Touching Text Character Localization in Graphical Documents Using SIFT
- 554 Downloads
Interpretation of graphical document images is a challenging task as it requires proper understanding of text/graphics symbols present in such documents. Difficulties arise in graphical document recognition when text and symbol overlapped/touched. Intersection of text and symbols with graphical lines and curves occur frequently in graphical documents and hence separation of such symbols is very difficult.
Several pattern recognition and classification techniques exist to recognize isolated text/symbol. But, the touching/overlapping text and symbol recognition has not yet been dealt successfully. An interesting technique, Scale Invariant Feature Transform (SIFT), originally devised for object recognition can take care of overlapping problems. Even if SIFT features have emerged as a very powerful object descriptors, their employment in graphical documents context has not been investigated much. In this paper we present the adaptation of the SIFT approach in the context of text character localization (spotting) in graphical documents. We evaluate the applicability of this technique in such documents and discuss the scope of improvement by combining some state-of-the-art approaches.
KeywordsSupport Vector Machine Text Component Graphical Line Document Image Scale Invariant Feature Transform
Unable to display preview. Download preview PDF.
- 2.Fletcher, L.A., Kasturi, R.: A robust algorithm for text string separation from mixed text/graphics images. IEEE Transactions on PAMI 10(6), 910–918 (1988)Google Scholar
- 4.Luo, H., Agam, G., Dinstein, I.: Directional mathematical morphology approach for line thinning and extraction of character strings from maps and line drawings. In: Proceedings of the ICDAR, Washington, DC, USA, p. 257 (1995)Google Scholar
- 7.Bicego, M., Lagorio, A., Grosso, E., Tistarelli, M.: On the use of SIFT features for face authentication. In: Proceedings of CVPRW, USA, p. 35 (2006)Google Scholar
- 8.Rusiñol, M., Lladós, J.: Word and Symbol Spotting Using Spatial Organization of Local Descriptors. In: Proceedings of IAPR Workshop on DAS, pp. 489–496 (2008)Google Scholar
- 10.Tombre, K., Lamiroy, B.: Graphics recognition - from re-engineering to retrieval. In: Proceedings of the ICDAR, pp. 148–155 (2003)Google Scholar
- 11.Roy, P.P., Pal, U., Lladós, J., Delalandre, M.: Multi-oriented and multi-sized touching character segmentation using dynamic programming. In: Proceedings of ICDAR, Barcelona, Spain, pp. 11–15 (2009)Google Scholar