ABSTRACT
Map image text segmentation has always been one of the difficult tasks because of its variety. The texts in a map may have the myriad background consists of various intensity values, different orientations, overlapping objects, intersected lines etc. Common problems for text extraction from map images are the lack of prior knowledge of text features such as color, font, size and orientation as well as the location of the probable text regions. Extracted texts can be used as an input to OCR for recognition. This paper presents an approach for text segmentation from map images using fuzzy graph analysis. Fuzzy graph is constructed from the map image. Fuzzy similarity value between two nodes within text region will be higher than other non-text regions. Seed points are selected through the fuzzy graph analysis. These seed points lie within texts in a map image. F* seed growing algorithm is used here for text localization.
The originality of this work lies in the fuzzy graph construction from map image and selection of seed points. The proposed text segmentation approach is tested on a collected dataset of paper map images (containing texts in Indian languages; like Bangla, Hindi etc.) and the results are encouraging.
- Oxford bengali atlas, oxford school atlas. Oxford University Press, India. ISBN:0-19-567211-9.Google Scholar
- B. Chanda and D. D. Majumder. Digital image processing and analysis, 2000. ISBN: 81-203-1618-5.Google Scholar
- S. Biswas and A. K. Das. Text segmentation from scanned land map images using radon transform based projection profile. In Soft Computing and Pattern Recognition (SoCPaR), 2011 International Conference of, pages 413--418, oct. 2011.Google ScholarCross Ref
- S. Biswas and A. K. Das. Text extraction from scanned land map images. In IEEE/OSA/IAPR International Conference on Informatics, Electronics & Vision, Dhaka, pages 231--236, May 2012.Google ScholarCross Ref
- R. Cao and C. L. Tan. Text/graphics separation in maps. In In Proceedings of the 4th International Workshop on Graphics Recognition Algorithms and Applications, pages 245--254, 2001. Google ScholarDigital Library
- S. P. Chowdhury, S. Mandal, A. K. Das, and B. Chanda. Segmentation of text and graphics from document images. In ICDAR, pages 619--623, 2007. Google ScholarDigital Library
- B. Epshtein, E. Ofek, and Y. Wexler. Detecting text in natural scenes with stroke width transform. In CVPR, pages 2963--2970, 2010.Google ScholarCross Ref
- R. C. Gonzalez and R. E. Woods. Digital image processing, 2nd ed., 2002. ISBN:0201180758. Google ScholarDigital Library
- N. Journet, V. Eglin, J. Ramel, and R. Mullot. Text/graphic labelling of ancient printed documents. In Document Analysis and Recognition, 2005. Proceedings. Eighth International Conference on, pages 1010--1014 Vol. 2, aug.-1 sept. 2005. Google ScholarDigital Library
- Q. Li, Q. Zou, D. Zhang, and Q. Mao. Fosa: F* seed-growing approach for crack-line detection from pavement images. Image and Vision Computing, 29(12): 861--872, 2011. Google ScholarDigital Library
- S. Makrogiannis, G. Economou, S. Fotopoulos, and N. G. Bourbakis. Segmentation of color images using multiscale clustering and graph theoretic region synthesis. IEEE Transactions on Systems, Man, and Cybernetics, Part A, 35(2): 224--238, 2005. Google ScholarDigital Library
- S. Mathew and M. Sunitha. Node connectivity and arc connectivity of a fuzzy graph. Information Sciences, 180(4): 519--531, 2010. Google ScholarDigital Library
- S. Mathew and M. S. Sunitha. Types of arcs in a fuzzy graph. Inf. Sci., 179(11): 1760--1768, May 2009. Google ScholarDigital Library
- A. Mishra, K. Alahari, and C. V. Jawahar. An mrf model for binarization of natural scene text. In ICDAR, pages 11--16, 2011. Google ScholarDigital Library
- W. Pan, T. Bui, and C. Suen. Text segmentation from complex background using sparse representations. In Document Analysis and Recognition, 2007. ICDAR 2007. Ninth International Conference on, volume 1, pages 412--416, sept. 2007. Google ScholarDigital Library
- A. Pezeshk and R. L. Tutwiler. Improved multi angled parallelism for separation of text from intersecting linear features in scanned topographic maps. In ICASSP, pages 1078--1081, 2010.Google ScholarCross Ref
- A. Pezeshk and R. L. Tutwiler. Automatic feature extraction and text recognition from scanned topographic maps. IEEE T. Geoscience and Remote Sensing, 49(12): 5047--5063, 2011.Google ScholarCross Ref
- J. Pouderoux, J.-C. Gonzato, A. Pereira, and P. Guitton. Toponym recognition in scanned color topographic maps. In ICDAR, pages 531--535, 2007. Google ScholarDigital Library
- R. Raveaux, J.-C. Burie, and J.-M. Ogier. A colour text/graphics separation based on a graph representation. In ICPR, pages 1--4, 2008.Google ScholarCross Ref
- P. P. Roy, E. Vazquez, J. Lladós, R. Baldrich, and U. Pal. A system to segment text and symbols from color maps. In GREC, pages 245--256, 2007.Google Scholar
- H. Shen and J. Coughlan. Grouping using factor graphs: an approach for finding text with a camera phone. In Proceedings of the 6th IAPR-TC-15 international conference on Graph-based representations in pattern recognition, GbRPR'07, pages 394--403, Berlin, Heidelberg, 2007. Springer-Verlag. Google ScholarDigital Library
- L. Suolan, W. Jianguo, and W. Hongyuan. Fuzzy graph-theoretical clustering approach on spatial relationship constrain. In Proceedings of the 2011 International Conference on Intelligence Science and Information Engineering, ISIE '11, pages 9--12, Washington, DC, USA, 2011. IEEE Computer Society. Google ScholarDigital Library
- M. Tabassum and M. S. Uddin. Extraction of roi in geographical map image. Journal of Emerging Trends in Computing and Information Sciences (ISSN 2079-8407), 2(5): 237--242, 2011.Google Scholar
- H. J. Zimmermann. Fuzzy set theory and its application, 1996. ISBN: 81-7023-525-1.Google Scholar
Index Terms
- Fuzzy graph modeling for text segmentation from land map images
Recommendations
An investigation on m-polar fuzzy tolerance graph and its application
AbstractThe tolerance graph is a well-defined topic for a crisp graph theory. But, tolerance in a fuzzy graph is defined recently and many properties have been investigated. But, in a fuzzy graph, only one tolerance is considered for every vertex. But, in ...
Cliques and clique covers in fuzzy graphs1
This paper deals with fuzzy clique covers in fuzzy graphs. The definition of a fuzzy clique is modified so that the fuzzy subgraph induced by each fuzzy clique is complete. Then, fuzzy cliques and maximal fuzzy cliques are characterized. Finally, fuzzy ...
Fuzzy chromatic number of union of fuzzy graphs: An algorithm, properties and its application
AbstractWe focus on fuzzy graphs with crisp vertex and fuzzy edge sets. A concept of the fuzzy chromatic number of these graphs based on fuzzy independent vertex set is used in this paper. A modified algorithm called a fuzzy chromatic ...
Comments