Abstract
Despite numerous efforts, the problem of effective correction of perspective and illumination distortions that arise from scanning or copying thick, bound documents, particularly books, remains a very important issue for the development of new image restoration methods and the creation of appropriate hardware. Using a simplified 2D reconstruction requires, in most cases, two-pass scanning and imposes restrictions onto the document types. Nonetheless, the restoration quality seems to be insufficient. In the case of one-pass data capture, the projective distortions remain in the image and there is no reliable way to identify and remove them via further processing due to the absence of mathematical procedures to estimate the surface shape (i.e. image depth) from a single image. The 3D approach described in current chapter is based on obtaining and analysing the form of the book binding areas from photos captured by additional lateral camera(s) that operate during the scanning/copying process. In the beginning, the distances from the platen to the recovered surface are measured via processing of the supporting lateral images. Afterwards, the page length is reconstructed during scanning. Based on the information mentioned above, the distortions are subsequently corrected in following order: (a) perspective distortion, (b) deskewing and relative page turn correction and (c) shadow near binding correction. For the correction of the shadow, the preliminary single calibration of the scanning device is performed. The proposed method allows actualizing one-pass, distortion-free scanning/copying of non-flat documents with minimal changes of existing hardware. The results of the corresponding numerical modelling, as well as processing of the data that was obtained from standard flatbed devices, are given. Considering the latest tendencies in document capture and processing using portable devices, the chapter was extended by the material related to mobile image/document enhancement and the most recent advances in depth extraction from single image using Convolutional Neural Networks (CNN).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Barney Smith, E.H.: document creation, image acquisition and document quality. In: Doermann, D., Tombre, K. (eds.) London Handbook of Document Image Processing and Recognition, pp. 11–61. Springer, Berlin (2014)
Brown, M.S., Seales, W.B.: Image restoration of arbitrary warped documents. IEEE Trans. Pattern Anal. Mach. Intell. 26(10) (2004)
Buckland, M.: document theory: an introduction. In: Willer, M., Gilliland, A.J., Tomić, M. (eds.) Records, Archives and Memory: Selected Papers from the Conference and School on Records, Archives and Memory Studies, pp. 223–237. University of Zadar, Croatia (2013)
Cao, Y., Wu, Z., Shen, C.: Estimating depth from monocular images as classification using deep fully convolutional residual networks. IEEE Trans. Circuits Syst. Video Technol. (2017)
Fu, H., Gong, M., Wang, C., Tao, D.: A Compromise Principle in Deep Monocular Depth Estimation. arXiv preprint arXiv:1708.08267 (2017)
Godard, C., Mac Aodha, O., Brostow, G.J.: Unsupervised monocular depth estimation with left-right consistency. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 2, no. 6, p. 7 (2017)
Ihrig, S., Ihrig, E.: Scanning of Professional Way. McGraw-Hill Inc, Berkeley (1995)
Kuznietsov, Y., Stückler, J., Leibe, B.: Semi-supervised deep learning for monocular depth map prediction. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6647–6655 (2017)
Li, B., Dai, Y., He, M.: Monocular Depth Estimation with Hierarchical Fusion of Dilated CNNs and Soft-Weighted-Sum Inference. arXiv preprint arXiv:1708.02287 (2017)
Lin, Q., Liu, J., Tretter, D.: Printing in a digital edge. In: Boll, S. (ed.) IEEE Trans. Multimed. 17(4), 100–107 (2010)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: MICCAI (2015)
Rychagov, M.N., Safonov, I.V.: System and methods of scanning and copying. RU Patent 2,298,292 (2007)
Safonov, I.V., Rychagov, M.N.: System and method of scanning and copying (3D). RU Patent 2,368,091 (2009)
Safonov, I.V., Kurilin, I.V, Rychagov, M.N., Tolstaya, E.V.: Adaptive Image Processing Algorithms for Printing (2018)
Vaughan, K.: Compare CCD vs CIS Scanner Technologies. https://www.tavco.net/wide-format-plotter-scanner-blog/bid/107329/compare-ccd-vs-cis-scanner-technologies (2017)
Wada, T., Ukida, H., Matsuyama, T.: Shape from shading with inter-reflections under proximal light source. In: Proceedings of ICCV’95 (1995)
Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)
Wang, C., Buenaposada, J. M., Zhu, R., Lucey, S.: Learning Depth from Monocular Videos using Direct Methods. arXiv preprint arXiv:1712.00175 (2017)
Ye, P., Doermann, D.: Document image quality assessment: a brief summary. In: IEEE 12th International Conference on Document Analysis and Recognition (ICDAR), pp. 723–727 (2013)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Safonov, I.V., Kurilin, I.V., Rychagov, M.N., Tolstaya, E.V. (2019). Distortion-Free Scanning and Copying of Bound Documents. In: Document Image Processing for Scanning and Printing . Signals and Communication Technology. Springer, Cham. https://doi.org/10.1007/978-3-030-05342-0_1
Download citation
DOI: https://doi.org/10.1007/978-3-030-05342-0_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-05341-3
Online ISBN: 978-3-030-05342-0
eBook Packages: EngineeringEngineering (R0)