Recognition of handwritten characters from Devanagari, Bangla, and Odia languages using transfer-learning-based VGG-16 networks

References

• Graves A, Liwicki M, Fernández S, et al. A novel connectionist system for unconstrained handwriting recognition. IEEE Trans Pattern Anal Mach Intell. 2008;31(5):855–868.
   Web of Science ®Google Scholar
• Ahlawat S, Choudhary A, Nayyar A, et al. Improved handwritten digit recognition using convolutional neural networks (CNN). Sensors. 2020;20(12):3344.
   PubMed Web of Science ®Google Scholar
• Dash KS, Puhan NB, Panda G. BESAC: Binary external symmetry axis constellation for unconstrained handwritten character recognition. Pattern Recognit Lett. 2016;83:413–422.
   Web of Science ®Google Scholar
• Gysel P, Motamedi M, Ghiasi S. Hardware-oriented approximation of convolutional neural networks. arXiv preprint arXiv:160403168. 2016.
   Google Scholar
• Khan S, Nazir S, Khan HU, et al. Pashto characters recognition using multi-class enabled support vector machine. Comput Mater Contin. 2021;67(3):2831–2844.
   Web of Science ®Google Scholar
• Khan S, Hafeez A, Ali H, et al. Pioneer dataset and recognition of handwritten Pashto characters using convolution neural networks. Meas Control. 2020;53(9–10):2041–2054.
   Web of Science ®Google Scholar
• Horry MJ, Chakraborty S, Paul M, et al. X-ray image based COVID-19 detection using pre-trained deep learning models. 2020.
   Google Scholar
• D'souza RN, Huang PY, Yeh FC. Structural analysis and optimization of convolutional neural networks with a small sample size. Sci Rep. 2020;10(1):1–13.
   PubMed Web of Science ®Google Scholar
• Sampath A, Gomathi N. Handwritten optical character recognition by hybrid neural network training algorithm. Imaging Sci J. 2019;67(7):359–373.
   Web of Science ®Google Scholar
• Yadav M, Purwar RK, Mittal M. Handwritten Hindi character recognition: a review. IET Image Process. 2018;12(11):1919–1933.
   Web of Science ®Google Scholar
• Singh S, Garg NK. Review of optical devanagari character recognition techniques. In: Satapathy SC, Bhateja V, Janakiramaiah B, Chen YW, editors. Intelligent system design. Organized by Lendi Institute of Engineering & Technology, India. Springer; 2021. p. 97–106.
   Google Scholar
• Deore SP, Pravin A. Devanagari handwritten character recognition using fine-tuned deep convolutional neural network on trivial dataset. Sādhanā. 2020;45(1):1–13.
   Web of Science ®Google Scholar
• Aneja N, Aneja S. Transfer learning using cnn for handwritten devanagari character recognition. In: 2019 1st International Conference on Advances in Information Technology (ICAIT); Chikmagalur, India; IEEE; 2019. p. 293–296.
   Google Scholar
• Guha R, Das N, Kundu M, et al. DevNet: an efficient CNN architecture for handwritten Devanagari character recognition. Int J Pattern Recognit Artif Intell. 2020;34(12):Article ID 2052009.
   PubMed Web of Science ®Google Scholar
• Jangid M, Srivastava S. Handwritten Devanagari character recognition using layer-wise training of deep convolutional neural networks and adaptive gradient methods. J Imaging. 2018;4(2):41.
   Web of Science ®Google Scholar
• Ram S, Gupta S, Agarwal B. Devanagri character recognition model using deep convolution neural network. J Stat Manag Syst. 2018;21(4):593–599.
   Web of Science ®Google Scholar
• Tushar AK, Ashiquzzaman A, Afrin A, et al. A novel transfer learning approach upon Hindi, Arabic, and Bangla numerals using convolutional neural networks. In: Computational vision and bio inspired computing. Cham: Springer; 2018. p. 972–981.
   Google Scholar
• Sufian A, Ghosh A, Naskar A, et al. Bdnet: Bengali handwritten numeral digit recognition based on densely connected convolutional neural networks. J King Saud Univ Comput Inf Sci. 2022;34(6, Part A):2610–2620.
   Google Scholar
• Hazra A, Choudhary P, Inunganbi S, et al. Bangla-Meitei Mayek scripts handwritten character recognition using convolutional neural network. Appl Intell. 2021;51(4):2291–2311.
   Web of Science ®Google Scholar
• Rahman MM, Islam MS, Sassi R, et al. Convolutional neural networks performance comparison for handwritten Bengali numerals recognition. SN Appl Sci. 2019;1(12):1–11.
   Web of Science ®Google Scholar
• Chowdhury RR, Hossain MS, ul Islam R, et al. Bangla handwritten character recognition using convolutional neural network with data augmentation. In: 2019 Joint 8th International Conference on Informatics, Electronics & Vision (ICIEV) and 2019 3rd International Conference on Imaging, Vision & Pattern Recognition (icIVPR); Spokane, WA, USA; IEEE; 2019. p. 318–323.
   Google Scholar
• Pramanik R, Bag S. Shape decomposition-based handwritten compound character recognition for Bangla OCR. J Vis Commun Image Represent. 2018;50:123–134.
   Web of Science ®Google Scholar
• Tripathy N, Panda M, Pal U. System for Oriya handwritten numeral recognition. In: Document Recognition and Retrieval XI; Vol. 5296; International Society for Optics and Photonics; Seoul, Korea (South). IEEE; 2003. p. 174–181.
   Google Scholar
• Roy K, Pal T, Pal U, et al. Oriya handwritten numeral recognition system. In: Eighth International Conference on Document Analysis and Recognition (ICDAR'05); Seoul, Korea (South). IEEE; 2005. p. 770–774.
   Google Scholar
• Pal U, Sharma N, Wakabayashi T, et al. Handwritten numeral recognition of six popular Indian scripts. In: Ninth International Conference on Document Analysis and Recognition (ICDAR 2007); Vol. 2; Curitiba, Brazil. IEEE; 2007. p. 749–753.
   Google Scholar
• Bhowmik TK, Parui SK, Bhattacharya U, et al. An HMM based recognition scheme for handwritten Oriya numerals. In: 9th International Conference on Information Technology (ICIT'06); Bhubaneswar, India. IEEE; 2006. p. 105–110.
   Google Scholar
• Jindal T, Bhattacharya U. Recognition of offline handwritten numerals using an ensemble of MLPs combined by adaboost. In: Proceedings of the 4th International Workshop on Multilingual OCR. ACM; 2013. p. 1–5.
   Google Scholar
• Dash KS, Puhan N, Panda G. A hybrid feature and discriminant classifier for high accuracy handwritten Odia numeral recognition. In: 2014 IEEE Region 10 Symposium; Kuala Lumpur, Malaysia. IEEE; 2014. p. 531–535.
   Google Scholar
• Dash KS, Puhan NB, Panda G. Handwritten numeral recognition using non-redundant stockwell transform and bio-inspired optimal zoning. IET Image Process. 2015;9(10):874–882.
   Web of Science ®Google Scholar
• Mohapatra RK, Mishra TK, Panda S, et al. OHCS: A database for handwritten atomic Odia character recognition. In: 2015 Fifth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG); Patna, India. IEEE; 2015. p. 1–4.
   Google Scholar
• Sethy A, Patra PK, Nayak S, et al. Symmetric axis based off-line Odia handwritten character and numeral recognition. In: 2017 3rd International Conference on Computational Intelligence and Networks (CINE); Odisha, India. IEEE; 2017. p. 83–87.
   Google Scholar
• Sethy A, Patra PK, Nayak DR. Off-line handwritten Odia character recognition using DWT and PCA. In: Kacprzyk J, editor. Progress in advanced computing and intelligent engineering. Springer; 2018. p. 187–195.
   Google Scholar
• Sethy A, Patra PK. Off-line Odia handwritten character recognition: an axis constellation model based research. Int J Innov Technol Explor Eng (IJITEE). 2019;8(9S2):788–793.
   Google Scholar
• Das D, Nayak DR, Dash R, et al. MJCN: Multi-objective Jaya convolutional network for handwritten optical character recognition. Multimed Tools Appl. 2020;79(43–44):33023–33042.
   Web of Science ®Google Scholar
• Dash KS, Puhan NB, Panda G. Odia character recognition: a directional review. Artif Intell Rev. 2017;48(4):473–497.
   Web of Science ®Google Scholar
• Das D, Dash R, Majhi B. Optimization based feature generation for handwritten Odia-numeral recognition. In: 2018 Fourteenth International Conference on Information Processing (ICINPRO); Bangalore, India. IEEE; 2018. p. 1–5.
   Google Scholar
• Dash KS, Puhan NB, Panda G. Sparse concept coded Tetrolet transform for unconstrained Odia character recognition. arXiv preprint arXiv:200401551, abs/2004.01551. 2020.
   Google Scholar
• Sethy A, Patra PK, Nayak SR. Offline handwritten numeral recognition using convolution neural network. Mach Vis Inspect Syst. 2020;1:197–212.
   Google Scholar
• Alzubi J, Nayyar A, Kumar A. Machine learning from theory to algorithms: an overview. J Phys Conf Ser. 2018;1142:Article ID 012012.
   Google Scholar
• El-Sawy A, Hazem EB, Loey M. CNN for handwritten Arabic digits recognition based on LeNet-5. In: International Conference on Advanced Intelligent Systems and Informatics; Cham: Springer; 2016. p. 566–575.
   Google Scholar
• Dey R, Balabantaray RC, Piri J, et al. Offline natural scene character recognition using VGG16 neural networks. In: 2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA); Coimbatore, India; IEEE; 2021. p. 946–951.
   Google Scholar
• Rani NS, Subramani A, Kumar A, et al. Deep learning network architecture based Kannada handwritten character recognition. In: 2020 Second International Conference on Inventive Research in Computing Applications (ICIRCA); Coimbatore, India; IEEE; 2020. p. 213–220.
   Google Scholar
• Alyahya H, Ismail MMB, Al-Salman A. Deep ensemble neural networks for recognizing isolated Arabic handwritten characters. ACCENTS Trans Image Process Comput Vis. 2020;6(21):68.
   Google Scholar
• Mohapatra RK, Shaswat K, Kedia S. Offline handwritten signature verification using CNN inspired by inception V1 architecture. In: 2019 Fifth International Conference on Image Information Processing (ICIIP); Shimla, India; IEEE; 2019. p. 263–267.
   Google Scholar
• Singh J, Bhushan B. Real time Indian license plate detection using deep neural networks and optical character recognition using LSTM Tesseract. In: 2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS); Greater Noida, India; IEEE; 2019. p. 347–352.
   Google Scholar
• Tallapragada V, Alivelu Manga N, Nagabhushanam M, et al. Greek handwritten character recognition using inception V3. In: Howlett RJ, Jain LC, editors. Smart systems: innovations in computing. Springer; 2022. p. 247–257.
   Google Scholar
• Zeng Z, Gao P, Sun S. License plate recognition system based on transfer learning. In: International Conference on Signal and Information Processing, Networking and Computers; Springer; 2018. p. 42–49.
   Google Scholar
• Huh M, Agrawal P, Efros AA. What makes imagenet good for transfer learning? arXiv preprint arXiv:160808614. 2016.
   Google Scholar
• Modhej N, Bastanfard A, Teshnehlab M, et al. Pattern separation network based on the hippocampus activity for handwritten recognition. IEEE Access. 2020;8:212803–212817.
   Web of Science ®Google Scholar
• Ghosh S, Chatterjee A, Singh PK, et al. Language-invariant novel feature descriptors for handwritten numeral recognition. Vis Comput. 2020;37:1781–1803.
   Web of Science ®Google Scholar
• Saha P, Jaiswal A. Handwriting recognition using active contour. In: Kacprzyk J, editors. Artificial intelligence and evolutionary computations in engineering systems. Springer; 2020. p. 505–514.
   Google Scholar
• Majid N, Smith EHB. Introducing the Boise State Bangla handwriting dataset and an efficient offline recognizer of isolated Bangla characters. In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR); Niagara Falls, NY, USA; IEEE; 2018. p. 380–385.
   Google Scholar
• Rabby ASA, Haque S, Islam S, et al. Bornonet: Bangla handwritten characters recognition using convolutional neural network. Procedia Comput Sci. 2018;143:528–535.
   Google Scholar
• Das D, Nayak DR, Dash R, et al. An empirical evaluation of extreme learning machine: application to handwritten character recognition. Multimed Tools Appl. 2019;78(14):19495–19523.
   Web of Science ®Google Scholar