Mudit Agrawal
ABSTRACT
This paper presents a dynamic approach to document page segmentation based on inter-component relationships, local patterns and context features. State-of-the art page segmentation algorithms segment zones based on local properties of neighboring connected components such as distance and orientation, and do not typically consider additional properties other than size. Our proposed approach uses a contextually aware and dynamically adaptive page segmentation scheme. The page is first over-segmented using a dynamically adaptive scheme of separation features based on [2] and adapted from [13]. A decision to form zones is then based on the context built from these local separation features and high-level content features. Zone-based evaluation was performed on sets of printed and handwritten documents in English and Arabic scripts with multiple font types, sizes and we achieved an increase of 15% over the accuracy reported in [2].
- W. Abd Almageed, M. Agrawal, W. Seo, and D. Doermann. Document-zone classification using partial least squares and hybrid classifiers. Int'l Conf. on Patt. Reco., pages 1--4, 2008.Google Scholar
- M. Agrawal and D. Doermann. Voronoi++: A dynamic page segmentation approach based on voronoi and docstrum features. In Proc. 10th Int'l Conf. on Doc. Analysis and Reco., pages 1011--1015, 2009. Google ScholarDigital Library
- A. Antonacopoulos and R. Ritchings. Flexible page segmentation using the background. In Proc. 12th Int'l Conf. on Patt. Reco., volume 2, pages 339--344, Oct 1994.Google ScholarCross Ref
- H. S. Baird. Background structure in document images. In Advances in Structural and Syntactic Pattern Recognition, pages 17--34. World Scientific, 1994.Google Scholar
- T. M. Breuel. Two geometric algorithms for layout analysis. In Workshop on Document Analysis Systems, pages 188--199. Springer-Verlag, 2002. Google ScholarDigital Library
- V. Ferrari, L. Fevrier, F. Jurie, and C. Schmid. Groups of adjacent contour segments for object detection. IEEE Trans. Patt. Anal. Mach. Intell., 30(1):36--51, 2008. Google ScholarDigital Library
- L. A. Fletcher and R. Kasturi. A robust algorithm for text string separation from mixed text/graphics images. IEEE Trans. Pattern Anal. Mach. Intell., 10(6):910--918, 1988. Google ScholarDigital Library
- I. Guyon, R. M. Haralick, J. J. Hull, and I. T. Phillips. Data sets for ocr and document image understanding research. In Proc. of SPIE - Document Recognition IV, pages 779--799. World Scientific, 1997.Google ScholarCross Ref
- F. Hones and J. Lichter. Layout extraction of mixed-mode documents. Mach. Vision Appl., 7(4):237--246, 1994. Google ScholarDigital Library
- A. Jain and Y. Zhong. Page segmentation using texture analysis. Patt. Reco., 29(5):743--770, May 1996. Google ScholarDigital Library
- A. K. Jain and S. Bhattacharjee. Text segmentation using gabor filters for automatic document processing. Mach. Vision Appl., 5(3):169--184, 1992. Google ScholarDigital Library
- N. Kato, M. Suzuki, S. Omachi, H. Aso, and Y. Nemoto. A handwritten character recognition system using directional element feature and asymmetric mahalanobis distance. IEEE Trans. Patt. Anal. Mach. Intell., 21(3):258--262, 1999. Google ScholarDigital Library
- K. Kise, A. Sato, and M. Iwata. Segmentation of page images using the area voronoi diagram. Comput. Vis. Image Underst., 70(3):370--382, 1998. Google ScholarDigital Library
- D. G. Lowe. Distinctive image features from scale-invariant keypoints. Int'l J. Comput. Vision, 60(2):91--110, 2004. Google ScholarDigital Library
- S. J. M. Roth and D. Doermann. Gedi: Ground truth. editor and document interface. In Summit on Arabic and Chinese Handwriting Recognition, 2006.Google Scholar
- S. Mao and T. Kanungo. Automatic training of page segmentation algorithms: An optimization approach. In Proc. of Int'l Conf. on Patt. Reco., pages 531--534, 2000.Google Scholar
- G. Nagy, S. Seth, and M. Viswanathan. A prototype document image analysis system for technical journals. Computer, 25(7):10--22, 1992. Google ScholarDigital Library
- N. Normand and C. Viard-Gaudin. A background based adaptive page segmentation algorithm. In Proc. 3rd Int'l Conf. on Doc. Analysis and Reco., page 138, Washington, DC, USA, 1995. IEEE Computer Society. Google ScholarDigital Library
- L. O'Gorman. The document spectrum for page layout analysis. IEEE Trans. Patt. Anal. Mach. Intell., 15(11):1162--1173, 1993. Google ScholarDigital Library
- T. Ojala, M. Pietikäinen, and T. Mäenpää. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Trans. Pattern Anal. Mach. Intell., 24(7):971--987, 2002. Google ScholarDigital Library
- T. Pavlidis and J. Zhou. Page segmentation and classification. CVGIP: Graph. Models Image Process., 54(6):484--496, 1992. Google ScholarDigital Library
- I. Sekita, R. Mori, K. Yamamoto, H. Yamada, and K. Toraichi. Feature extraction of handwritten japanese characters by spline functions for relaxation matching. Patt. Reco., 21(1):9--17, 1988. Google ScholarDigital Library
- W. Seo, M. Agrawal, and D. Doermann. Performance evaluation tools for zone segmentation and classification (PETS). Int'l Conf. on Patt. Reco., 2010. Google ScholarDigital Library
- F. Shafait, D. Keysers, and T. M. Breuel. Performance comparison of six algorithms for page segmentation. In 7th IAPR Workshop on Document Analysis Systems, pages 368--379. Springer, 2006. Google ScholarDigital Library
- Y. Wang, I. T. Phillips, and R. M. Haralick. Document zone content classification and its performance evaluation. Patt. Reco., 39(1):57--73, 2006. Google ScholarDigital Library
- K. Y. Wong, R. G. Casey, and F. M. Wahl. Document Analysis System. j-IBM-JRD, 26(6):647--656, Nov. 1982. Google ScholarDigital Library
Recommendations
A robust page segmentation method for Persian/Arabic documents
ISCGAV'05: Proceedings of the 5th WSEAS International Conference on Signal Processing, Computational Geometry & Artificial VisionOptical Character Recognition (OCR) softwares are widely used in the office automation systems. One of the first steps in the recognition of the documents is to segment the input image. Various methods have been offered for the English language. For the ...
Voronoi++: A Dynamic Page Segmentation Approach Based on Voronoi and Docstrum Features
ICDAR '09: Proceedings of the 2009 10th International Conference on Document Analysis and RecognitionThis paper presents a dynamic approach to document page segmentation. Current page segmentation algorithms lack the ability to dynamically adapt local variations in the size, orientation and distance of components within a page. Our approach builds upon ...
Extending Page Segmentation Algorithms for Mixed-Layout Document Processing
ICDAR '11: Proceedings of the 2011 International Conference on Document Analysis and RecognitionThe goal of this work is to add the capability to segment documents containing text, graphics, and pictures in the open source OCR engine OCRopus. To achieve this goal, OCRopus' RAST algorithm was improved to recognize non-text regions so that mixed ...
Comments