A CRF Based Scheme for Overlapping Multi-colored Text Graphics Separation

In this paper, we propose a novel framework for segmentation of documents with complex layouts. The document segmentation is performed by combination of clustering and conditional random fields (CRF) based modeling. The bottom-up approach for segmentation assigns each pixel to a cluster plane based on color intensity. A CRF based discriminative model is learned to extract the local neighborhood information in different cluster/color planes. The final category assignment is done by a top-level CRF based on the semantic correlation learned across clusters. The proposed framework has been extensively tested on multi-colored document images with text overlapping graphics/image.

[1]  T. Sivatanabe,et al.  Layout analysis of complex documents , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[2]  Santanu Chaudhury,et al.  Model-Guided Segmentation and Layout Labelling of Document Images Using a Hierarchical Conditional Random Field , 2009, PReMI.

[3]  Nicolai Petkov,et al.  Comparison of texture features based on Gabor filters , 1999, Proceedings 10th International Conference on Image Analysis and Processing.

[4]  Nello Cristianini,et al.  Large Margin DAGs for Multiclass Classification , 1999, NIPS.

[5]  Azriel Rosenfeld,et al.  Document structure analysis algorithms: a literature survey , 2003, IS&T/SPIE Electronic Imaging.

[6]  Andrew Zisserman,et al.  A Visual Vocabulary for Flower Classification , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[7]  Nasser Sherkat,et al.  Use of colour in form layout analysis , 2001, Proceedings of Sixth International Conference on Document Analysis and Recognition.

[8]  Michelangelo Ceci,et al.  A color-based layout analysis to process censorship cards of film archives , 2005, Eighth International Conference on Document Analysis and Recognition (ICDAR'05).

[9]  Scott T. Acton,et al.  Document page segmentation using multiscale clustering , 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348).

[10]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[11]  Stefano Messelodi,et al.  Geometric Layout Analysis Techniques for Document Image Understanding: a Review , 2008 .

[12]  Jules-Raymond Tapamo,et al.  A texture-based method for document segmentation and classification , 2006, South Afr. Comput. J..

[13]  N. Na.  THE SCIENCE OF COLOR , 1952 .

[14]  Toyohide Watanabe,et al.  Layout Analysis of Complex Documents , 2000, ICPR.

[15]  Stephen W. K. Lam,et al.  A Local-to-Global Approach to Complex Document Layout Analysis , 1994, MVA.

[16]  Mausumi Acharyya,et al.  Document image segmentation using wavelet scale-space features , 2002, IEEE Trans. Circuits Syst. Video Technol..

[17]  Dimosthenis Karatzas,et al.  Text Segmentation in Colour Posters from the Spanish Civil War Era , 2009, 2009 10th International Conference on Document Analysis and Recognition.

[18]  Sunil Kumar,et al.  Text Extraction and Document Image Segmentation Using Matched Wavelets and MRF Model , 2007, IEEE Transactions on Image Processing.

[19]  C. Strouthopoulos,et al.  Text identification in color documents , 2003, 3rd International Symposium on Image and Signal Processing and Analysis, 2003. ISPA 2003. Proceedings of the.

[20]  Gaurav Sharma,et al.  Curvature feature distribution based classification of Indian scripts from document images , 2009, MOCR '09.