Abstract
Document image binarization is a difficult task, especially for complex document images. Nonuniform background, stains, and variation in the intensity of the printed characters are some examples of challenging document features. In this work, binarization is accomplished by taking advantage of local probabilistic models and of a flexible active contour scheme. More specifically, local linear models are used to estimate both the expected stroke and the background pixel intensities. This information is then used as the main driving force in the propagation of an active contour. In addition, a curvature-based force is used to control the viscosity of the contour and leads to more natural-looking results. The proposed implementation benefits from the level set framework, which is highly successful in other contexts, such as medical image segmentation and road network extraction from satellite images. The validity of the proposed approach is demonstrated on both recent and historical document images of various types and languages. In addition, this method was submitted to the Document Image Binarization Contest (DIBCO’09), at which it placed 3rd.
Similar content being viewed by others
References
Otsu N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9, 62–66 (1979)
da Silva J.M.M., Lins R.D., Martins F.M.J., Wachenchauzer R.: A new and efficient algorithm to binarize document images removing back-to-front interference. J. Univers. Comput. Sci. 14(2), 299–313 (2008)
Robert Milewski V.G.: Binarization and cleanup of handwritten text from carbon copy medical form images. Pattern Recognit. 41, 1308–1315 (2008)
Sauvola J., Pietikäinen M.: Adaptive document image binarization. Pattern Recognit. 33(2), 225–236 (2000)
Trier O., Jain A.: Goal-directed evaluation of binarization methods. IEEE Trans. Pattern Anal. Mach. Intell. 17(12), 1191–1201 (1995). doi:10.1109/34.476511
Farrahi Moghaddam R., Cheriet M.: A multi-scale framework for adaptive binarization of degraded document images. Pattern Recognit. 43, 2186–2198 (2010). doi:10.1016/j.patcog.2009.12.024
Drira F., Le Bourgeois F., Emptoz H.: Restoring ink bleed-through degraded document images using a recursive unsupervised classification technique. Doc. Anal. Syst. VII, 38–49 (2006). doi:10.1007/11669487_4
Tan, C.L., Cao, R., Shen, P., Wang, Q., Chee, J., Chang, J.: Removal of interfering strokes in double-sided document images. In: Fifth IEEE Workshop on Applications of Computer Vision, 2000, pp. 16–21. Palm Springs, CA (2000). doi:10.1109/WACV.2000.895397
Su, B., Lu, S., Tan, C.L.: Binarization of historical document images using the local maximum and minimum. In: DAS’10, pp. 159–166. ACM, Boston, Massachusetts (2010) doi:10.1145/1815330.1815351
Cheriet M.: Extraction of handwritten data from noisy gray-level images using a multiscale approach. Int. J. Pattern Recognit. Artif. Intell. 13(5), 665–684 (1999)
Shafait, F., Keysers, D., Breuel, T.M.: Efficient implementation of local adaptive thresholding techniques using integral images. In: Document Recognition and Retrieval XV. San Jose, USA (2008)
Hedjam, R., Farrahi Moghadam, R., Cheriet, M.: Text extraction from degraded document images. In: EUVIP’10, pp. 248–253. Paris, France (2010)
Gatos, B., Ntirogiannis, K., Pratikakis, I.: Icdar 2009 document image binarization contest (dibco 2009). In: ICDAR (2009)
Serra J.: From Pixels to Features, Ch Toggle Mappings, pp. 61–72. Elsevier, Amsterdam (1989)
Naegel B., Wendling L.: A document binarization method based on connected operators. Pattern Recognit. Lett. 31(11), 1251–1259 (2010)
Cao H., Govindaraju V.: Preprocessing of low-quality handwritten documents using markov random fields. IEEE Trans. Pattern Anal. Mach. Intell. 31(7), 1184–1194 (2009). doi:10.1109/TPAMI.2008.126
Dimov, D., Dimov, A.: Data driven approach to binarization of astronomical images. In: CompSysTech’10, pp. 478–484. ACM, Sofia, Bulgaria (2010). doi:10.1145/1839379.1839465
Bar-Yosef I., Mokeichev A., Kedem K., Dinstein I., Ehrlich U.: Adaptive shape prior for recognition and variational segmentation of degraded historical characters. Pattern Recognit. 42(12), 3348–3354 (2009). doi:10.1016/j.patcog.2008.10.005
Tan C.L., Cao R., Shen P.: Restoration of archival documents using a wavelet technique. IEEE Trans. Pattern Anal. Mach. Intell. 24(10), 1399–1404 (2002). doi:10.1109/TPAMI.2002.1039211
Rivest-Hénault, D., Cheriet, M.: Unsupervised mri segmentation of brain tissues using a local linear model and level set, Elsevier MRI (online) (2010). doi:10.1016/j.mri.2010.08.007
Gatos, B., Pratikakis, I., Perantonis, S.: Improved document image binarization by using a combination of multiple binarization techniques and adapted edge information. In: ICPR’08, pp. 1–4. (2008)
Farrahi Moghaddam, R., Rivest-Hénault, D., Cheriet, M.: Restoration and segmentation of highly degraded characters using a shape-independent level set approach and multi-level classifiers. In: ICDAR’09, pp. 828–832. Barcelona, Spain (2009). doi:10.1109/ICDAR.2009.107
Farrahi Moghaddam R., Cheriet M.: RSLDI: restoration of single-sided low-quality document images. Pattern Recognit. 42, 3355–3364 (2009)
Sethian J.: Level Set Methods and Fast Marching Methods. Cambridge University Press, Cambridge (1999)
Osher S., Sethian J.A.: Fronts propagating with curvature dependent speed: algorithms based on Hamilton–Jacobi formulations. J. Comput. Phys. 79(2), 12–49 (1988)
Malladi R., Sethian J.: A unified approach to noise removal, image enhancement, and shape recovery. IEEE IP 5, 1554–1568 (1996)
Caselles V., Kimmel R., Sapiro G.: Geodesic active contours. Int. J. Comput. Vis. 22, 61–79 (1997)
Tsai A., Yezzi A., Willsky A.S.: Curve evolution implementation of the Mumford–Shah functional for image segmentation, denoising, interpolation, and magnification. IEEE Trans. Image Process. 10(8), 1169–1186 (2001)
Vese L.A., Chan T.F.: A multiphase level set framework for image segmentation using the Mumford and Shah model. Int. J. Comput. Vis. Vol. 50(2), 271–293 (2002)
Chan T.F., Vese L.: Active contours without edge. IEEE Trans. Image Process. 10(2), 266–277 (2001)
Paragios N., Deriche R.: Geodesic active regions: a new framework to deal with frame partition problems in computer vision. J. Visual Commun. Image Rep. 13(2), 249–268 (2002)
Liu, J.: Robust image segmentation using local median. In: Proceedings of the of the 3rd Canadian Conference on Computer Robot Vision, p. 31. (2006)
Rivest-Hénault D., Cheriet M.: Image segmentation using level set and local linear approximations. In: Kamel, M., Campilho, A. (eds) ICIAR 2007, LNCS 4633, pp. 234–245. Springer, Berlin (2007)
Rosenhahn B., Brox T., Weickert J.: Three-dimensional shape knowledge for joint image segmentation and pose tracking. Int. J. Comput. Vis. 73(3), 243–262 (2007)
Li C., Kao C.-Y., Gore J.C., Ding Z.: Minimization of region-scalable fitting energy for image segmentation. IEEE Trans. Image Process. 17(10), 1940–1949 (2008)
Ben Ayed I., Mitiche A., Belhadj Z.: Polarimetric image segmentation via maximum-likelihood approximation and efficient multiphase level-sets. IEEE Trans. Pattern Anal. Mach. Intell. 28, 1493–1500 (2006)
Brox T., Cremers D.: On local region models and a statistical interpretation of the piecewise smooth mumford-shah functional. Int. J. Comput. Vis. 84, 184–193 (2009)
Breu H., Gil J., Kirkpatrick D., Werman M.: Linear time euclidean distance transform algorithms. IEEE PAMI 17, 529–533 (1995)
Liu, J., Chelberg, D., Smith, C., Chebrolu, H.: Distribution-based level set segmentation for brain mr images. In: BMVC07. (2007)
Farrahi Moghaddam R., Cheriet M.: Beyond pixels and regions: a non-local patch means (NLPM) method for content-level restoration, enhancement, and reconstruction of degraded document images. Pattern Recognit. 44(2), 363–374 (2011). doi:10.1016/j.patcog.2010.07.027
Haykin S.S.: Blind Deconvolution. PTR Prentice Hall, Englewood Cliffs (1994)
Farrahi Moghaddam R., Cheriet M.: Low quality document image modeling and enhancement. IJDAR 11(4), 183–201 (2009). doi:10.1007/s10032-008-0076-2
Google, Book Search Dataset, version v Edition (2007)
Deriche, R., Faugeras, O.: Les EDP en traitement des images et vision par ordinateur. Technical Report 2697, INRIA, 1–63 (1996)
Bradley D., Roth G.: Adaptive thresholding using the integral image. J. Graph. GPU Game Tools 12(2), 13–21 (2007)
Cremers, D., Fluck, O., Rousson, M., Aharon, S.: A probabilistic level set formulation for interactive organ segmentation. In: SPIE Medical Imaging. (2007)
Mei, X., Decaudin, P., Hu, B., Zhang, X.: Real-time marker level set on gpu. In: International Conference on Cyberworlds, CW ’08. (2008)
Mackay K., Henderson W., Mackay R.: Introduction to Modern Inorganic Chemistry. CRC Press, Boca Raton (2002)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Rivest-Hénault, D., Farrahi Moghaddam, R. & Cheriet, M. A local linear level set method for the binarization of degraded historical document images. IJDAR 15, 101–124 (2012). https://doi.org/10.1007/s10032-011-0157-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10032-011-0157-5