Overlapped text segmentation using Markov random field and aggregation

Separating machine printed text and handwriting from overlapping text is a challenging problem in the document analysis field and no reliable algorithms have been developed thus far. In this paper, we propose a novel approach for separating handwriting from binary image of overlapped text. Instead of using fixed size training patches, we describe an aggregation method which uses shape context features to extract training samples automatically. We use a Markov Random Field (MRF) to model the overlapped text. The neighbor system is inherited from a coarsening procedure and the prior and likelihood of the MRF is learned based on a distance metric. Experimental results show that the proposed method can achieve 87.97% recall for handwriting and 91.44% recall for machine printed text.

[1]  Jinhong Katherine Guo,et al.  Separating handwritten material from machine printed text using hidden Markov models , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[2]  Sargur N. Srihari,et al.  Interpretation of handwritten addresses in US mailstream , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).

[3]  William T. Freeman,et al.  Example-Based Super-Resolution , 2002, IEEE Computer Graphics and Applications.

[4]  L. Davis,et al.  Iterative figure-ground discrimination , 2004, ICPR 2004.

[5]  Ronen Basri,et al.  Image Segmentation by Probabilistic Bottom-Up Aggregation and Cue Integration , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[6]  Venu Govindaraju,et al.  Handwritten Carbon Form Preprocessing Based on Markov Random Field , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  George Nagy,et al.  DOCUMENT ANALYSIS WITH AN EXPERT SYSTEM , 1986 .

[8]  William T. Freeman,et al.  Learning low-level vision , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[9]  Greg Hamerly,et al.  Learning the k in k-means , 2003, NIPS.

[10]  Fei Wang,et al.  Multilevel Belief Propagation for Fast Inference on Markov Random Fields , 2007, Seventh IEEE International Conference on Data Mining (ICDM 2007).

[11]  Lawrence O'Gorman,et al.  The Document Spectrum for Page Layout Analysis , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Jason J. Corso.  Discriminative modeling by Boosting on Multilevel Aggregates , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  C. V. Jawahar,et al.  Contextual restoration of severely degraded document images , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[15]  Shimon Ullman,et al.  Combined Top-Down/Bottom-Up Segmentation , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Jitendra Malik,et al.  Shape matching and object recognition using shape contexts , 2010, 2010 3rd International Conference on Computer Science and Information Technology.

[17]  Venu Govindaraju,et al.  Markov Random Field Based Text Identification from Annotated Machine Printed Documents , 2009, 2009 10th International Conference on Document Analysis and Recognition.

[18]  David S. Doermann,et al.  Machine printed text and handwriting identification in noisy document images , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.