Zarif, S., Hammam, M., Wagdy, M. (2025). DEEP Learning Based Handwritten Recognition using Checkerboard Pattern. Journal of Computing and Communication, 4(2), 89-99. doi: 10.21608/jocc.2025.446644
Sameh Zarif; Mahmoud Hammam; Marian Wagdy. "DEEP Learning Based Handwritten Recognition using Checkerboard Pattern". Journal of Computing and Communication, 4, 2, 2025, 89-99. doi: 10.21608/jocc.2025.446644
Zarif, S., Hammam, M., Wagdy, M. (2025). 'DEEP Learning Based Handwritten Recognition using Checkerboard Pattern', Journal of Computing and Communication, 4(2), pp. 89-99. doi: 10.21608/jocc.2025.446644
Zarif, S., Hammam, M., Wagdy, M. DEEP Learning Based Handwritten Recognition using Checkerboard Pattern. Journal of Computing and Communication, 2025; 4(2): 89-99. doi: 10.21608/jocc.2025.446644
DEEP Learning Based Handwritten Recognition using Checkerboard Pattern
1Department of Information Technology, Faculty of Computers and Information, Menoufia University, Menoufia, Egypt
2MSc student at Banha University
3Department of Information Technology, Faculty of Computers and Information, Tanta University, Tanta, Egypt
Abstract
This research addresses Egypt's Vision 2030 by developing an AI system for automating optical character recognition for documents. This paper uses a deep learning to eliminate manual data entry and improve data accuracy, saving time and resources for organizations, which aligns with the Vision's goals of using AI for document processing and better decision-making. The paper uses mainly the checkerboard pattern to fix the de-warpping data on the bills, then the proposed method will be able to recognize the content of each bill separately and categorize the data inside those bills. The proposed method uses the mix of image correction for de-warpping the image and the usage of LSTMs to recognize the oriented text in the handwritten document. Also the checkerboard is aiding in the usage of the LSTM algorithm which advances its performance to be better than the other state of the art techniques for both the RIMES and IAM datasets.
[1] Ibrahim, M., Wagdy, M., AlHarithi, F. S., Qahtani, A. M., Elkilani, W. S., & Zarif, S. An Efficient Method for Document Correction Based on Checkerboard Calibration Pattern. Applied Sciences, 12(18), 9014, 2022.
[2] Baird, H.S., 2007. The state of the art of document image degradation modelling. Digital Document Processing: Major Directions and Recent Advances, pp.261-279.
[3] Wagdy, M., Amin, K., & Ibrahim, M. Dewarping document image techniques: survey and comparative study. International Journal of Image and Graphics, 21(03), 2150031, 2021.
[4] Gatos, B. and Ntirogiannis, K., 2007, February. Restoration of arbitrarily warped document images based on text line and word detection. In 4th IASTED International Conference on Signal Processing, Pattern Recognition, and Applications (pp. 203-208).
[5] Bouillon M, Anquetil E. Handwriting analysis with online fuzzy models. In17th Biennal Conference of the International Graphonomics Society (IGS) 2015 Jun 21.
[6] Simonnet D, Girard N, Anquetil E, Renault M, Thomas S. Evaluation of children cursive handwritten words for e-education. Pattern Recognition Letters. 2019 Apr 15;121:133-9.
[7] Li H, Zhu F, Qiu J. CG-DIQA: No-reference document image quality assessment based on character gradient. In2018 24th International Conference on Pattern Recognition (ICPR) 2018 Aug 20 (pp. 3622-3626).
[8] Schneider, D.; Block, M.; Rojas, R. Robust document warping with interpolated vector fields. In Proceedings of the Ninth International Conference on Document Analysis and Recognition (ICDAR 2007), Curitiba, Brazil, 23–26 September 2007; Volume 1, pp. 113–117.
[9] Bukhari, S.S.; Shafait, F.; Breuel, T.M. Dewarping of document images using coupled-snakes. In Proceedings of the Third International Workshop on Camera-Based Document Analysis and Recognition, Barcelona, Spain, 23–24 July 2009; pp. 34–41.
[10] Zhang, Y.; Liu, C.; Ding, X.; Zou, Y. Arbitrary warped document image restoration based on segmentation and Thin-Plate Splines. In Proceedings of the 2008 19th International Conference on Pattern Recognition, Tampa, FL, USA, 8–11 December 2008; pp. 1–4.
[11] Lu, S.; Chen, B.M.; Ko, C.C. A partition approach for the restoration of camera images of planar and curled document. Image Vis. Comput. 2006, 24, 837–848.
[12] Bolelli, F. Indexing of historical document images: Ad hoc dewarping technique for handwritten text. In Italian Research Conference on Digital Libraries; Springer: Cham, Switzerland, 2017; pp. 45–55.
[13] Leifert, G., Strau, T., Gr, T., Wustlich, W., Labahn, R., et al.: Cells in multidimensional recurrent neural networks. Journal of Machine Learning Research 17(97), 1–37 (2016).
[14] Krishnan, P., Dutta, K., Jawahar, C.: Word spotting and recognition using deep embedding. In: 2018 13th IAPR International Workshop on Document Analysis Systems (DAS). pp. 1–6. IEEE (2018).
[15] Dutta, K., Krishnan, P., Mathew, M., Jawahar, C.: Improving CNN-RNN hybrid networks for handwriting recognition. In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR). pp. 80–85, 2018.
[16] Retsinas, G., Sfikas, G., Nikou, C., Maragos, P.: Deformation-invariant networks for handwritten text recognition. In: 2021 IEEE International Conference on Image Processing (ICIP). pp. 949–953, 2021.
[17] Tassopoulou, V., Retsinas, G., Maragos, P.: Enhancing handwritten text recognition with n-gram sequence decomposition and multitask learning. In: 2020 25th International Conference on Pattern Recognition (ICPR). pp. 10555–10560, 2021.
[18] Chen, Z., Wu, Y., Yin, F., Liu, C.L.: Simultaneous script identification and handwriting recognition via multi-task learning of recurrent neural networks. In: 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). vol. 1, pp. 525–530, 2017.
[19] Pham, V., Bluche, T., Kermorvant, C., Louradour, J.: Dropout improves recurrent neural networks for handwriting recognition. In: 2014 14th international conference on frontiers in handwriting recognition. pp. 285–290. 2014.
[20] Chowdhury, A., Vig, L.: An efficient end-to-end neural model for handwritten text recognition, 2018.
[21] Puigcerver, J.: Are multidimensional recurrent layers really necessary for handwritten text recognition? In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). vol. 1, pp. 67–72. 2017.
[22] Markou, K., Tsochatzidis, L., Zagoris, K., Papazoglou, A., Karagiannis, X., Symeonidis, S., Pratikakis, I.: A convolutional recurrent neural network for the handwritten text recognition of historical greek manuscripts. In: International Workshop on Pattern Recognition for Cultural Heritage (PATRECH), 2020.
[23] Wick, C., Z¨ollner, J., Gr¨uning, T.: Transformer for handwritten text recognition using bidirectional post-decoding. In: International Conference on Document Analysis and Recognition. pp. 112–126, 2021.
[24] Michael, J., Labahn, R., Gr¨uning, T., Z¨ollner, J.: Evaluating sequence-to-sequence models for handwritten text recognition. In: 2019 International Conference on Document Analysis and Recognition (ICDAR). pp. 1286–1293, 2019.
[25] Yousef, M., Hussain, K.F., Mohammed, U.S.: Accurate, data-efficient, unconstrained text recognition with convolutional neural networks. Pattern Recognition 108, 107482, 2020.
[26] Retsinas, G., Sfikas, G., Gatos, B., & Nikou, C. “ Best practices for a handwritten text recognition system. arXiv:2404.11339v1, 17 Apr 2024.
View on SCiNiTO
Top