Firefly Algorithm with Cauchy Crow Search Algorithm Based Feature Selection for English Character Recognition
Snehal Prabhakarrao Dongre
Department of Computer Science and Engineering, Shri Guru Gobind Singhji Institute of Engineering and Technology, Vishnupuri, Nanded, Maharashtra, India.
Department of Electronics and Telecommunication Engineering, Shri Guru Gobind Singhji Institute of Engineering and Technology, Vishnupuri, Nanded, Maharashtra, India.
In the present scenario, the identification of English characters from the synthesized, natural, and handwritten images is considered an emerging problem in the researchers’ community. The variations in writing style, size of the text, orientation of the text, complex backgrounds, and lower image resolution, along with irrelevant features make character recognition a challenging task. Therefore, a novel automated model of feature selection is implemented in this manuscript for Optical Character Recognition (OCR). In this research, the Firefly Algorithm with Improved Crow Search Algorithm (FAICSA) is proposed for selecting optimal feature vectors for enhancing the classification accuracy. This OCR considers the images acquired from Chars74K and real-time datasets which are pre-processed by implementing binarization and normalization techniques. From the pre-processed real-time images, the English characters are precisely segmented by performing morphological operations known as erosion and dilation. Moreover, the significant features from the images are extracted by using the Local Binary Pattern (LBP), Zernike Moments (ZM), Stroke Width Transform (SWT) and ResNet-18 model. At last, the selected optimal feature vectors from FAICSA are given to the stacked autoencoder model for effective OCR. The proposed FAICSA based OCR is analysed using Matthew’s Correlation Coefficient (MCC), sensitivity, Positive Predictive Value (PPV), accuracy, and specificity. The numerical examination states that the FAICSA-stacked autoencoder model attained higher recognition accuracies of 99.64% and 92.06% on the Chars74K and real-time datasets, which are superior values in contrast to those measured for conventional machine-learning classifiers and optimization algorithms.
N. D. Cilia, C. De Stefano, F. Fontanella, and A. Scotto di Freca, “A ranking-based feature selection approach for handwritten character recognition,” Pattern Recognition Letters, vol. 121, pp. 77–86, Apr. 2019, doi: 10.1016/j.patrec.2018.04.007.
A. K. Sampath and N. Gomathi, “Handwritten optical character recognition by hybrid neural network training algorithm,” The Imaging Science Journal, vol. 67, no. 7, pp. 359–373, Sep. 2019, doi: 10.1080/13682199.2019.1661591.
R. Ahmed et al., “Novel Deep Convolutional Neural Network-Based Contextual Recognition of Arabic Handwritten Scripts,” Entropy, vol. 23, no. 3, p. 340, Mar. 2021, doi: 10.3390/e23030340.
R. S. Alkhawaldeh, “Arabic (Indian) digit handwritten recognition using recurrent transfer deep architecture,” Soft Computing, vol. 25, no. 4, pp. 3131–3141, Oct. 2020, doi: 10.1007/s00500-020-05368-8.
S. Misra and R. H. Laskar, “Integrated features and GMM Based Hand Detector Applied to Character Recognition System under Practical Conditions,” Multimedia Tools and Applications, vol. 78, no. 24, pp. 34927–34961, Sep. 2019, doi: 10.1007/s11042-019-08105-y.
P. Sahare and S. B. Dhok, “Robust Character Segmentation and Recognition Schemes for Multilingual Indian Document Images,” IETE Technical Review, vol. 36, no. 2, pp. 209–222, Apr. 2018, doi: 10.1080/02564602.2018.1450649.
N. R. Soora, E. Ur, and S. Waseem, “A Novel Geometrical Scale and Rotation Independent Feature Extraction Technique for Multi-lingual Character Recognition,” International Journal of Advanced Computer Science and Applications, vol. 11, no. 11, 2020, doi: 10.14569/ijacsa.2020.0111130.
N. Modhej, A. Bastanfard, M. Teshnehlab, and S. Raiesdana, “Pattern Separation Network Based on the Hippocampus Activity for Handwritten Recognition,” IEEE Access, vol. 8, pp. 212803–212817, 2020, doi: 10.1109/access.2020.3040298.
Md. H. H. Nashif et al., “Handwritten Numeric and Alphabetic Character Recognition and Signature Verification Using Neural Network,” Journal of Information Security, vol. 09, no. 03, pp. 209–224, 2018, doi: 10.4236/jis.2018.93015.
S. P. Deore and A. Pravin, “Devanagari Handwritten Character Recognition using fine-tuned Deep Convolutional Neural Network on trivial dataset,” Sādhanā, vol. 45, no. 1, Sep. 2020, doi: 10.1007/s12046-020-01484-1.
L. Xu, Y. Wang, R. Li, X. Yang, and X. Li, “A Hybrid Character Recognition Approach Using Fuzzy Logic and Stroke Bayesian Program Learning With Naïve Bayes in Industrial Environments,” IEEE Access, vol. 8, pp. 124767–124782, 2020, doi: 10.1109/access.2020.3007487.
M. Jangid and S. Srivastava, “Handwritten Devanagari Character Recognition Using Layer-Wise Training of Deep Convolutional Neural Networks and Adaptive Gradient Methods,” Journal of Imaging, vol. 4, no. 2, p. 41, Feb. 2018, doi: 10.3390/jimaging4020041.
S. R. Narang, M. K. Jindal, and M. Kumar, “Devanagari ancient character recognition using DCT features with adaptive boosting and bootstrap aggregating,” Soft Computing, vol. 23, no. 24, pp. 13603–13614, Mar. 2019, doi: 10.1007/s00500-019-03897-5.
N. P. Sutramiani, N. Suciati, and D. Siahaan, “MAT-AGCA: Multi Augmentation Technique on small dataset for Balinese character recognition using Convolutional Neural Network,” ICT Express, vol. 7, no. 4, pp. 521–529, Dec. 2021, doi: 10.1016/j.icte.2021.04.005.
S. Chandure and V. Inamdar, “Handwritten MODI Character Recognition Using Transfer Learning with Discriminant Feature Analysis,” IETE Journal of Research, vol. 69, no. 5, pp. 2584–2594, Apr. 2021, doi: 10.1080/03772063.2021.1902867.
K. Nongmeikapam, W. K. Kumar, O. N. Meetei, and T. Tuithung, “Increasing the effectiveness of handwritten Manipuri Meetei-Mayek character recognition using multiple-HOG-feature descriptors,” Sādhanā, vol. 44, no. 5, Apr. 2019, doi: 10.1007/s12046-019-1086-0.
S. Inunganbi, P. Choudhary, and K. M. Singh, “Local texture descriptors and projection histogram based handwritten Meitei Mayek character recognition,” Multimedia Tools and Applications, vol. 79, no. 3–4, pp. 2813–2836, Dec. 2019, doi: 10.1007/s11042-019-08482-4.
F. Naiemi, V. Ghods, and H. Khalesi, “An efficient character recognition method using enhanced HOG for spam image detection,” Soft Computing, vol. 23, no. 22, pp. 11759–11774, Jan. 2019, doi: 10.1007/s00500-018-03728-z.
E. H. Houssein, D. Oliva, E. Çelik, M. M. Emam, and R. M. Ghoniem, “Boosted sooty tern optimization algorithm for global optimization and feature selection,” Expert Systems with Applications, vol. 213, p. 119015, Mar. 2023, doi: 10.1016/j.eswa.2022.119015.
S. R. Zanwar, Y. H. Bhosale, D. L. Bhuyar, Z. Ahmed, U. B. Shinde, and S. P. Narote, “English Handwritten Character Recognition Based on Ensembled Machine Learning,” Journal of The Institution of Engineers (India): Series B, vol. 104, no. 5, pp. 1053–1067, Sep. 2023, doi: 10.1007/s40031-023-00917-9.
S. P. T. Parashivamurthy and S. V. Rajashekararadhya, “HDLNet: design and development of hybrid deep learning network for optimally recognising the handwritten Kannada characters,” Australian Journal of Electrical and Electronics Engineering, vol. 21, no. 3, pp. 268–288, Mar. 2024, doi: 10.1080/1448837x.2024.2316497.
S. N. Devi and N. S. Fatima, “Handwritten optical character recognition using TransRNN trained with self improved flower pollination algorithm (SI-FPA),” Multimedia Tools and Applications, vol. 84, no. 18, pp. 19947–19969, Jul. 2024, doi: 10.1007/s11042-024-19758-9.
R. Ptucha, F. Petroski Such, S. Pillai, F. Brockler, V. Singh, and P. Hutkowski, “Intelligent character recognition using fully convolutional neural networks,” Pattern Recognition, vol. 88, pp. 604–613, Apr. 2019, doi: 10.1016/j.patcog.2018.12.017.
R. Anand, T. Shanthi, R. S. Sabeenian, and S. Veni, “Real time noisy dataset implementation of optical character identification using CNN,” International Journal of Intelligent Enterprise, vol. 7, no. 1/2/3, p. 67, 2020, doi: 10.1504/ijie.2020.104646.
S. Lee, W. Yu, and C. Yang, “ILBPSDNet: Based on improved local binary pattern shallow deep convolutional neural network for character recognition,” IET Image Processing, vol. 16, no. 3, pp. 669–680, Apr. 2021, doi: 10.1049/ipr2.12226.
CRediT Author Statement
The authors confirm contribution to the paper as follows:
Conceptualization: Snehal Prabhakarrao Dongre;
Methodology: Dharmpal D Doye;
Data Curation: Dharmpal D Doye;
Manuscript Original Draft: Dharmpal D Doye;
Visualization: Snehal Prabhakarrao Dongre;
Investigation: Snehal Prabhakarrao Dongre;
Supervision: Dharmpal D Doye;
Validation: Dharmpal D Doye;
Formal Analysis: Snehal Prabhakarrao Dongre;
Resources: Snehal Prabhakarrao Dongre;
Project Administration: Snehal Prabhakarrao Dongre;
Manuscript - Review & Editing: Dharmpal D Doye; All authors reviewed the results and approved the final version of the manuscript.
Acknowledgements
Author(s) thanks to Shri Guru Gobind Singhji Institute of Engineering and Technology for research lab and equipment support.
Funding
No funding was received to assist with the preparation of this manuscript.
Ethics declarations
Conflict of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Availability of data and materials
The datasets generated during and/or analysed during the current study are available in the Chars74K. Chars74K dataset link = https://www.ee.surrey.ac.uk/CVSSP/demos/chars74k/.
Author information
Contributions
All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.
Corresponding author
Snehal Prabhakarrao Dongre
Department of Computer Science and Engineering, Shri Guru Gobind Singhji Institute of Engineering and Technology, Vishnupuri, Nanded, Maharashtra, India.
Open Access This article is licensed under a Creative Commons Attribution NoDerivs is a more restrictive license. It allows you to redistribute the material commercially or non-commercially but the user cannot make any changes whatsoever to the original, i.e. no derivatives of the original work. To view a copy of this license, visit https://creativecommons.org/licenses/by-nc-nd/4.0/
Cite this article
Snehal Prabhakarrao Dongre and Dharmpal D Doye, “Firefly Algorithm with Cauchy Crow Search Algorithm Based Feature Selection for English Character Recognition”, Journal of Machine and Computing, vol.5, no.4, pp. 2422-2437, October 2025, doi: 10.53759/7669/jmc202505187.
