Acta Informatica Pragensia 2022, 11(3), 324-347 | DOI: 10.18267/j.aip.1973490

Classification of Handwritten Text Signatures by Person and Gender: A Comparative Study of Transfer Learning Methods

Sidar Agduk ORCID...1,2, Emrah Aydemir ORCID...2
Department of Management Information Systems, Faculty of Economics and Administrative Sciences, Tarsus University, Tarsus, Turkey
Department of Management Information Systems, Faculty of Business, Sakarya University, Sakarya, Turkey

The writing process, in which feelings and thoughts are expressed in writing, differs from person to person. Handwriting samples, which are very easy to obtain, are frequently used to identify individuals because they are biometric data. Today, with human-machine interaction increasing by the day, machine learning algorithms are frequently used in offline handwriting identification. Within the scope of this study, a dataset was created from 3250 handwritten images of 65 people. We tried to classify collected handwriting samples according to person and gender. In the classification made for person and gender recognition, feature extraction was done using 32 different transfer learning algorithms in the Python program. For person and gender estimation, the classification process was carried out using the random forest algorithm. 28 different classification algorithms were used, with DenseNet169 yielding the most successful results, and the data were classified in terms of person and gender. As a result, the highest success rates obtained in person and gender classification were 92.46% and 92.77%, respectively.

Keywords: Offline Handwriting Recognition; DenseNet169; Machine Learning.

Received: August 6, 2022; Revised: October 19, 2022; Accepted: October 21, 2022; Prepublished online: November 2, 2022; Published: December 26, 2022  Show citation

ACS AIP APA ASA Harvard Chicago Chicago Notes IEEE ISO690 MLA NLM Turabian Vancouver
Agduk, S., & Aydemir, E. (2022). Classification of Handwritten Text Signatures by Person and Gender: A Comparative Study of Transfer Learning Methods. Acta Informatica Pragensia, 11(3), 324-347. doi: 10.18267/j.aip.197
Download citation
  • BibTeX (.bib)
  • Bookends (.ris)
  • EasyBib (.ris)
  • EndNote (.enw)
  • EndNote 8 (.xml)
  • ISI WoS (.isi)
  • Medlars (.medlars)
  • Mendeley (.ris)
  • MODS (.xml)
  • Papers (.ris)
  • RefWorks (.txt)
  • RefManager (.ris)
  • RIS (.ris)
  • MS Word (.xml)
  • Zotero (.ris)
    • Open full article

    References

    1. Ağduk, S., & Aydemir, E. (2022). Handwriting Same Text Image - Data set. Kaggle. https://doi.org/10.34740/KAGGLE/DSV/3328630 Go to original source...
    2. Ahmad, A. R., Khalia, M., Viard-Gaudin, C., & Poisson, E. (2004, November). Online handwriting recognition using support vector machine. In 2004 IEEE Region 10 Conference TENCON 2004. (pp. 311-314). IEEE. https://doi.org/10.1109/TENCON.2004.1414419 Go to original source...
    3. Akyiğit, H. E. & Taşci, T. (2022). Customer churn analysis in the insurance sector using machine learning. Journal of Design Architecture and Engineering, 2(1), 66-79. https://dergipark.org.tr/en/pub/dae/issue/68555/1073934
    4. AlJarrah, M. N., Mo'ath, M. Z., & Duwairi, R. (2021, May). Arabic handwritten characters recognition using convolutional neural network. In 2021 12th International Conference on Information and Communication Systems (ICICS) (pp. 182-188). IEEE. https://doi.org/10.1109/ICICS52457.2021.9464596 Go to original source...
    5. Al Maadeed, S., & Hassaine, A. (2014). Automatic prediction of age, gender, and nationality in offline handwriting. EURASIP Journal on Image and Video Processing, 2014(1). https://doi.org/10.1186/1687-5281-2014-10 Go to original source...
    6. Almansari, O. A., & Hashim, N. N. W. N. (2019, October). Recognition of isolated handwritten Arabic characters. In 2019 7th International Conference on Mechatronics Engineering (ICOM) (pp. 1-5). IEEE. https://doi.org/10.1109/ICOM47790.2019.8952035 Go to original source...
    7. Alyahya, H., Ismail, M. M. B., & Al-Salman, A. (2020). Deep ensemble neural networks for recognizing isolated Arabic handwritten characters. ACCENTS Transactions on Image Processing and Computer Vision, 6(21), Article no. 68. https://doi.org/10.19101/TIPCV.2020.618051 Go to original source...
    8. Aydemir, E., & Al-Azzawi, M. S. H. (2022). Classification of foot images according to person, age, and gender with the local phase quantization. Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, 11(3), 467-476. https://doi.org/10.28948/ngumuh.1055199 Go to original source...
    9. Bouadjenek, N., Nemmour, H., & Chibani, Y. (2014, August). Local descriptors to improve off-line handwriting-based gender prediction. In 2014 6th International Conference of Soft Computing and Pattern Recognition (SoCPaR) (pp. 43-47). IEEE. https://doi.org/10.1109/SOCPAR.2014.7007979 Go to original source...
    10. Bouadjenek, N., Nemmour, H., & Chibani, Y. (2015, August). Age, gender and handedness prediction from handwriting using gradient features. In 2015 13th International Conference on Document Analysis and Recognition (ICDAR) (pp. 1116-1120). IEEE. https://doi.org/10.1109/ICDAR.2015.7333934 Go to original source...
    11. Bulacu, M., & Schomaker, L. (2007). Text-Independent Writer Identification and Verification Using Textural and Allographic Features. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(4), 701-717. https://doi.org/10.1109/tpami.2007.1009 Go to original source...
    12. Cha, S. H., & Srihari, S. N. (2001, September). A priori algorithm for sub-category classification analysis of handwriting. In Proceedings of Sixth International Conference on Document Analysis and Recognition (pp. 1022-1025). IEEE. https://doi.org/10.1109/ICDAR.2001.953940 Go to original source...
    13. Dagdeviren, E. (2013). Comparison Of Support Vector Machines and Artificial Neural Networks for Handwritten Digit Recognition. Master's Thesis. Istanbul University.
    14. Demirkaya, K. G., & Çavuşoğlu, Ü. (2022). Handwritten Digit Recognition With Machine Learning Algorithms. Academic Platform Journal of Engineering and Smart Systems, 10(1), 9-18. https://doi.org/10.21541/apjess.1060753 Go to original source...
    15. Djeddi, C., Siddiqi, I., Souici-Meslati, L., & Ennaji, A. (2013). Text-independent writer recognition using multi-script handwritten texts. Pattern Recognition Letters, 34(10), 1196-1202. https://doi.org/10.1016/j.patrec.2013.03.020 Go to original source...
    16. Erdinç, G. H. (2020). Processing Biometric Data in The Scope of Adequacy Principle and Consent. The Turkish Journal of Privacy and Data Protection, 2(1), 1-19.
    17. Erdoğan, A. A., & Tümer, A. E. (2021). Deep Learning Method for Handwriting Recognition. MANAS Journal of Engineering, 9(1), 85-92. https://doi.org/10.51354/mjen.852312 Go to original source...
    18. Gawda, B. (2008). A Graphical Analysis of Handwriting of Prisoners Diagnosed with Antisocial Personality. Perceptual and Motor Skills, 107(3), 862-872. https://doi.org/10.2466/pms.107.3.862-872 Go to original source...
    19. He, M., Zhang, S., Mao, H., & Jin, L. (2015, August). Recognition confidence analysis of handwritten Chinese character with CNN. In 2015 13th International Conference on Document Analysis and Recognition (ICDAR) (pp. 61-65). IEEE. https://doi.org/10.1109/ICDAR.2015.7333726 Go to original source...
    20. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778). IEEE. https://doi.org/10.1109/CVPR.2016.90 Go to original source...
    21. Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition. IEEE. https://doi.org/10.1109/CVPR.2017.243 Go to original source...
    22. Ibrahim, A. S., Youssef, A. E., & Abbott, A. L. (2014, December). Global vs. local features for gender identification using Arabic and English handwriting. In 2014 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT) (pp. 155-160). IEEE. https://doi.org/10.1109/ISSPIT.2014.7300580 Go to original source...
    23. Kalsi, K. S., & Rai, P. (2017, January). A classification of emotion and gender using approximation image Gabor local binary pattern. In 2017 7th International Conference on Cloud Computing, Data Science & Engineering-Confluence (pp. 623-628). IEEE. https://doi.org/10.1109/CONFLUENCE.2017.7943227 Go to original source...
    24. Karakaya, R. (2020). Handwriting Recognition Using Machine Learning. Master's Thesis. Sakarya University. Go to original source...
    25. Katiyar, G., Katiyar, A., & Mehfuz, S. (2017). Off-Line Handwritten Character Recognition System Using Support Vector Machine. American Journal of Neural Networks and Applications, 3(2), 22-28. https://doi.org/10.11648/j.ajnna.20170302.12 Go to original source...
    26. Khandokar, I., Hasan, M., Ernawan, F., Islam, S., & Kabir, M. N. (2021). Handwritten character recognition using convolutional neural network. Journal of Physics: Conference Series, 1918(4), 042152. https://doi.org/10.1088/1742-6596/1918/4/042152 Go to original source...
    27. Kirli, Ö., & Gülmezoğlu, M. B. (2012). Automatic writer identification from text line images. International Journal on Document Analysis and Recognition, 15(2), 85-99. https://doi.org/10.1007/s10032-011-0161-9 Go to original source...
    28. Knerr, S., Personnaz, L., & Dreyfus, G. (1992). Handwritten digit recognition by neural networks with single-layer training. IEEE Transactions on Neural Networks, 3(6), 962-968. https://doi.org/10.1109/72.165597 Go to original source...
    29. Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84-90. https://doi.org/10.1145/3065386 Go to original source...
    30. Küpeli, C. & Bulut, F. (2020). Görüntüdeki Tuz Biber ve Gauss Gürültülerine Karşi Filtrelerin Performans Analizleri. Haliç Üniversitesi Fen Bilimleri Dergisi, 3(2), 211-239. https://doi.org/10.46373/hafebid.768240 Go to original source...
    31. Lemarié, B. (1993, October). Practical implementation of a radial basis function network for handwritten digit recognition. In Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR'93) (pp. 412-415). IEEE. https://doi.org/10.1109/ICDAR.1993.395705 Go to original source...
    32. Liwicki, M., Schlapbach, A., & Bunke, H. (2011). Automatic gender detection using on-line and off-line information. Pattern Analysis and Applications, 14(1), 87-92. https://doi.org/10.1007/s10044-010-0178-6 Go to original source...
    33. Mai, T. A., & Suen, C. Y. (1990). A generalized knowledge-based system for the recognition of unconstrained handwritten numerals. IEEE Transactions on Systems, Man, and Cybernetics, 20(4), 835-848. https://doi.org/10.1109/21.105083 Go to original source...
    34. Maji, P., Chatterjee, S., Chakraborty, S., Kausar, N., Samanta, S., & Dey, N. (2015, March). Effect of Euler number as a feature in gender recognition system from offline handwritten signature using neural networks. In 2015 2nd International Conference on Computing for Sustainable Global Development (INDIACom) (pp. 1869-1873). IEEE.
    35. Morera, Á., Sánchez, Á., Vélez, J. F., & Moreno, A. B. (2018). Gender and Handedness Prediction from Offline Handwriting Using Convolutional Neural Networks. Complexity, 2018, Article ID 3891624. https://doi.org/10.1155/2018/3891624 Go to original source...
    36. Najadat, H. M., Alshboul, A. A., & Alabed, A. F. (2019). Arabic Handwritten Characters Recognition using Convolutional Neural Network. In 2019 10th International Conference on Information and Communication Systems (ICICS), (pp. 147-151). IEEE. https://doi.org/10.1109/IACS.2019.8809122. Go to original source...
    37. Nasien, D., Haron, H., & Yuhaniz, S. S. (2010, March). Support Vector Machine (SVM) for English handwritten character recognition. In 2010 Second international conference on computer engineering and applications (Vol. 1, pp. 249-252). IEEE. https://doi.org/10.1109/ICCEA.2010.56 Go to original source...
    38. Navya, B. J., Shivakumara, P., Shwetha, G. C., Roy, S., Guru, D. S., Pal, U., & Lu, T. (2018, August). Adaptive multi-gradient kernels for handwritting based gender identification. In 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR) (pp. 392-397). IEEE. https://doi.org/10.1109/ICFHR-2018.2018.00075 Go to original source...
    39. Pal, A., & Singh, D. (2010). Handwritten English character recognition using neural network. International Journal of Computer Science & Communication, 1(2), 141-144.
    40. Plamondon, R., & Srihari, S. N. (2000). Online and off-line handwriting recognition: a comprehensive survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(1), 63-84. https://doi.org/10.1109/34.824821 Go to original source...
    41. Powers, D. M. (2011). Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. Journal of Machine Learning Technologies, 2(1), 37-63.
    42. Rao, S., & Aditya, J. (2014). Handwriting Recognition|Offline Approach. https://cs.stanford.edu/people/adityaj/HandwritingRecognition.pdf
    43. Sadri, J., Suen, C. Y., & Bui, T. D. (2003, February). Application of support vector machines for recognition of handwritten Arabic/Persian digits. In Proceedings of Second Iranian Conference on Machine Vision and Image Processing (Vol. 1, pp. 300-307). http://www.cenparmi.concordia.ca/publications/pdf/2003/MVIP2003.pdf
    44. Seong-Whan, L. (1996). Off-line recognition of totally unconstrained handwritten numerals using multilayer cluster neural network. IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(6), 648-652. https://doi.org/10.1109/34.506416 Go to original source...
    45. Sharma, V., Bains, M., Verma, R., Verma, N., & Kumar, R. (2021). Novel use of logistic regression and likelihood ratios for the estimation of gender of the writer from a database of handwriting features. Australian Journal of Forensic Sciences, (in press), 1-18. https://doi.org/10.1080/00450618.2021.1956587 Go to original source...
    46. Siddiqi, I., & Vincent, N. (2010). Text independent writer recognition using redundant writing patterns with contour-based orientation and curvature features. Pattern Recognition, 43(11), 3853-3865. https://doi.org/10.1016/j.patcog.2010.05.019 Go to original source...
    47. Simonyan, K., & Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556. https://doi.org/10.48550/arXiv.1409.1556 Go to original source...
    48. Intrator, N., Steinherz, T., & Rivlin, E. (1999). Offline cursive script word recognition - A survey. International Journal on Document Analysis and Recognition, 2(2-3), 90-110. https://doi.org/10.1007/s100320050040 Go to original source...
    49. Şekerci, M. (2007). Compound and Oblique Turkish Handwriting Recognition System. Master's Thesis. Trakya University.
    50. Tolosana, R., Vera-Rodriguez, R., Ortega-Garcia, J., & Fierrez, J. (2015). Preprocessing and Feature Selection for Improved Sensor Interoperability in Online Biometric Signature Verification. IEEE Access, 3, 478-489. https://doi.org/10.1109/access.2015.2431493 Go to original source...
    51. Tomai, C. I., Kshirsagar, D. M., & Srihari, S. N. (2003, December). Group discriminatory power of handwritten characters. In Document Recognition and Retrieval XI (Vol. 5296, pp. 116-123). SPIE. https://doi.org/10.1117/12.527276 Go to original source...
    52. Topaloglu, M., & Ekmekci, S. (2017). Gender detection and identifying one's handwriting with handwriting analysis. Expert Systems with Applications, 79, 236-243. https://doi.org/10.1016/j.eswa.2017.03.001 Go to original source...
    53. Tuncer, T., Aydemir, E., Ozyurt, F., & Dogan, S. (2022). A deep feature warehouse and iterative MRMR based handwritten signature verification method. Multimedia Tools and Applications, 81(3), 3899-3913. https://doi.org/10.1007/s11042-021-11726-x Go to original source...
    54. Yang, W., Jin, L., & Liu, M. (2016). DeepWriterID: An End-to-End Online Text-Independent Writer Identification System. IEEE Intelligent Systems, 31(2), 45-53. https://doi.org/10.1109/mis.2016.22 Go to original source...
    55. Yilmaz, B. (2014). Design of A Mobile Device Application with Handwriting Recognition to Make Learning Easy for Students Who Have Learning Disabilities. Master's Thesis. Maltepe University.
    56. Younis, K. S. (2017). Arabic hand-written character recognition based on deep convolutional neural networks. Jordanian Journal of Computers and Information Technology, 3(3),186-200. https://doi.org/10.5455/jjcit.71-1498142206 Go to original source...
    57. Yuan, A., Bai, G., Jiao, L., & Liu, Y. (2012, March). Offline handwritten English character recognition based on convolutional neural network. In 2012 10th IAPR International Workshop on Document Analysis Systems (pp. 125-129). IEEE. https://doi.org/10.1109/DAS.2012.61 Go to original source...
    58. Zhao, H. H., & Liu, H. (2020). Multiple classifiers fusion and CNN feature extraction for handwritten digits recognition. Granular Computing, 5(3), 411-418. https://doi.org/10.1007/s41066-019-00158-6 Go to original source...

    This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits use, distribution, and reproduction in any medium, provided the original publication is properly cited. No use, distribution or reproduction is permitted which does not comply with these terms.


    Return to the content