Abstract
This article presents a set of novel features for robust online Bangla handwritten character recognition. Two feature extraction methods are presented here. The first describes the transition from background to foreground pixels and vice versa. The second uses a combination of topological features and centre-of-gravity- (CG) based circular features where global information, local information, and Circular Quadrant Mass Distribution information have been extracted. The impact of each along with their combination have also been analyzed. A total of 15,000 isolated online Bangla character samples have been collected and used for the evaluation. A Support Vector Machine classifier records the best recognition rate when the transition count feature, CG-based circular features, and topological features are combined.
- S. Agarwal and V. Kumar. 2005. Online character recognition. In Proceedings of the 3rd International Conference on Information Technology and Applications. 698--703. Google Scholar
Digital Library
- B. B. Ahmed, S. Naz, M. I. Razzak, S. F. Rashid, M. Z. Afzal, and T. M. Breuel. 2016. Evaluation of cursive and non-cursive scripts using recurrent neural networks. Int. J. Neur. Comput. Appl. 27, 3 (2016), 603--613. Google Scholar
Digital Library
- F. Alvaro and R. Zanibbi. 2013. A shape-based layout descriptor for classifying spatial relationships in handwritten math. In Proceedings of the ACM Symposium on Document Engineering. 123--126. Google Scholar
Digital Library
- C. Bahlmann and H. Burkhardt. 2004. The writer independent online handwriting recognition system frog on hand and cluster generative statistical dynamic time warping. IEEE Trans. Pattern Anal. Mach. Intell. 26, 3 (2004), 299--310. Google Scholar
Digital Library
- A. Bandyopadhyay and B. Chakraborty. 2009. Development of online handwriting recognition system: A case study with handwritten bangla character. In Proceedings of the World Congress on Nature and Biologically Inspired Computing. 514--519.Google Scholar
- R. K. Bawa and R. Rani. 2011. A preprocessing technique for recognition of online handwritten gurmukhi numerals. In Proceedings of the International Conference on High Performance Architecture and Grid Computing. IEEE, 275--281.Google Scholar
- N. Bhattacharya, U. Pal, and F. Kimura. 2013. A system for bangla online handwritten text. In Proceedings of the International Conference on Document Analysis and Recognition. 1335--1339. Google Scholar
Digital Library
- U. Bhattacharya, R. Banerjee, S. Baral, R. Dey, and S. K. Parui. 2012. A semi automatic annotation scheme for Bangla online mixed cursive handwriting samples. In Proceedings of the International Conference on Frontiers in Handwriting Recognition. 680--685. Google Scholar
Digital Library
- U. Bhattacharya, B. K. Gupta, and S. K. Parui. 2007. Direction code based features for recognition of online handwritten characters of bangla. In Proceedings of the International Conference on Document Analysis and Recognition. 58--62. Google Scholar
Digital Library
- M. R. Bouguelia, S. Nowaczyk, and A. Verikas K. C. Santosh. 2017. Agreeing to disagree: Active learning with noisy labels without crowdsourcing. Int. J. Mach. Learn. Cybernet. (2017), 1--13.Google Scholar
- S. D. Connell, R. M. K. Sinha, and A. K. Jain. 2000. Recognition of unconstrained online devanagari characters. In Proceedings of the 15th International Conference on Pattern Recognition. 368--371.Google Scholar
- J. Demsar. 2006. Statistical comparisons of classifiers over multiple data sets. Int. J. Mach. Learn. Res. 7 (2006), 1--30. Google Scholar
Digital Library
- J. Du, J. Zhai, and J. Hu. 2017. Writer adaptation via deeply learned features for online Chinese handwriting recognition. Int. J. Doc. Anal. Recogn. 20, 1 (2017), 69--78. Google Scholar
Digital Library
- A. El-Sawy, H. EL-Bakry, and M. Loey. 2016. CNN for handwritten arabic digits recognition based on LeNet-5. In Proceedings of the International Conference on Advanced Intelligent Systems and Informatics. 566--575.Google Scholar
- M. Farha, G. Srinivasa, A. J. Ashwini, and K. Hemant. 2013. Online handwritten character recognition. Int. J. Comput. Sci. 11, 5 (2013), 30--36.Google Scholar
- G. A. Fink, S. Vajda, U. Bhattacharya, S. Parui, and B. B. Chaudhuri. 2010. Online bangla word recognition using sub-stroke level features and hidden markov models. In Proceedings of the International Conference on Frontiers in Handwriting Recognition. 393--398. Google Scholar
Digital Library
- V. Frinken, N. Bhattacharya, and U. Pal. 2014. Design of unsupervised feature extraction system for on-line handwriting recognition. In Proceedings of the 11th IAPR International Workshop on Document Analysis and Systems. 355--359. Google Scholar
Digital Library
- A. Fu, C. Dong, and L. Wang. 2015. An experimental study on stability and generalization of extreme learning machines. Int. J. Mach. Learn. Cybernet. 6, 1 (2015), 129--135.Google Scholar
Cross Ref
- R. Ghosh. 2015. A novel feature extraction approach for online bengali and devanagari character recognition. In Proceedings of the International Conference on Signal Processing and Integrated Networks. 483--488.Google Scholar
Cross Ref
- M. Gupta, N. Gupta, and R. Agrawal. 2012. Recognition of online handwritten gurmukhi strokes using support vector machine. In Proceedings of the International Conference on Bio-Inspired Computing: Theories and Application. 495--506.Google Scholar
- M. Hall, E. Frank, G. Holmes, B. Pfahringer, P. Reutemann, and I. H. Witten. 2009. The WEKA data mining software: An update. ACM SIGKDD Explor. Newslett. 11, 1 (2009), 10--18. Google Scholar
Digital Library
- N. Joshi, G. Sita, A. G. Ramakrishnan, and V. Deepu. 2005. Machine recognition of online handwritten devanagari characters. In Proceedings of the International Conference on Document Analysis and Recognition. 1156--1160. Google Scholar
Digital Library
- S. Kubatur, M. Sid-Ahmed, and M. Ahmadi. 2012. A neural network approach to online Devanagari handwritten character recognition. In Proceedings of the International Conference on High Performance Computing and Simulation.Google Scholar
- A. Kumar and S. Bhattacharya. 2010. Online devanagari isolated character recognition for the iPhone using hidden markov models. In Proceedings of the International Conference on Students’ Technology Symposium. 300--304.Google Scholar
- V. L. Lajish and S. K. Kopparapu. 2014. Online handwritten Devanagari stroke recognition using extended directional features. In Proceedings of the 8th International Conference on Signal Processing and Communication System. IEEE.Google Scholar
- T. Mondal, U. Bhattacharya, S. K. Parui, K. Das, and D. Mandalapu. 2010. Online handwriting recognition of indian scripts - the first benchmark. In Proceedings of the 12th International Conference on Frontiers in Handwriting Recognition. 200--205. Google Scholar
Digital Library
- S. K. Parui, K. Guin, U. Bhattacharya, and B. B. Chaudhuri. 2008. Online handwritten bangla character recognition using HMM. In Proceedings of the International Conference on Pattern Recognition. 1--4.Google Scholar
- J. R. Prasad and U. Kulkarni. 2015. Gujarati character recognition using adaptive neuro fuzzy classifier with fuzzy hedges. Int. J. Mach. Learn. Cybernet. 6, 5 (2015), 763--775.Google Scholar
Cross Ref
- J. D. Prusa and T. M. Khoshgoftaar. 2017. Improving deep neural network design with new text data representations. Int. J. Big Data 4, 7 (2017).Google Scholar
- K. Roy. 2012. Stroke-database design for online handwriting recognition in bangla. Int. J. Mod. Eng. Res. 2, 4 (2012), 2534--2540.Google Scholar
- K. Roy, N. Sharma, and U. Pal. 2007. Online bangla handwriting recognition system. In Proceedings of the International Conference on Advances in Pattern Recognition. 117--122.Google Scholar
- M. K. Sachan, G. Lehal Singh, and V. K. Jain. 2011. A novel method to segment online gurmukhi script. In Proceedings of the International Conference on Information Systems for Indian Languages. 1--8.Google Scholar
- M. K. Sachan, G. Lehal Singh, and V. K. Jain. 2011. A system for online gurmukhi script recognition. In Proceedings of the International Conference on Information Systems for Indian Languages. 299--300.Google Scholar
- K. C. Santosh and J. Iwata. 2012. Stroke-Based Cursive Character Recognition. Xiaoqing Ding, INTECH.Google Scholar
- K. C. Santosh, C. Nattee, and B. Lamiroy. 2012. Relative positioning of stroke-based clustering: A new approach to online handwritten devanagari character recognition. Int. J. Image Graph. 12, 2 (2012), 25 pages.Google Scholar
Cross Ref
- K. C. Santosh and L. Wendlingc. 2015. Character recognition based on non-linear multi-projection profiles measure. Int. J. Front. Comput. Sci. 9, 5 (2015), 678--690. Google Scholar
Digital Library
- S. P. Sen, A. Bhattacharyya, A. Das, R. Sarkar, and K. Roy. 2016. Design of novel feature vector for recognition of online handwritten bangla basic characters. In Proceedings of the 1st International Conference on First International Conference on Intelligent Computing 8 Communication. 485--494.Google Scholar
- S. P. Sen, M. Mitra, S. Chowdhury, R. Sarkar, and K. Roy. 2016. Quad-tree based image segmentation and feature extraction to recognize online handwritten bangla characters. In Proceedings of the 7th IAPR TC3 Workshop on Artificial Neural Networks in Pattern Recognition. Ulm, Germany, 246--256.Google Scholar
- S. P. Sen, R. Sarkar, and K. Roy. 2016. A simple and effective technique for online handwritten bangla character recognition. In Proceedings of the 4th International Conference on Frontiers in Intelligent Computing: Theory and Application. 201--209.Google Scholar
- S. P. Sen, R. Sarkar, K. Roy, and N. Hori. 2016. Recognize online handwritten bangla characters using hausdorff distance based feature. In Proceedings of the 5th International Conference on Frontiers in Intelligent Computing: Theory and Application. 541--549.Google Scholar
- A. Sharma and K. Dahiya. 2012. Online handwriting recognition of gurmukhi and devanagiri characters in mobile phone devices. In Proceedings of the International Conference on Recent Advances and Future Trends in Information Technology. 37--41.Google Scholar
- A. Sharma, R. Kumar, and R. K. Sharma. 2008. Online handwritten gurmukhi character recognition using elastic matching. In Proceedings of the Congress on Image and Signal Processing. IEEE, 391--396. Google Scholar
Digital Library
- A. Sharma, R. Kumar, and R. K. Sharma. 2009. Rearrangement of recognized strokes in online handwritten gurmukhi words recognition. In Proceedings of the 10th International Conference on Document Analysis and Recognition. 1241--1245. Google Scholar
Digital Library
- A. Sharma, R. Kumar, and R. K. Sharma. 2010. HMM-based online handwritten gurmukhi character recognition. Int. J. Mach. Graph. Vision 19, 4 (2010), 439--449. Google Scholar
Digital Library
- P. K. Singh, R. Sarkar, N. Das, S. Basu, and M. Nasipuri. 2014. Statistical comparison of classifiers for script identification from multi-script handwritten documents. Int. J. Appl. Pattern Recogn. 1, 2 (2014), 152--172.Google Scholar
Cross Ref
- H. Swethalakshmi, A. Jayaraman, V. S. Chakravarthy, and C. C. Sekhar. 2006. Online handwritten character recognition for devanagari and telugu scripts using support vector machines. In Proceedings of the International Workshop on Frontiers in Handwriting Recognition. 367--372.Google Scholar
- H. Swethalakshmi, C. C. Sekhar, and V. S. Chakravarthy. 2007. Spatiostructural features for recognition of online handwritten characters in Devanagari and Tamil scripts. In Proceedings of the International Conference on Artificial Neural Networks. 230--239. Google Scholar
Digital Library
- X. Tang, Y. Ding, and K. Hao. 2017. A novel method based on line-segment visualizations for hyper-parameter optimization in deep networks. Int. J. Pattern Recogn. Artif. Intell. 32, 3 (2017), 1851002-1--1851002-15.Google Scholar
Cross Ref
- C. C. Tappert, C. Y. Suen, and T. Wakahara. 1990. The state of online handwriting recognition. In Transaction on Pattern Analysis and Machine Intelligence. IEEE 12, 8 (1990), 787--808. Google Scholar
Digital Library
- A. Tripathi, S. S. Paul, and V. K. Pandey. 2012. Standardisation of stroke order for online isolated Devanagari character recognition for iPhone. In Proceedings of the International Conference on Technology Enhanced Education. IEEE, 1--5.Google Scholar
- Gerrit J. J. van den Burg and Patrick J. F. Groenen. 2016. GenSVM: A generalized multiclass support vector machine. J. Mach. Learn. Res. 17, 225 (2016), 1--42. Google Scholar
Digital Library
- G. D. Vescovo and A. Rizzi. 2007. Online handwriting recognition by the symbolic histograms approach. In Proceedings of the International Conference on Granular Computing. IEEE, 686--690. Google Scholar
Digital Library
- W. Wang, G.Tan, and H. Wang. 2017. Cross-domain comparison of algorithm performance in extracting aspect-based opinions from chinese online reviews. Int. J. Machine. Learn. Cybernet. 8, 3 (2017), 1053--1070.Google Scholar
Cross Ref
- Q. Wu, Z. Gui, S. Li, and J. Ou. 2017. Directly connected convolutional neural networks. Int. J. Pattern Recogn. Artif. Intell. 32, 5 (2017), 1859007-1--1859007-17.Google Scholar
Cross Ref
- M. F. Zafar, D. Mohammad, and M. M. Anwar. 2006. Recognition of online isolated handwritten characters by back propagation neural nets using sub-character primitive features. In Proceedings of the 9th International Conference on INMIC. IEEE, 157--162.Google Scholar
- W. Zhao, J. F. Liu, and X. L. Tang. 2002. Online handwritten english word recognition based on cascade connection of character HMMs. In Proceedings of the International Conference on Machine Learning and Cybernetics. IEEE, 1758--1761.Google Scholar
Index Terms
Application of Structural and Topological Features to Recognize Online Handwritten Bangla Characters
Recommendations
BYANJON: A Ground Truth Preparation System for Online Handwritten Bangla Documents
The work reported in this article deals with the ground truth generation scheme for online handwritten Bangla documents at text-line, word, and stroke levels. The aim of the proposed scheme is twofold: firstly, to build a document level database so that ...
Online Handwritten Gurmukhi Words Recognition: An Inclusive Study
Identification of offline and online handwritten words is a challenging and complex task. In comparison to Latin and Oriental scripts, the research and study of handwriting recognition at word level in Indic scripts is at its initial phases. The two ...
Stroke Segmentation and Recognition from Bangla Online Handwritten Text
ICFHR '12: Proceedings of the 2012 International Conference on Frontiers in Handwriting RecognitionThis paper deals with recognition of online handwritten Bangla (Bengali) text. Here, at first, we segment cursive words into strokes. A stroke may represent a character or a part of a character. We selected a set of Bangla words written by different ...






Comments