Abstract
Handwritten script classification is still considered as a challenging research problem in the domain of document image analysis. Although some research attempts have been made by the researchers for solving the challenging issues, a comprehensive solution is yet to be achieved. The case study, undertaken here, analyzes the performances of various state-of-the art handwritten script classification methods for Indian scripts where features, needed for the script classification task, are extracted from the script images at four different granularity levels, i.e., page, block, text line, or word. The results of handwritten script classification at each level have been obtained and compared using eight different feature sets and six different state-of-the-art classifiers. Based on the classification results, an ideal level for performing the handwritten script classification task is suggested among these four classification levels. The results have also been improved by using two feature dimensionality reduction methods. All these experiments are done on two different handwritten Indic script databases, of which one is an in-house developed dataset and the other one is a freely available dataset. Finally, some future research directions that may be undertaken by the researchers as an application of the handwritten Indic script classification problem are also highlighted. The work presented here provides a basic foundation for the construction of a comprehensive handwritten script classification method for official Indian scripts.
Supplemental Material
Available for Download
Supplemental movie, appendix, image and software files for, A Case Study on Handwritten Script Classification: Benchmarking of the Results at Page, Block, Text-line, and Word Levels
- [1] . 2010. Script Recognition: A Review. IEEE Trans. Pattern Anal. Mach. Intell. 32, 12 (2010), 21422161. Google Scholar
Digital Library
- [2] . 2018. Handwritten Indic Script Identification in Multi-script Document Images—A Survey. Int. J. Pattern Recogn. Artif. Intel. 32, 10 (2018), 1856012.Google Scholar
Cross Ref
- [3] . 2019. A survey of mono- and multi-lingual character recognition using deep and shallow architectures: Indic and non-Indic scripts. Artif. Intell. Rev. 53 (2019), 1813–1872.
DOI: DOI: https://doi.org/10.1007/s10462-019-09720-9Google Scholar - [4] . 2018. Automatic line-level script identification from handwritten document images—A region-wise classification framework for Indian subcontinent. Malays. J. Comput. Sci. 31, 1 (2018), 63–84.Google Scholar
Cross Ref
- [5] 2013. LBP based line-wise script identification. In 12th IEEE International Conference on Document Analysis and Recognition (ICDAR). 369–373. Google Scholar
Digital Library
- [6] . 2014. Multi-script identification from printed words. In Image Analysis and Recognition. A. Campilho and M. Kamel (Eds.) (LNCS, vol. 8814). Springer, 359–368.Google Scholar
Cross Ref
- [7] . 2015. Language identification from handwritten documents. In 13th IEEE International Conference on Document Analysis and Recognition (ICDAR). 676–680. Google Scholar
Digital Library
- [8] . 2008. Script and language identification in noisy and degraded document images. IEEE Trans. Pattern Anal. Mach. Intell. 30, 1 (2008), 14–24. Google Scholar
Digital Library
- [9] . 2018. Character and numeral recognition for non-Indic and Indic scripts: A survey. Artif. Intell. Rev. 4 (2018), 1–27.Google Scholar
- [10] . 2016. Pixel plot and trace based segmentation method for bilingual handwritten scripts using feedforward neural network. Neural Comput. Applic. 27, 7 (2016), 1817–1829. Google Scholar
Digital Library
- [11] . 2015. A sequence learning approach for multiple script identification. In 13th IEEE International Conference on Document Analysis and Recognition (ICDAR). 1046–1050. Google Scholar
Digital Library
- [12] . 2015. A robust script identification system for historical Indian document images. Malay. J. Comput. Sci. 28, 4 (2015), 283–300.Google Scholar
Cross Ref
- [13] Retrieved on 12 April, 2019 from http://rajbhasha.nic.in/hi/languages_included_in_the_eighth_schedule.Google Scholar
- [14] . 2017. Line-wise script identification from handwritten document images using sift method. In International Conference on Intelligent Computing Systems (ICICS). 117–125. Retrieved from https://ssrn.com/abstract=3126650.Google Scholar
Cross Ref
- [15] . 2015. Offline script identification from multilingual Indic-script documents: A state-of-the-art. Comput. Sci. Rev. 15, C (2015), 1–28. Google Scholar
Digital Library
- [16] . 2017. Script identification algorithms: A survey. Int. J. Multim. Inf. Retr. 6, 3 (2017), 211–232.Google Scholar
Cross Ref
- [17] . 2017. Script identification of multi-script documents: A survey. In IEEE Access 5 (2017) 6546–6559.
DOI: DOI: 10.1109/ACCESS.2017.2689159Google Scholar - [18] . 2017. A texture-based approach for word script and nature identification. In Pattern Anal. Applic. 20, 4 (2017), 1157–1167. Google Scholar
Digital Library
- [19] . 2013. Identification of Devnagari and Roman script from multiscript handwritten documents. In 5th International Conference on Pattern Recognition and Machine Intelligence (PReMI) (LNCS, vol. 8251). 509–514.Google Scholar
Cross Ref
- [20] . 2015. Word level script identification for handwritten Indic scripts. In 13th IEEE International Conference on Document Analysis and Recognition. 1106–1110. Google Scholar
Digital Library
- [21] . 2017. Separating Indic scripts with “Matra” for effective handwritten script identification in multi-script documents. Int. J. Pattern Recogn. Artif. Intell. 31, 5 (2017), 17.Google Scholar
Cross Ref
- [22] . 2019. Automatic Indic script identification from handwritten documents: Page, block, line and word level approach. Int. J. Mach. Learn. Cybern. 10, 1 (2019), 87–106.Google Scholar
Cross Ref
- [23] . 2018. Extreme learning machine for handwritten Indic script identification in multi-script documents. J. Electron. Imag. 27, 5 (2018), 051214.Google Scholar
Cross Ref
- [24] . 2014. Word level script identification from multi-script handwritten documents. In 3rd International Conference on Frontiers in Intelligent Computing Theory and Applications (FICTA). Google Scholar
Digital Library
- [25] . 2015. Line-level script identification for six handwritten scripts using texture based features. In 2nd Information Systems Design and Intelligent Applications.Google Scholar
Cross Ref
- [26] . 2015. Page level script identification from multi-script handwritten documents. In 3rd IEEE International Conference on Computer, Communication, Control and Information Technology (C3IT).
DOI: DOI: 10.1109/C3IT.2015.7060113Google ScholarCross Ref
- [27] . 2017. A two-stage approach to handwritten Indic script identification. In Hybrid Intelligence for Image Analysis and Understanding, (Eds.). Wiley Publishers, 47–77.Google Scholar
Cross Ref
- [28] . 2015. Page level handwritten script identification using modified log-Gabor filter based features. In 2nd IEEE International Conference on Recent Trends in Information Systems (ReTIS). 225–230.Google Scholar
Cross Ref
- [29] . 2016. Statistical textural features for text-line level handwritten Indic script identification. In 3rd International Doctoral Symposium on Applied Computation and Security Systems (ACSS). 139–151.Google Scholar
- [30] . 2016. Line parameter based word level Indic script identification system. Int. J. Comput. Vis. Image Process. 6, 2 (2016), 18–41. Google Scholar
Digital Library
- [31] . 2013. Directional discrete cosine transform for handwritten script identification. In 12th IEEE International Conference on Document Analysis and Recognition (ICDAR). 344–348. Google Scholar
Digital Library
- [32] . 2014. Automatic handwritten Indian scripts identification. In 14th IEEE International Conference on Frontiers in Handwriting Recognition (ICFHR). 375–380.Google Scholar
Cross Ref
- [33] . 2015. Indic script identification from handwritten document images—An unconstrained block level approach. In 2nd IEEE International Conference on Recent Trends in Information Systems (ReTIS). 213–218.Google Scholar
Cross Ref
- [34] . 2017. Word level multi-script Indic document image dataset and baseline results on script identification. Int. J. Comput. Vis. Image Process. 7, 2 (2017), 81–94 Google Scholar
Digital Library
- [35] . 2015. Script recognition using GLCM and DWT features. Int. J. Adv. Res. Comput. Commun. Eng. 4, 1 (2015), 256–260.Google Scholar
- [36] . 2008. A survey of shape feature extraction techniques. In Pattern Recognition Techniques, Technology and Applications, Peng-Yeng Yin (Ed.). pp. 626.Google Scholar
- [37] . 2005. Histograms of oriented gradients for human detection. In Conference on Computer Vision and Pattern Recognition. 886–893. Google Scholar
Digital Library
- [38] . 1973. Textural features of image classification. In IEEE Trans. Syst., Man, Cybern. 3, 6 (1973), 610–621.Google Scholar
Cross Ref
- [39] . 1992. Digital Image Processing I. Prentice-Hall, India. Google Scholar
Digital Library
- [40] . 1979. A threshold selection method from gray-level histograms. IEEE Trans. Syst., Man., Cybern. 9, 1 (1979), 62–66.Google Scholar
Cross Ref
- [41] . 1985. Uncertainty relation for resolution in space, spatial-frequency, and orientation optimized by two-dimensional visual cortical filters. J. Optical Soc. Amer. 2, 7 (1985), 1160–1169.Google Scholar
Cross Ref
- [42] . 1989. Textural features corresponding to textural properties. IEEE Trans. Syst., Man, Cybern. 19, 5 (1989), 1264–1274.Google Scholar
Cross Ref
- [43] . 1975. Texture analysis using gray level run lengths. Comput. Graph. Image Process. 4 (1975), 172–179.Google Scholar
Cross Ref
- [44] . 1990. Use of gray value distribution of run lengths for texture analysis. Pattern Recogn. Lett. 11, 6 (1990), 415–420. Google Scholar
Digital Library
- [45] . 1991. Image characterizations based on joint gray-level run-length distributions. Pattern Recogn. Lett. 12, 8 (1991), 497–502. Google Scholar
Digital Library
- [46] . 2009. Text-line segmentation for unconstrained handwritten document images using neighborhood connected component analysis. In 3rd International Conference on Pattern Recognition and Machine Intelligence (PReMI) (LNCS, vol. 5909). 369–374. Google Scholar
Digital Library
- [47] . 2016. Page-to-word extraction from unconstrained handwritten document images. In 1st International Conference on Intelligent Computing and Communication (ICIC2). 517–524.Google Scholar
- [48] . 2001. An empirical study of the naive Bayes classifier. In IJCAI 2001 Workshop on Empirical Methods in Artificial Intelligence.Google Scholar
- [49] . 1995. Support-vector networks. Mach. Learn. 20, 3 (1995), 273–297. Google Scholar
Digital Library
- [50] . 2005. Comparison of the multilayer perceptron and the nearest neighbor classifier for handwritten digit recognition. J. Inf. Sci. Eng. 21, 6 (2005), 1245–1257.Google Scholar
- [51] . 1999. Improved boosting algorithms using confidence-rated predictions. Mach. Learn. 37, 3 (1999), 297–336,
DOI: DOI: https://doi.org/10.1023/A:1007614523901 Google ScholarDigital Library
- [52] . 1995. Random decision forests. In 3rd IEEE International Conference on Document Analysis and Recognition 278–282. Google Scholar
Digital Library
- [53] . 2002. Logistic regression and artificial neural network classification models: A methodology review. J. Biomed. Inform. 35 (2002), 352–359. Google Scholar
Digital Library
- [54] . 2018. A comprehensive handwritten Indic script recognition system: A tree-based approach. J. Amb. Intell. Human. Comput.
DOI: DOI: https://doi.org/10.1007_s12652-018-1052-4Google ScholarCross Ref
- [55] . 2015. Statistical validation of multiple classifiers over multiple datasets in the field of pattern recognition. Int. J. Appl. Pattern Recogn. 2, 1 (2015), 1–23.Google Scholar
Cross Ref
- [56] . 1937. The use of ranks to avoid the assumption of normality implicit in the analysis of variance. J. Amer. Statist. Assoc. 32, 200 (1937), 675–701.Google Scholar
Cross Ref
- [57] . 1940. A comparison of alternative tests of significance for the problem of m rankings. In Ann. Math. Statist. 11, 1 (1940), 86–92.Google Scholar
Cross Ref
- [58] . 2010. Feature selection using principal component analysis. In IEEE International Conference on System Science, Engineering Design and Manufacturing Informatization 27–30.
DOI: DOI: 10.1109/ICSEM.2010.14 Google ScholarDigital Library
- [59] . 2018. Feature selection using harmony search for script identification from handwritten document images. J. Intell. Syst. 27, 3 (2018), 465–488.Google Scholar
Cross Ref
- [60] . 2018. PHDIndic_11: Page level handwritten document image dataset of 11 official Indic scripts for script identification. In Multim. ToolsApplic. 77, 2 (2018), 1643–1678. Google Scholar
Digital Library
- [61] . 2015. A comprehensive survey of handwritten document benchmarks: Structure, usage and evaluation. EURASIP J. Image Video Proces. 5, 1 (2015) 46, 1–24.Google Scholar
- [62] . 2012. A clustering based feature selection method in spectro-temporal domain for speech recognition. Eng. Applic. Artif. Intell. 25, 6 (2012), 1194–1202. Google Scholar
Digital Library
- [63] . 2014. A novel binary adaptive weight GSA-based feature selection for face recognition using local gradient patterns, modified census transform, and local binary patterns. Eng. Applic. Artif. Intell. 33, (2014), 80–90.Google Scholar
Cross Ref
- [64] . 2017. An evolutionary single Gabor kernel-based filter approach to face recognition. Eng. Applic. Artif. Intell. 62, (2017), 286–301. Google Scholar
Digital Library
- [65] . 2018. An advanced particle swarm optimization based feature selection method for tri-script handwritten digit recognition. In International Conference on Computational Intelligence, Communications, and Business Analytics (CICBA). 82–94.Google Scholar
- [66] . 2018. A novel multivariate filter method for feature selection in text classification problems. Eng. Applic. Artif. Intell. 70 (2018), 25–37.Google Scholar
Cross Ref
- [67] . 2016. Feature selection for Bangla handwritten word recognition using harmony search. Int. J. Inf. Process. 10, 4 (2016), 20–33.Google Scholar
- [68] . 2019. Recursive memetic algorithm for gene selection in microarray data. In Exp. Syst. Applic. 116 (2019), 172–185.Google Scholar
Cross Ref
- [69] . 2019. A clustering-based feature selection framework for handwritten Indic script classification. Exp. Syst. 36, 6 (2019).
DOI: https://doi.org/10.1111/exsy.12459Google Scholar - [70] . 2012. Multi-column deep neural networks for image classification. In 25th IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 3642–3649. Google Scholar
Digital Library
- [71] . 2018. Deep convolutional framework for abnormal behavior detection in a smart surveillance system. Eng. Applic. Artif. Intell. 67 (2018), 226–234, Google Scholar
Digital Library
- [72] . 2019. Implementing deep learning for comprehensive aircraft icing and actuator/sensor fault detection/identification. Eng. Applic. Artif. Intell. 83 (2019), 28–44,Google Scholar
Cross Ref
- [73] . 2019. Railway track fastener defect detection based on image processing and deep learning techniques: A comparative study. Eng. Applic. Artif. Intell. 80 (2019), 66–81.Google Scholar
Cross Ref
- [74] . 2016. Deep neural network for halftone image classification based on sparse auto-encoder. Eng. Applic. Artif. Intell. 50 (2016), 245–255 Google Scholar
Digital Library
- [75] . 2018. Deep convolutional framework for abnormal behavior detection in a smart surveillance system. Eng. Applic. Artif. Intell. 67 (2018), 226–234, Google Scholar
Digital Library
- [76] . 2018. Deep learning for word level handwritten Indic script identification. CoRR abs/1801.01627 (2018).Google Scholar
- [77] . 2020. Improved word level handwritten Indic script identification by integrating small convolutional neural networks. Neural Comput. Applic. 32, 7 (2020), 2829–2844.
DOI: DOI: https://doi.org/10.1007/s00521-019-04111-1Google ScholarCross Ref
- [78] . 2020. Understanding NFC-Net: A deep learning approach to word level handwritten Indic script recognition. Neural Comput. Applic. 32, 12 (2020), 7879–7895.
DOI: DOI: https://doi.org/10.1007/s00521-019-04235-4Google ScholarCross Ref
- [79] . 2015. New gradient-spatial-structural features for video script identification. Comput. Vis. Image Underst. 130 (2015), 35–53. Google Scholar
Digital Library
- [80] . 2015. Video script identification using a combination of textural features. In 11th IEEE International Conference on Signal-Image Technology & Internet-based Systems (SITIS. 61–67.
DOI: DOI: 10.1109/SITIS.2015.15 Google ScholarDigital Library
- [81] . 2019. Script identification in natural scene image and video frames using an attention based convolutional-LSTM network. Pattern Recogn. 85 (2019), 172–184.Google Scholar
Cross Ref
- [82] . 2013. Word-wise script identification from video frames. In 12th International Conference on Document Analysis and Recognition. 867–871.
DOI: DOI: 10.1109/ICDAR.2013.177 Google ScholarDigital Library
- [83] . 2014. Automatic video scene segmentation to separate script and recognition. In 3rd International Conference on Frontiers of Intelligent Computing: Theory and Applications (FICTA). 225–235.Google Scholar
- [84] . 2019. Review of scene text detection and recognition. Arch. Comput. Meth. Eng. 27 (2019), 433–454.
DOI: DOI: https://doi.org/10.1007/s11831-019-09315-1Google Scholar - [85] . 2016. Script identification in the wild via discriminative convolutional neural network. Pattern Recogn. 52 (2016) 448–458. Google Scholar
Digital Library
- [86] . 2017. Accurate recognition of words in scenes without character segmentation using recurrent neural network. Pattern Recogn. 63 (2017), 397–405. Google Scholar
Digital Library
- [87] . 2017. WeText scene text detection under weak supervision. In IEEE International Conference on Computer Vision. 1501–1509Google Scholar
Cross Ref
- [88] . 2014. A robust arbitrary text detection system for natural scene images. Exp. Syst. Applic. 41, 18 (2014), 8027–8048.Google Scholar
Cross Ref
- [89] . 2016. Strokelets: A learned multi-scale mid-level representation for scene text recognition. IEEE Trans. Image Process. 25 (2016), 2789–2802 Google Scholar
Digital Library
- [90] . 2017. EAST: An efficient and accurate scene text detector. arXiv:1704.03155v2, 2017.Google Scholar
- [91] . 2018. Accurate scene text detection through border semantics awareness and bootstrapping. In 15th European Conference on Computer Vision (LNCS, vol. 11220). 370–387.Google Scholar
Cross Ref
- [92] . 2016. Robust scene text recognition with automatic rectification. In IEEE Conference on Computer Vision and Pattern Recognition. 1–9.Google Scholar
Cross Ref
- [93] . 2016. CannyText detector fast and robust scene text localization algorithm. In IEEE Conference on Computer Vision and Pattern Recognition. 3566–3573.Google Scholar
Cross Ref
- [94] . 2018. Rotation-sensitive regression for oriented scene text detection. In IEEE Conference on Computer Vision and Pattern Recognition. 1–10.Google Scholar
Cross Ref
- [95] . 2017. Focusing attention: Towards accurate text recognition in natural images. In IEEE International Conference on Computer Vision (ICCV). 5086–5094.Google Scholar
Cross Ref
- [96] . 2018. PixelLink: Detecting scene text via instance segmentation. In 32nd AAAI Conference on Artificial Intelligence. 6773–6780. Google Scholar
Digital Library
- [97] . 2018. Scene text detection and recognition system for visually impaired people in real world. Proc. SPIE 10794, Target and Background Signatures IV, 107940S (9 Oct. 2018).
DOI: DOI: https://doi.org/10.1117/12.2325523Google ScholarCross Ref
- [98] . 2018. Scene text detection using superpixel-based stroke feature transform and deep learning based region classification. IEEE Trans. Multim. 20, 9 (2018), 2276–2288. Google Scholar
Digital Library
- [99] . 2018. Scene text detection based on enhanced multi-channels MSER and a fast text grouping process. Int. J. Comput. Ling. Res. 9 2, (2018) 47–59.Google Scholar
- [100] . 2018. Multi-oriented text detection and verification in video frames and scene images. Neurocomputing 275 (2018), 1531–1549.Google Scholar
Cross Ref
- [101] . 2017. Script independent approach for multi-oriented text detection in scene image. Neurocomputing 242 (2017), 96–112. Google Scholar
Digital Library
- [102] . 2019. Multi-lingual text localization from camera captured images based on foreground homogeneity analysis. In Advances in Intelligent Systems and Computing, vol. 740. Springer, Singapore. https://doi.org/10.1007/978-981-13-1280-9_15Google Scholar
- [103] . 2019. Multi-lingual scene text detection using one-class classifier. Int. J. Comput. Vis. Image Process. 9, 2 (2019), 48–65.Google Scholar
Digital Library
- [104] . 2019. Script identification from camera-captured multi-script scene text components. In Advances in Intelligent Systems and Computing, vol. 740. Springer, Singapore. https://doi.org/10.1007/978-981-13-1280-9_16Google Scholar
Cross Ref
- [105] . 2020. Application of daisy descriptor for language identification in the wild. In Multimedia Tools and Applications. Springer Publishers, 1–22.
DOI: DOI: https://doi.org/10.1007/s11042-020-09728-2Google Scholar - [106] . 2019. Writer identification approach based on bag of words with OBI features. Inf. Process. Manag. 52, 2 (2019), 354–366.Google Scholar
Cross Ref
- [107] . 2007. Writer identification in handwritten documents. In 9th IEEE International Conference on Document Analysis and Recognition (ICDAR). 108–112. Google Scholar
Digital Library
- [108] . 2017. Writer identification from offline isolated handwritten Gurumukhi characters. In Adv. Comput. Sci. Technol. 10, 5 (2017), 903–914.Google Scholar
- [109] . 2018. Writer identification using texture features in Kannada handwritten documents. Int. J. Eng. Res. Technol. 6, 13 (2018), 1–5.Google Scholar
- [110] . 2017. Writer identification in Indic scripts: A stroke distribution based approach. In 4th Asian Conference on Pattern Recognition (ACPR). 947–952.Google Scholar
Cross Ref
- [111] . 2010. Text independent writer identification for Bengali script. In 20th IEEE International Conference on Pattern Recognition (ICPR). 2005–2008. Google Scholar
Digital Library
- [112] . 2017. Text independent writer identification for Telugu script using directional filter based features. In ICDAR-2017 Workshop on Machine Learning. 65–70.Google Scholar
- [113] . 2012. Text independent writer identification for Oriya script. In 10th IAPR International Workshop on Document Analysis Systems. 369–373. Google Scholar
Digital Library
- [114] . 2003. ICDAR 2003 robust reading competitions. In 7th IEEE International Conference on Document Analysis and Recognition. 682–687. Google Scholar
Digital Library
- [115] . 2005. ICDAR 2005 text locating competition results. In 8th IEEE International Conference on Document Analysis and Recognition (ICDAR). 80–84. Google Scholar
Digital Library
- [116] . 2011. ICDAR 2011 robust reading competition - Challenge 1: Reading text in born-digital images (web and email). In 11th IEEE International Conference of Document Analysis and Recognition. 1485–1490. Google Scholar
Digital Library
- [117] . 2011. ICDAR 2011 robust reading competition challenge 2: Reading text in scene images. In 11th IEEE International Conference on Document Analysis and Recognition (ICDAR). IEEE Computer Society. 1491–1496. Google Scholar
Digital Library
- [118] . 2013. ICDAR 2013 robust reading competition. In 12th IEEE International Conference of Document Analysis and Recognition. 1115–1124 Google Scholar
Digital Library
- [119] . 2015. ICDAR 2015 competition on robust reading. In 13th IEEE International Conference on Document Analysis and Recognition (ICDAR). IEEE Computer Society, 1156–1160. Google Scholar
Digital Library
- [120] . 2017. ICDAR2017 robust reading challenge on COCO-Text. In 14th IEEE IAPR International Conference on Document Analysis and Recognition (ICDAR). 1435–1443. Google Scholar
Digital Library
- [121] . 2017. ICDAR2017 robust reading challenge on omnidirectional video. In 14th IEEE IAPR International Conference on Document Analysis and Recognition (ICDAR). 1448–1453.Google Scholar
Cross Ref
- [122] . 2017. ICDAR2017 robust reading challenge on multi-lingual scene text detection and script identification-RRC-MLT. In 14th IEEE IAPR International Conference on Document Analysis and Recognition (ICDAR). 1454–1459.Google Scholar
Cross Ref
- [123] . 2017. An approach to stroke-based online handwritten Bangla character recognition. In Advanced Computing and Systems for Security. (Eds.). Springer, 153–163.Google Scholar
- [124] . 2020. A novel segmentation technique for online handwritten Bangla words. Pattern Recogn. Lett. 139 (2020), 26–33.
DOI: DOI: https://doi.org/10.1016/j.patrec.2018.02.008Google ScholarCross Ref
- [125] . 2016. Online recognition of handwritten Telugu script characters. In International Conference on Signal Processing, Communication, Power and Embedded System (SCOPES). 426–432.Google Scholar
Cross Ref
- [126] . 2007. Spatiostructural features for recognition of online handwritten characters in Devanagari and Tamil scripts. In International Conference on Artificial Neural Networks (ICANN) (LNCS vol. 4669). Springer, 230–239. Google Scholar
Digital Library
- [127] . 2015. Machine recognition of online handwritten Devanagari characters. In 8th International Conference on Document Analysis and Recognition (ICDAR). IEEE Computer Society, 1156–1160.
DOI: DOI: http://dx.doi.org/10.1109/ICDAR.2005.156Google Scholar - [128] . 2012. A neural network approach to online Devanagari handwritten character recognition. In International Conference on High Performance Computing & Simulation (HPCS). 209–214.Google Scholar
Cross Ref
- [129] . 2015. Online handwritten Devanagari stroke recognition using extended directional features. arXiv:1501.02887v1 [cs.CV] 11.Google Scholar
- [130] . 2007. On-line handwriting recognition system for Tamil handwritten characters. In Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA) (LNCS, vol. 4477). Springer, Berlin, 370–377. Google Scholar
Digital Library
- [131] . 2004. Online handwriting recognition for Tamil. In 9th International Workshop on Frontiers in Handwriting Recognition. 438–443. Google Scholar
Digital Library
- [132] . 2008. Online handwritten Gurmukhi character recognition using elastic matching. In Congress on Image and Signal Processing. 391–396.
DOI: DOI: 10.1109/CISP.2008.297 Google ScholarDigital Library
- [133] . 2019. Online handwritten Gurmukhi words recognition: An inclusive study. In ACM Trans. Asian Low-Resour. Lang. Inf. Process. 18, 3 (2019).
DOI: DOI: https://doi.org/10.1145/3282441 Google ScholarCross Ref
- [134] . 2016. Online handwritten Gurmukhi strokes dataset based on minimal set of words. ACM Trans. Asian Low-Resour. Lang. Info. Process. 16, 1 (2016), 1–20. Google Scholar
Digital Library
- [135] . 2012. On-line handwritten character recognition system for Kannada using principal component analysis approach: For handheld devices. In World Congress on Information and Communication Technologies. 675–678. Google Scholar
Digital Library
- [136] . 2017. Handwritten online character recognition for single stroke Kannada characters. In 2nd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT). 548–552.Google Scholar
Cross Ref
- [137] . 2015. On-line character recognition for handwritten Kannada characters using wavelet features and neural classifier. IETE J. Res. 46, 5 (2015), 387–393.Google Scholar
Cross Ref
- [138] . 2012. Malayalam online handwriting recognition system: A simplified fuzzy ARTMAP approach. In Annual IEEE India Conference (INDICON). 613–618.
DOI: DOI: 10.1109/INDCON.2012.6420691Google ScholarCross Ref
- [139] . 2013. On-line Malayalam handwritten character recognition using HMM and SVM. In International Conference on Signal Processing , Image Processing & Pattern Recognition. 322–326.
DOI: DOI: 10.1109/ICSIPR.2013.6497991Google ScholarCross Ref
- [140] . 2011. Online handwriting recognition for Malayalam script. In International Conference on Information Systems for Indian Languages (Communications in Computer and Information Science, vol. 139). Springer, Berlin, 199–203.Google Scholar
Cross Ref
- [141] . 2014. Online Urdu handwritten character recognition: Initial half form single stroke characters. In 12th International Conference on Frontiers of Information Technology. 292–297.
DOI: DOI: 10.1109/FIT.2014.61 Google ScholarDigital Library
- [142] . 2007. Online Urdu character recognition system. In IAPR Conference on Machine Vision Applications (IAPR MVA). 98–101.Google Scholar
- [143] . 2005. Urdu online handwriting recognition. In IEEE International Conference on Emerging Technologies. 27–31.Google Scholar
Cross Ref
- [144] . 2017. Online handwritten Gujarati character recognition using SVM, MLP, and K-NN. In 8th International Conference on Computing, Communication and Networking Technologies (ICCCNT). 1–6.
DOI: DOI: 10.1109/ICCCNT.2017.8203926Google ScholarCross Ref
- [145] . 2015. On-line handwritten Gujarati character recognition using low level stroke. 3rd International Conference on Image Information Processing (ICIIP). 130–134.
DOI: DOI: 10.1109/ICIIP.2015.7414753Google ScholarDigital Library
- [146] . 2018. Deep learning based Gujarati handwritten character recognition. In International Conference On Advances in Communication and Computing Technology (ICACCT). 563–566.
DOI: DOI: 10.1109/ICACCT.2018.8529410Google ScholarCross Ref
- [147] . 2020. Handwritten Indic script recognition based on the Dempster–Shafer theory of evidence. J. Intell. Syst. 29, 1 (2020), 264–282.
DOI: DOI: https://doi.org/10.1515/jisys-2017-0431Google ScholarCross Ref
- [148] . 2018. A study of different classifier combination approaches for handwritten Indic script recognition. J. Imag. 4, 39 (2018), 1–21.
DOI: DOI: 10.3390/jimaging4020039Google Scholar
Index Terms
A Case Study on Handwritten Indic Script Classification: Benchmarking of the Results at Page, Block, Text-line, and Word Levels
Recommendations
Character and numeral recognition for non-Indic and Indic scripts: a survey
AbstractA collection of different scripts is employed in writing languages throughout the world. Character and numeral recognition of a particular script is a key area in the field of pattern recognition. In this paper, we have presented a comprehensive ...
Word-level script identification for handwritten Indic scripts
ICDAR '15: Proceedings of the 2015 13th International Conference on Document Analysis and Recognition (ICDAR)Automatic script identification from handwritten document images facilitates many important applications such as indexing, sorting and triage. A given Optical Character Recognition (OCR) system is typically trained on only a single script but for ...
iiit-indic-hw-words: A Dataset for Indic Handwritten Text Recognition
Document Analysis and Recognition – ICDAR 2021AbstractHandwritten text recognition (htr) for Indian languages is not yet a well-studied problem. This is primarily due to the unavailability of large annotated datasets in the associated scripts. Existing datasets are small in size. They also use small ...






Comments