Text Segmentation from Bangla Land Map Images

• Autorzy: Biswas S. , Das A. K , Chanda B.
• Języki publikacji: EN

Abstrakty

EN

Text segmentation from land map images is a non-trivial task as map components are interleaved and overlapped in a complex spatial form. The characters in a word in most of the Indic languages, including Bangla (the 6th most spoken language in the world), are connected through a headline (”matra” or ”shirorekha”) which makes the corresponding word a single component. It has been observed that the Delaunay triangulation (DT) forms a number of small triangles on the text regions compared to other regions of the map - a property very much discernible for Bangla (and some other Indic scripts) texts. This property is primarily exploited here to segment text from the complex background of the land map images. The proposed text segmentation approach is tested and compared with an existing method on a collected dataset of paper map images( containing Bangla, an Indian regional language texts) and the results are encouraging.

Słowa kluczowe

EN

map image analysis; Delaunay triangulation

• Wydawca: Instytut Telekomunikacji i Informatyki Uniwersytetu Technologiczno-Przyrodniczego w Bydgoszczy
• Czasopismo: Image Processing & Communications
• Rocznik: 2014
• Tom: Vol. 19, no. 1
• Strony: 21--34
• Opis fizyczny: Bibliogr. 34 poz.

Twórcy

autor

Biswas S.

• Dept. of CST, Indian Institute of Engineering Science and Technology, Shibpur, Howrah, India

autor

Das A. K

• Dept. of CST, Indian Institute of Engineering Science and Technology, Shibpur, Howrah, India

autor

Chanda B.

• ECSU, Indian Statistical Institute, Kolkata

Bibliografia

• [1] Ahmed, S., Liwicki, M., Dengel, A. (2012). Extraction of text touching graphics using surf. Document Analysis Systems (DAS), 2012 10th IAPR International Workshop on, 349-353.
• [2] Ahmed, S., Weber, M., Liwicki, M., Dengel, A. (2011). Text/graphics segmentation in architectural floor plans. Document Analysis and Recognition (ICDAR), 2011 International Conference on, 734-738.
• [3] Biswas, S., Das, A. K. (2012). Fuzzy graph mod eling for text segmentation from land map images. Proceedings of the Eighth Indian Conference on Computer Vision, Graphics and Image Processing, 75-757.
• [4] Biswas, S., Mandal, S., Das, A. K., Chanda, B., (2014). Land Map Images Binarization Based on Distance Transform and Adaptive Threshold. Document Analysis Systems (DAS), 2014 11th IAPR International Workshop on, 334-338.
• [5] Cao, R., Tan, C. L., (2002). Text/graphics separation in maps. Graphics Recognition Algorithms and Applications, 176-177.
• [6] Chaudhuri, B. B., Pal, U., (1997). An ocr system to read two indian language scripts: Bangla and devnagari (hindi). Document Analysis and Recognition, 1997., Proceedings of the Fourth International Conference on, 2, 1011-1015.
• [7] Degenhardt, J., Recht, P., (2008). On a relation between the cycle packing number and the cyclomatic number of a graph. : manuscript.
• [8] Dhar, D. B., Chanda, B., (2006). Extraction and recognition of geographical features from paper maps. International Journal of Document Analysis and Recognition (IJDAR), 8(4), 232-245.
• [9] Epshtein, B., Ofek, E., Wexler, Y., (2010). Detecting text in natural scenes with stroke width transform. Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, 2963-2970.
• [10] Fletcher, L. A., Kasturi, R., (1988). A robust algorithm for text string separation from mixed text/- graphics images. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 10(6), 910-918.
• [11] Gatos, B., Ntirogiannis, K., Pratikakis, I. (2009). ICDAR 2009 Document Image Binarization Contest (DIBCO 2009). In ICDAR 9, 1375-1382.
• [12] Hoang, T. V., Tabbone, S., (2010). Text extraction from graphical document images using sparse representation. Proceedings of the 9th IAPR International Workshop on Document Analysis Systems, 143-150.
• [13] Huang, R., Shivakumara, P., Uchida, S., (2013). Scene Character Detection by an Edge-Ray Filter. Document Analysis and Recognition (ICDAR), 462-466.
• [14] Imade, S., Tatsuta, S., Wada, T., (1993). Segmentation and classification for mixed text/image documents using neural network. Document Analysis and Recognition, 930-934.
• [15] Jordan, M. I., Ghahramani, Z., Jaakkola, T. S., Saul, L. K., (1999). An introduction to variational methods for graphical models. Machine learning, 37(2), 183-233.
• [16] Journet, N., Eglin, V., Ramel, J. Y., Mullot, R., (2005). Text/graphic labelling of ancient printed documents. In Document Analysis and Recognition. Document Analysis and Recognition, 2005. Proceedings. Eighth International Conference on, 2, 1010-1014.
• [17] Kim, Z. (2006). Realtime obstacle detection and tracking based on constrained delaunay triangulation. Intelligent Transportation Systems Conference, 2006. ITSC’06. IEEE, 548-553.
• [18] Li, L., Nagy, G., Samal, A., Seth, S., Xu, Y., (2000). Cooperative text and line-art extraction from a topographic map. Document Analysis and Recognition, 1999. ICDAR’99. Proceedings of the Fifth International Conference on, 2(4), 177-185.
• [19] Mishra, A., Alahari, K., Jawahar, C. V., (2011). An mrf model for binarization of natural scene text. Document Analysis and Recognition (ICDAR), 2011 International Conference on, 11-16.
• [20] Pezeshk, A., Tutwiler, R. L., (2010). Improved multi angled parallelism for separation of text from intersecting linear features in scanned topographic maps. Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on, 1078-1081.
• [21] Pezeshk, A., Tutwiler, R. L., (2011). Automatic feature extraction and text recognition from scanned topographic maps. Geoscience and Remote Sensing, IEEE Transactions on, 49(12), 5047-5063.
• [22] Pons, J. P., Boissonnat, J. D., (2007). Delaunay deformable models: Topology-adaptive meshes based on the restricted delaunay triangulation. Computer Vision and Pattern Recognition, 2007. CVPR’07. IEEE Conference on, 1-8.
• [23] Ramakrishnan, K., Arvind, K. R., Ramakrishnan, A. G., (2007). Localization of handwritten text in documents using moment invariants and delaunay triangulation. Conference on Computational Intelligence and Multimedia Applications, 2007. International Conference on, 3, 408-414.
• [24] Regen, F. (2010). On cycles and independence in graphs. : Universitatsbibliothek Ilmenau.
• [25] Roy, P. P., Vazquez, E., Lladòs, J., Baldrich, R., Pal, U., (2007). A system to segment text and symbols from color maps. Graphics Recognition. Recent Advances and New Opportunities, 245-256.
• [26] Roy, P. P., Llados, J., Pal, U. (2007). Text/graphics separation in color maps. In Computing: Theory and Applications. Computing: Theory and Applications, 2007. ICCTA’07. International Conference on, 545-551.
• [27] Situ, L., Liu, R., Tan, a. C. L. (2011). Text localization in web images using probabilistic candidate selection model. Document Analysis and Recognition (ICDAR), 2011 International Conference on, 1359-1363.
• [28] Sloan, S. W. (1978). A fast algorithm for constructing delaunay triangulations in the plane. Advances in Engineering Software, 9(1), 34-55.
• [29] Tabassum, M., Uddin, M. S. (2011). Extraction of roi in geographical map image. Journal of Emerging Trends in Computing and Information Sciences, 2(5), 237-242.
• [30] Tofani, P., Kasturi, R., (1998). Segmentation of text from color map images. Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on, 1, 945-947.
• [31] Tombre, K., Tabbone, S., Pélissier, L., Lamiroy, B., Dosch, P., (2002). Text/graphics separation revisited. Document Analysis Systems V, 200-211.
• [32] Vincent, L. (1993). Morphological grayscale reconstruction in image analysis: applications and efficient algorithms. Image Processing, IEEE Transactions, 2(2), 176-201.
• [33] Watanabe, T., Zhang, R., (1997). Recognition of character strings from color urban map images on the basis of validation mechanism. Document Analysis and Recognition, 1997., Proceedings of the Fourth International Conference on, 805-808.
• [34] Zhou, L., Lu, Y., Tan, C. L., (2006). Bangla/English script identification based on analysis of connected component profiles. Document Analysis Systems VII, 243-254.