minimization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 825–832 (2010) Hanasusanto, G.A., Wu, Z., Brown, M.S. : Ink-bleed reduction using functional minimization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 825–832 (2010)
4.
5.
Zurück zum Zitat Tonazzini, A., Gerace, I., Martinelli, F.: Multichannel blind separation and deconvolution of images for document analysis. IEEE Trans. Image Process. 19(4), 912–925 (2010)MathSciNetCrossRefMATH Tonazzini, A., Gerace, I., Martinelli, F.: Multichannel blind separation and deconvolution of images for document analysis. IEEE Trans. Image Process. 19(4), 912–925 (2010)MathSciNetCrossRefMATH
6.
Zurück zum Zitat Merrikh-Bayat, F., Babaie-Zadeh, M., Jutten, C.: Using non-negative matrix factorization for removing show-through. In: Proceedings LVA/ICA, pp. 482–489 (2010) Merrikh-Bayat, F., Babaie-Zadeh, M., Jutten, C.: Using non-negative matrix factorization for removing show-through. In: Proceedings LVA/ICA, pp. 482–489 (2010)
7.
Zurück zum Zitat Moghaddam, R.F., Cheriet, M.: A variational approach to degraded document enhancement. IEEE Trans. Pattern Anal. Mach. Intell. 32(8), 1347–1361 (2010)CrossRef Moghaddam, R.F., Cheriet, M.: A variational approach to degraded document enhancement. IEEE Trans. Pattern Anal. Mach. Intell. 32(8), 1347–1361 (2010)CrossRef
8.
Zurück zum Zitat Almeida, M.S.C., Almeida, L.B.: Nonlinear separation of show-through image mixtures using a physical model trained with ica. Signal Process. 92, 872884 (2012)CrossRef Almeida, M.S.C., Almeida, L.B.: Nonlinear separation of show-through image mixtures using a physical model trained with ica. Signal Process. 92, 872884 (2012)CrossRef
9.
Zurück zum Zitat Martinelli, F., Salerno, E., Gerace, I., Tonazzini, A.: Non-linear model and constrained ML for removing back-to-front interferences from recto–verso documents. Pattern Recognit. 45, 596–605 (2012)CrossRef Martinelli, F., Salerno, E., Gerace, I., Tonazzini, A.: Non-linear model and constrained ML for removing back-to-front interferences from recto–verso documents. Pattern Recognit. 45, 596–605 (2012)CrossRef
10.
Zurück zum Zitat Rowley-Brooke, R., Kokaram, A.: Bleed-through removal in degraded documents. In: Proceedings SPIE 8297 Document Recognition and Retrieval XIX, p. 82970T-10 (2012) Rowley-Brooke, R., Kokaram, A.: Bleed-through removal in degraded documents. In: Proceedings SPIE 8297 Document Recognition and Retrieval XIX, p. 82970T-10 (2012)
11.
Zurück zum Zitat Rowley-Brooke, R., Pitié, F., Kokaram, A.C.: A non-parametric framework for document bleed-through removal. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition (Online), Portland, OR, USA, 23–28 June 2013, pp. 2954–2960. https://doi.org/10.1109/CVPR.2013.380 (2013) Rowley-Brooke, R., Pitié, F., Kokaram, A.C.: A non-parametric framework for document bleed-through removal. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition (Online), Portland, OR, USA, 23–28 June 2013, pp. 2954–2960. https://​doi.​org/​10.​1109/​CVPR.​2013.​380 (2013)
12.
Zurück zum Zitat Tonazzini, A., Savino, P., Salerno, E.: A non-stationary density model to separate overlapped texts in degraded documents. Signal Image Video Process. 9, 155–164 (2015)CrossRef Tonazzini, A., Savino, P., Salerno, E.: A non-stationary density model to separate overlapped texts in degraded documents. Signal Image Video Process. 9, 155–164 (2015)CrossRef
13.
Zurück zum Zitat Ai, Y., Li, W., Chan, T.-H., Liao, Q.: Removal of bleed-through effect via nonnegative least-correlation. In: Proceedings of IEEE International Conference on Acoustic, Speech and Signal Processing ICASSP, pp. 2774–2778 (2014) Ai, Y., Li, W., Chan, T.-H., Liao, Q.: Removal of bleed-through effect via nonnegative least-correlation. In: Proceedings of IEEE International Conference on Acoustic, Speech and Signal Processing ICASSP, pp. 2774–2778 (2014)
14.
Zurück zum Zitat Dubois, E., Pathak, A.: Reduction of bleed-through in scanned manuscript documents. In: Proceedings of IS&T Image Processing, Image Quality, Image Capture Systems Conference, pp. 177–180 (2001) Dubois, E., Pathak, A.: Reduction of bleed-through in scanned manuscript documents. In: Proceedings of IS&T Image Processing, Image Quality, Image Capture Systems Conference, pp. 177–180 (2001)
15.
Zurück zum Zitat Tonazzini, A., Bianco, G., Salerno, E.: Registration and enhancement of double-sided degraded manuscripts acquired in multispectral modality. In: Proceedings 10th International Conference on Document Analysis and Recognition ICDAR 2009, pp. 546 – 550 (2009) Tonazzini, A., Bianco, G., Salerno, E.: Registration and enhancement of double-sided degraded manuscripts acquired in multispectral modality. In: Proceedings 10th International Conference on Document Analysis and Recognition ICDAR 2009, pp. 546 – 550 (2009)
16.
Zurück zum Zitat Wang, J., Brown, M.S., Tan, C.L.: Accurate alignment of double-sided manuscripts for bleed-through removal. In: Proceedings 8-th IAPR Workshop on Document Analysis System, pp. 69–75 (2008) Wang, J., Brown, M.S., Tan, C.L.: Accurate alignment of double-sided manuscripts for bleed-through removal. In: Proceedings 8-th IAPR Workshop on Document Analysis System, pp. 69–75 (2008)
17.
Zurück zum Zitat Li, B., Wang, W., Ye, H.: Multi-sensor image registration based on algebraic projective invariants. Opt. Express 21, 9824–9838 (2013)CrossRef Li, B., Wang, W., Ye, H.: Multi-sensor image registration based on algebraic projective invariants. Opt. Express 21, 9824–9838 (2013)CrossRef
18.
Zurück zum Zitat Savino, P., Tonazzini, A.: Digital restoration of ancient color manuscripts from geometrically misaligned recto–verso pairs. J. Cult. Herit. 19, 511–521 (2016)CrossRef Savino, P., Tonazzini, A.: Digital restoration of ancient color manuscripts from geometrically misaligned recto–verso pairs. J. Cult. Herit. 19, 511–521 (2016)CrossRef
19.
Zurück zum Zitat Wang, J., Tan, C.L.: Non-rigid registration and restoration of double-sided historical manuscripts. In: Proceedings International Conference on Document Analysis and Recognition (ICDAR), p. 13741378 (2011) Wang, J., Tan, C.L.: Non-rigid registration and restoration of double-sided historical manuscripts. In: Proceedings International Conference on Document Analysis and Recognition (ICDAR), p. 13741378 (2011)
20.
Zurück zum Zitat Myronenko, A., Song, X.: Intensity-based image registration by minimizing residual complexity. IEEE Trans. Med. Imaging 29, 1882–1891 (2010)CrossRef Myronenko, A., Song, X.: Intensity-based image registration by minimizing residual complexity. IEEE Trans. Med. Imaging 29, 1882–1891 (2010)CrossRef
21.
Zurück zum Zitat Rowley-Brooke, R., Pitié, F., Kokaram, A.C.: Nonrigid recto-verso registration using page outline structure and content preserving warps. In: Proceedings of the 2nd International Workshop on Historical Document Imaging and Processing ACM, pp. 8–13 (2013) Rowley-Brooke, R., Pitié, F., Kokaram, A.C.: Nonrigid recto-verso registration using page outline structure and content preserving warps. In: Proceedings of the 2nd International Workshop on Historical Document Imaging and Processing ACM, pp. 8–13 (2013)
22.
Zurück zum Zitat Rowley-Brooke, R., Pitié, F., Kokaram, A.: A ground truth bleed-through document image database. In: Theory and Practice of Digital Libraries, series Lecture Notes in Computer Science, P. Z. and G. Buchanan, E. Rasmussen, and F. Loizides (eds.), vol. 7489. Springer, pp. 185–196 (2012) Rowley-Brooke, R., Pitié, F., Kokaram, A.: A ground truth bleed-through document image database. In: Theory and Practice of Digital Libraries, series Lecture Notes in Computer Science, P. Z. and G. Buchanan, E. Rasmussen, and F. Loizides (eds.), vol. 7489. Springer, pp. 185–196 (2012)
24.
Zurück zum Zitat Sauvola, J., Pietikäinen, M.: Adaptive document image binarization. Pattern Recognit. 33, 225–236 (2000)CrossRef Sauvola, J., Pietikäinen, M.: Adaptive document image binarization. Pattern Recognit. 33, 225–236 (2000)CrossRef
25.
Zurück zum Zitat Klein, S., Staring, M., Murphy, K., Viergever, M.A., Pluim, J.: Elastix: a toolbox for intensity based medical image registration. IEEE Trans. Med. Imaging 29, 196–205 (2010)CrossRef Klein, S., Staring, M., Murphy, K., Viergever, M.A., Pluim, J.: Elastix: a toolbox for intensity based medical image registration. IEEE Trans. Med. Imaging 29, 196–205 (2010)CrossRef
26.
Zurück zum Zitat Hanif, M., Tonazzini, A., Savino, P., Salerno, E.: Non-local sparse image inpainting for document bleed-through removal. J. Imaging 4, 68 (2018)CrossRef Hanif, M., Tonazzini, A., Savino, P., Salerno, E.: Non-local sparse image inpainting for document bleed-through removal. J. Imaging 4, 68 (2018)CrossRef
Metadaten
Titel
Bleed-through cancellation in non-rigidly misaligned recto–verso archival manuscripts based on local registration
verfasst von
Pasquale Savino
Anna Tonazzini
Luigi Bedini
Publikationsdatum
05.04.2019
Verlag
Springer Berlin Heidelberg
Erschienen in
International Journal on Document Analysis and Recognition (IJDAR) / Ausgabe 2/2019
Print ISSN: 1433-2833
Elektronische ISSN: 1433-2825
DOI
https://doi.org/10.1007/s10032-019-00323-2

Weitere Artikel der Ausgabe 2/2019

International Journal on Document Analysis and Recognition (IJDAR) 2/2019 Zur Ausgabe