Abstract
A good benchmark dataset is a primary requirement in the offline handwritten character recognition (HCR) process. Only three handwritten numerals and alphabet datasets from Odia are publicly accessible for study, although many writers have used several datasets in their experiments. In this article, two tasks are done to address this issue. Those are the following: First, an extensive survey focused on various datasets is provided with the methodologies used in chronological order. The second factor is a solution to the lack of publicly available handwritten characters and numeral datasets. A new dataset of handwritten Odia characters with numerals has been developed. Anyone can access this dataset by sending an email to the authors of the article. This dataset was created with the help of 150 volunteers of various age groups, races, and qualifications. Some homogeneous experiments are conducted using deep learning models to evaluate the consistency of the dataset. One heterogeneous trial has also been performed to estimate the complexities of the characters present in the dataset by comparing them with the existing benchmark datasets.
- [1] . 2015. Deep learning based large scale handwritten Devanagari character recognition. In 9th International Conference on Software, Knowledge, Information Management and Applications (SKIMA). IEEE, 1–6.Google Scholar
Cross Ref
- [2] . 2005. Databases for research on recognition of handwritten characters of Indian scripts. In 8th International Conference on Document Analysis and Recognition (ICDAR’05). IEEE, 789–793.Google Scholar
Digital Library
- [3] . 2012. Offline recognition of handwritten Bangla characters: An efficient two-stage approach. Pattern Anal. Applic. 15, 4 (2012), 445–458.Google Scholar
Digital Library
- [4] . 2006. An HMM based recognition scheme for handwritten Oriya numerals. In 9th International Conference on Information Technology (ICIT’06). IEEE, 105–110.Google Scholar
Digital Library
- [5] . 2020. Zero-shot handwritten Chinese character recognition with hierarchical decomposition embedding. Pattern Recog. 107 (2020), 107488.Google Scholar
Cross Ref
- [6] . 2012. Text independent writer identification for Oriya script. In 10th IAPR International Workshop on Document Analysis Systems. IEEE, 369–373.Google Scholar
- [7] . 2018. Optimization based feature generation for handwritten Odia-numeral recognition. In 14th International Conference on Information Processing (ICINPRO). IEEE, 1–5.Google Scholar
Cross Ref
- [8] . 2019. An empirical evaluation of extreme learning machine: Application to handwritten character recognition. Multim. Tools Applic. 78, 14 (2019), 19495–19523.Google Scholar
Digital Library
- [9] . 2020. MJCN: Multi-objective Jaya convolutional network for handwritten optical character recognition. Multim. Tools Applic. 79, 43 (2020), 33023–33042.Google Scholar
Digital Library
- [10] . 2016. Odia offline character recognition using DWT features. IOSR J. Electron. Commun. Eng. (2016), 31–37.Google Scholar
- [11] . 2014. A hybrid feature and discriminant classifier for high accuracy handwritten Odia numeral recognition. In IEEE Region 10 Symposium. IEEE, 531–535.Google Scholar
- [12] . 2015. Handwritten numeral recognition using non-redundant Stockwell transform and bio-inspired optimal zoning. IET Image Process. 9, 10 (2015), 874–882.Google Scholar
Cross Ref
- [13] . 2015. On extraction of features for handwritten Odia numeral recognition in transformed domain. In 8th International Conference on Advances in Pattern Recognition (ICAPR). IEEE, 1–6.Google Scholar
Cross Ref
- [14] . 2017. Odia character recognition: A directional review. Artif. Intell. Rev. 48, 4 (2017), 473–497.Google Scholar
Digital Library
- [15] . 2020. Sparse concept coded tetrolet transform for unconstrained Odia character recognition. arXiv preprint arXiv:2004.01551.Google Scholar
- [16] . 2009. Character recognition in natural images. VISAPP 7, 2 (2009).Google Scholar
- [17] . 2009. ImageNet: A large-scale hierarchical image database. In IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 248–255.Google Scholar
Cross Ref
- [18] . 2019. A novel sliding window approach for offline handwritten character recognition. In International Conference on Information Technology (ICIT). IEEE, 178–183.Google Scholar
Cross Ref
- [19] . 2021. Sliding window based off-line handwritten text recognition using edit distance. Multim. Tools Applic. 81, 16 (2021), 1–28.Google Scholar
- [20] . 2020. A robust handwritten digit recognition system based on sliding window with edit distance. In IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT). IEEE, 1–6.Google Scholar
Cross Ref
- [21] . 2021. Offline natural scene character recognition using VGG16 neural networks. In 3rd International Conference on Inventive Research in Computing Applications (ICIRCA). IEEE, 946–951.Google Scholar
Cross Ref
- [22] . 2020. DevNet: An efficient CNN architecture for handwritten Devanagari character recognition. Int. J. Pattern Recog. Artif. Intell. 34, 12 (2020), 2052009.Google Scholar
Cross Ref
- [23] . 2013. Recognition of offline handwritten numerals using an ensemble of MLPs combined by AdaBoost. In 4th International Workshop on Multilingual OCR. ACM, 1–5.Google Scholar
- [24] . 1981. Median filtering: Statistical properties. In Two-dimensional Digital Signal Processing II. Springer, 161–196.Google Scholar
- [25] . 2017. ImageNet classification with deep convolutional neural networks. Commun. ACM 60, 6 (2017), 84–90.Google Scholar
Digital Library
- [26] . 2020. Deep matching network for handwritten Chinese character recognition. Pattern Recog. 107 (2020), 107471.Google Scholar
Cross Ref
- [27] . 2011. Asystem for Oriya handwritten numeral recognization for Indian postal automation. Int. J. Appl. Sci. Technol. Res. Excell. 1, 1 (2011), 17–23.Google Scholar
- [28] . 2018. On development and performance evaluation of novel Odia handwritten digit recognition methods. Arab. J. Sci. Eng. 43, 8 (2018), 3887–3901.Google Scholar
Cross Ref
- [29] . 2011. An intelligent scanner with handwritten Odia character recognition capability. In 5th International Conference on Sensing Technology. IEEE, 53–59.Google Scholar
Cross Ref
- [30] . 2013. A comparative analysis of image transformations for handwritten Odia numeral recognition. In International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE, 790–793.Google Scholar
Cross Ref
- [31] . 2014. Model based Odia numeral recognition using fuzzy aggregated features. Front. Comput. Sci. 8, 6 (2014), 916–922.Google Scholar
Digital Library
- [32] . 2015. Classification of handwritten Odia basic character using Stockwell transform. Int. J. Appl. Pattern Recog. 2, 3 (2015), 235–254.Google Scholar
Cross Ref
- [33] . 2015. OHCS: A database for handwritten atomic Odia Character Recognition. In 5th National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG). IEEE, 1–4.Google Scholar
Cross Ref
- [34] . 2017. Odia character recognition using backpropagation network with binary features. Int. J. Computat. Vis. Robot. 7, 5 (2017), 588–604.Google Scholar
Digital Library
- [35] . 2019. Handwritten Manipuri Meetei-Mayek classification using convolutional neural network. ACM Trans. Asian Low-resour. Lang. Inf. Process. 18, 4 (2019), 1–23.Google Scholar
Digital Library
- [36] . 1979. A threshold selection method from gray-level histograms. IEEE Trans. Syst., Man, Cybern. 9, 1 (1979), 62–66.Google Scholar
Cross Ref
- [37] . 2013. Zone centroid distance and standard deviation based feature matrix for Odia handwritten character recognition. In International Conference on Frontiers of Intelligent Computing: Theory and Applications (FICTA). Springer, 649–658.Google Scholar
Cross Ref
- [38] . 2012. Handwriting recognition in Indian regional scripts: A survey of offline techniques. ACM Trans. Asian Lang. Inf. Process. 11, 1 (2012), 1–35.Google Scholar
Digital Library
- [39] . 2007. Oriya off-line handwritten character recognition. In Advances in Pattern Recognition. World Scientific, 123–128.Google Scholar
- [40] . 2007. Handwritten numeral recognition of six popular Indian scripts. In 9th International Conference on Document Analysis and Recognition (ICDAR’07), Vol. 2. IEEE, 749–753.Google Scholar
Cross Ref
- [41] . 2007. A system for off-line Oriya handwritten character recognition using curvature feature. In 10th International Conference on Information Technology (ICIT’07). IEEE, 227–229.Google Scholar
Digital Library
- [42] . 2015. Odia offline typewritten character recognition using template matching with unicode mapping. In International Symposium on Advanced Computing and Communication (ISACC). IEEE, 109–115.Google Scholar
- [43] . 2005. Oriya handwritten numeral recognition system. In 8th International Conference on Document Analysis and Recognition (ICDAR’05). IEEE, 770–774.Google Scholar
Digital Library
- [44] . 2016. Handwritten character recognition of Odia script. In International Conference on Signal Processing, Communication, Power and Embedded System (SCOPES). IEEE, 764–767.Google Scholar
Cross Ref
- [45] . 2018. MobileNetV2: Inverted residuals and linear bottlenecks. In IEEE Conference on Computer Vision and Pattern Recognition. 4510–4520.Google Scholar
Cross Ref
- [46] . 2013. Recognition of handwritten Odia numerals using artificial intelligence techniques. Int. J. Comput. Sci. 2, 02 (2013), 35–38.Google Scholar
- [47] . 2014. Naïve Bayes classifier with Lu factorization for recognition of handwritten Odia numerals. Ind. J. Sci. Technol. 7, 1 (2014), 35–38.Google Scholar
Cross Ref
- [48] . 2012. Recognition of isolated handwritten oriya numerals using Hopfield neural network. Int. J. Comput. Applic. 40, 8 (2012), 36–42.Google Scholar
Cross Ref
- [49] . 2018. Use of stacked autoencoder in Odia numeral image recognition. Int. J. Pure Appl. Math. 118, 24 (2018).Google Scholar
- [50] . 2016. Off-line Odia handwritten numeral recognition using neural network: A comparative analysis. In International Conference on Computing, Communication and Automation (ICCCA). IEEE, 1099–1103.Google Scholar
Cross Ref
- [51] . 2019. Off-line Odia handwritten character recognition: An axis constellation model based research. Int. J. Innov. Technol. Explor. Eng. 8, 9S2 (2019), 788–793.Google Scholar
Cross Ref
- [52] . 2020. R-HOG feature-based off-line Odia handwritten character recognition. In Examining Fractal Image Processing and Analysis. IGI Global, 196–210.Google Scholar
Cross Ref
- [53] . 2018. Off-line handwritten Odia character recognition using DWT and PCA. In Progress in Advanced Computing and Intelligent Engineering. Springer, 187–195.Google Scholar
Cross Ref
- [54] . 2019. Gray-level co-occurrence matrix and random forest based off-line Odia handwritten character recognition. Recent Patents Eng. 13, 2 (2019), 136–141.Google Scholar
Cross Ref
- [55] . 2017. Symmetric axis based off-line Odia handwritten character and numeral recognition. In 3rd International Conference on Computational Intelligence and Networks (CINE). IEEE, 83–87.Google Scholar
Cross Ref
- [56] . 2020. Offline handwritten numeral recognition using convolution neural network. Mach. Vis. Inspect. Syst.: Image Process., Concepts, Methodol. Applic. 1 (2020), 197–212.Google Scholar
- [57] . 2021. A new feature extraction approach for script invariant handwritten numeral recognition. Expert Syst. 38, 6 (2021), e12699.Google Scholar
- [58] . 2021. Odia character recognition system: A study on feature extraction and classification techniques. Mater. Today: Proc. 34 (2021), 742–747.Google Scholar
Cross Ref
- [59] . 2020. Study on automated approach to generate character recognition for handwritten and historical documents. ACM Trans. Asian Low-resour. Lang. Inf (2020).Google Scholar
- [60] . 2003. System for Oriya handwritten numeral recognition. In Document Recognition and Retrieval XI, Vol. 5296. International Society for Optics and Photonics, IEEE, 174–181.Google Scholar
- [61] . 2006. Handwriting segmentation of unconstrained Oriya text. Sadhana 31, 6 (2006), 755–769.Google Scholar
Cross Ref
Index Terms
Development of a Benchmark Odia Handwritten Character Database for an Efficient Offline Handwritten Character Recognition with a Chronological Survey
Recommendations
Offline Odia handwritten character recognition with a focus on compound characters
AbstractRecognition of Odia character images is one of the ongoing applications of offline OCR. An attempt has been made here to develop an efficient feature extraction procedure that can assist the recognition of Odia handwritten digits, basic characters,...
Odia character recognition: a directional review
Character recognition is one of the challenging tasks of pattern recognition and machine learning arena. Though a level of saturation has been obtained in machine printed character recognition, there still remains a void while recognizing handwritten ...
Handwritten Cursive Jawi Character Recognition: A Survey
CGIV '08: Proceedings of the 2008 Fifth International Conference on Computer Graphics, Imaging and VisualisationThe subject of cursive handwritten character recognition is still open to be studied because of its complex nature. Recognition of Arabic handwritten and its variants such as Farsi (Persian) and Urdu had been receiving considerable attention in recent ...






Comments