Generic Document Image Dewarping by Probabilistic Discretization of Vanishing Points

Document images dewarping is still a challenge especially when documents are captured with one camera in an uncontrolled environment. In this paper we propose a generic approach based on vanishing points (VP) to reconstruct the 3D shape of document pages. Unlike previous methods we do not need to segment the text included in the documents. Therefore, our approach is less sensitive to pre-processing and segmentation errors. The computation of the VPs is robust and relies on the a-contrario framework, which has only one parameter whose setting is based on probabilistic reasoning instead of experimental tuning. Thus, our method can be applied to any kind of document including text and non-text blocks and extended to other kind of images. Experimental results show that the proposed method is robust to a variety of distortions.

[1]  Syed Saqib Bukhari,et al.  An Image Based Performance Evaluation Method for Page Dewarping Algorithms Using SIFT Features , 2011, CBDAR.

[2]  Yu Zhang,et al.  Restoring camera-captured distorted document images , 2014, International Journal on Document Analysis and Recognition (IJDAR).

[3]  Changsong Liu,et al.  A cylindrical surface model to rectify the bound document image , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[4]  Scott Workman,et al.  Detecting Vanishing Points Using Global Image Context in a Non-ManhattanWorld , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Rafael Grompone von Gioi,et al.  LSD: a Line Segment Detector , 2012, Image Process. Line.

[6]  Yu Zhang,et al.  A fast and stable approach for restoration of warped document images , 2005, Eighth International Conference on Document Analysis and Recognition (ICDAR'05).

[7]  Anthony Hoogs,et al.  A Minimum Error Vanishing Point Detection Approach for Uncalibrated Monocular Images of Man-Made Environments , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Hui Ren,et al.  A New Vanishing Point Detection Algorithm Based on Hough Transform , 2010, 2010 Third International Joint Conference on Computational Science and Optimization.

[9]  Salvatore Tabbone,et al.  Camera-captured document image perspective distortion correction using vanishing point detection based on Radon transform , 2016, 2016 23rd International Conference on Pattern Recognition (ICPR).

[10]  Ioannis Pratikakis,et al.  A Two-Step Dewarping of Camera Document Images , 2008, 2008 The Eighth IAPR International Workshop on Document Analysis Systems.

[11]  Bernd Michaelis,et al.  Book Scanner Dewarping with Weak 3d Measurements and a Simplified Surface Model , 2008, DGCI.

[12]  David S. Doermann,et al.  Geometric Rectification of Camera-Captured Document Images , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Yuandong Tian,et al.  Rectification and 3D reconstruction of curved document images , 2011, CVPR 2011.

[14]  Nam Ik Cho,et al.  Document dewarping via text-line based optimization , 2015, Pattern Recognit..

[15]  Syed Saqib Bukhari,et al.  The IUPR Dataset of Camera-Captured Document Images , 2011, CBDAR.

[16]  Andreas Dengel,et al.  Document Image Dewarping using Deep Learning , 2019, ICPRAM.

[17]  Jean-Michel Morel,et al.  From Gestalt Theory to Image Analysis: A Probabilistic Approach , 2007 .

[18]  Christoph H. Lampert,et al.  Document capture using stereo vision , 2004, DocEng '04.

[19]  Syed Saqib Bukhari,et al.  Performance evaluation of curled textline segmentation algorithms on CBDAR 2007 dewarping contest dataset , 2010, 2010 IEEE International Conference on Image Processing.

[20]  Atsushi Yamashita,et al.  Shape reconstruction and image restoration for non-flat surfaces of documents with a stereo vision system , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[21]  Salvatore Tabbone,et al.  Robust Perspective Rectification of Camera-Captured Document Images , 2017, 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR).

[22]  Roberto Manduchi,et al.  Towards Mobile OCR: How to Take a Good Picture of a Document Without Sight , 2015, DocEng.

[23]  Nam Ik Cho,et al.  State Estimation in a Document Image and Its Application in Text Block Identification and Text Line Extraction , 2010, ECCV.

[24]  Dimitris Samaras,et al.  DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[25]  Christoph H. Lampert,et al.  Document image dewarping using robust estimation of curled text lines , 2005, Eighth International Conference on Document Analysis and Recognition (ICDAR'05).

[26]  Marie-Odile Berger,et al.  A-Contrario Horizon-First Vanishing Point Detection Using Second-Order Grouping Laws , 2018, ECCV.

[27]  Nam Ik Cho,et al.  Robust Document Image Dewarping Method Using Text-Lines and Line Segments , 2017, 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR).

[28]  Dimitris Samaras,et al.  DocUNet: Document Image Unwarping via a Stacked U-Net , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.