Abstract
In this paper, we make an attempt to give graph representation to handwritten Devanagari words. Each edge in resulted word graph is weighted with its corresponding stretching (or length). For transforming/embedding word graphs into feature vectors their Eigen decomposition aka spectral decomposition is carried out from their weighted associated matrices. Since, these associated matrices contain complementary information we fused their sorted Eigen values at decision level by exploiting multi-class support vector machines (SVM). In order to corroborate the experimental results, we employed Legal amount dataset. From the experimentation, we observe some interesting insights that might be useful for future investigations.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
There is a subtle difference between labelled graph and weighted graph, however, in this paper, we have used them interchangeable.
- 2.
Eigen decomposition and spectral decomposition refer the same thing.
- 3.
Spectrum (Eigen values) is singular but spectra is plural.
References
Madhvanath, S., Govindaraju, V.: The role of holistic paradigms in handwritten word recognition. IEEE Trans. Pattern Anal. Mach. Intell. 23(2), 149–64 (2001)
Pal, U., Roy, P.P., Tripathy, N., Lladós, J.: Multi-oriented Bangla and Devnagari text recognition. Pattern Recogn. 43(12), 4124–4136 (2010)
Shaw, B., Parui, S.K., Shridhar, M.: Offline handwritten Devanagari word recognition: a segmentation based approach. In: 19th International Conference on Pattern Recognition (ICPR), pp. 1–4 (2008)
Pal, U., Roy, R.K., Kimura, F.: Multi-lingual city name recognition for Indian postal automation. In: Proceedings - International Workshop on Frontiers in Handwriting Recognition (IWFHR) (1), pp. 169–173 (2012)
Malakar, S., Sharma, P., Singh, P.K., Das, M., Sarkar, R., Nasipuri, M.: A holistic approach for handwritten Hindi word recognition. Int. J. Comput. Vis. Image Process. (IJCVIP) 7(1), 59–78 (2017)
Shaw, B., Bhattacharya, U., Parui, S.K.: Offline handwritten Devanagari word recognition: information fusion at feature and classifier levels. In: 3rd IAPR Asian Conference on Pattern Recognition (ACPR), 09 June 2015 (2015)
Bhat, M.I., Sharada, B.: Automatic recognition of legal amounts on Indian bank cheques: a fusion-based approach at feature and decision levels. Int. J. Comput. Vis. Image Process. (IJCVIP) 10(4), 54–73 (2020)
Conte, D., Foggia, P., Sansone, C., Vento, M.: Thirty years of graph matching in pattern recognition. Int. J. Pattern Recogn. Artif. Intell. (IJPRAI) 18(03), 265–298 (2004)
Kandel, A., Bunke, H., Last, M.: Applied Graph Theory in Computer Vision and Pattern Recognition. Studies in Computational Intelligence, vol. 52. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-68020-8
Riesen, K., Bunke, H.: Graph classification based on vector space embedding. Int. J. Pattern Recogn. Artif. Intell. (IJPRAI) 23(06), 1053–1081 (2009)
Lempitsky, V., Kohli, P., Rother, C., Sharp, T.: Image segmentation with a bounding box prior. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 277–284 (2009)
Lee, J.D.: Object Detection. Brigham Young Robotic Vision Class 163050048, 11–26 (2011)
Chen, H.M., Varshney, P.K., Slamani, M.A.: On registration of Regions of Interest (ROI) in video sequences. In: Proceedings - IEEE Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 313–318 (2003)
Stauffer, M., Fischer, A., Riesen, K.: A novel graph database for handwritten word images. In: Robles-Kelly, A., Loog, M., Biggio, B., Escolano, F., Wilson, R. (eds.) S+SSPR 2016. LNCS, vol. 10029, pp. 553–563. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-49055-7_49
Deza, M.M., Deza, E.: Encyclopedia of Distances. Springer (2012)
Schmidt, M., Palm, G., Schwenker, F.: Spectral graph features for the classification of graphs and graph sequences. Comput. Stat. 29(1–2), 65–80 (2014). https://doi.org/10.1007/s00180-012-0381-6
Chung, F.R.K.: Spectral graph theory. ACM SIGACT News 30, 14 (1999)
Brouwer, A.E., Haermers, W.H.: Spectra of Graphs. Universitext. Springer, New York (2012). https://doi.org/10.1007/978-1-4614-1939-6
Cvetkovic, D.M., et al.: Recent Results in the Theory of Graph Spectra, vol. 36. Elsevier (1991)
Jayadevan, R., Kolhe, S.R., Patil, P.M., Pal, U.: Database development and recognition of handwritten Devanagari legal amount words. In: International Conference on Document Analysis and Recognition (ICDAR), Beijing, pp. 304–308 (2011)
Malik, L.: A graph based approach for handwritten Devanagari word recognition. In: International Conference on Emerging Trends in Engineering & Technology, vol. 1 (2012). 2012-42
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Bhat, M.I., Sharada, B., Sinha, M.K. (2022). A Graph-Based Holistic Recognition of Handwritten Devanagari Words: An Approach Based on Spectral Graph Embedding. In: Santosh, K., Hegadi, R., Pal, U. (eds) Recent Trends in Image Processing and Pattern Recognition. RTIP2R 2021. Communications in Computer and Information Science, vol 1576. Springer, Cham. https://doi.org/10.1007/978-3-031-07005-1_25
Download citation
DOI: https://doi.org/10.1007/978-3-031-07005-1_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-07004-4
Online ISBN: 978-3-031-07005-1
eBook Packages: Computer ScienceComputer Science (R0)