Siamese Neural Network Model for Recognizing Optically Processed Devanagari Hindi Script
DOI:
https://doi.org/10.5281/zenodo.8210372Keywords:
Optical Character Recognition, Deep learning, Siamese Neural Networks, Deep neural Network, Dissimilarity ScoreAbstract
Optical Character Recognition (OCR) is a technology that allows computers to recognize and extract text from images or scanned documents. It is commonly used to convert printed or handwritten text into machine-readable format. This Study presents an OCR system on Devanagari script Hindi Characters based on Siamese Neural Network. Here the Siamese Neural Network, a Deep neural network which comprises of two identical Convolution Network compare the script and ranks based on the dissimilarity. When lesser dissimilarity score is identified, prediction is done as character match. In this work the authors use 5 classes of Hindi characters which were initially preprocessed using grey scaling and convert it to pgm format. This is directly input into the Deep convolutional network which are learnt from matching and non-matching image between the CNN with contrastive loss function in Siamese architecture. The Proposed OCR system uses very less time and gives more accurate results as compared to the regular CNN.References
Kaur, J., Goyal, V., & Kumar, M. (2021, November). Tesseract OCR for Hindi Typewritten Documents. In 2021 Sixth International Conference on Image Information Processing (ICIIP) (Vol. 6, pp. 450-454). IEEE.
Melekhov, I., Kannala, J., & Rahtu, E. (2016, December). Siamese network features for image matching. In 2016 23rd international conference on pattern recognition (ICPR) (pp. 378-383). IEEE.
Barakat, B. K., Alasam, R., & El-Sana, J. (2018, April). Word spotting using convolutional siamese network. In 2018 13th IAPR International Workshop on Document Analysis Systems (DAS) (pp. 229-234). IEEE.
Naseer, A., & Zafar, K. (2022). Meta‐feature based few‐shot Siamese learning for Urdu optical character recognition. Computational Intelligence, 38(5), 1707-1727.
Sokar, G., Hemayed, E. E., & Rehan, M. (2018, November). A generic OCR using deep siamese convolution neural networks. In 2018 IEEE 9th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) (pp. 1238-1244). IEEE.
Ahmed, S. T., & Basha, S. M. (2022). Information and Communication Theory-Source Coding Techniques-Part II. MileStone Research Publications.
Jenckel, M., Bukhari, S. S., & Dengel, A. (2018, August). Transcription free lstm ocr model evaluation. In 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR) (pp. 122-126). IEEE.
Jain, M., Mathew, M., & Jawahar, C. V. (2017, November). Unconstrained OCR for Urdu using deep CNN-RNN hybrid networks. In 2017 4th IAPR Asian Conference on Pattern Recognition (ACPR) (pp. 747-752). IEEE.
Mathew, M., Singh, A. K., & Jawahar, C. V. (2016, April). Multilingual OCR for Indic scripts. In 2016 12th IAPR Workshop on Document Analysis Systems (DAS) (pp. 186-191). IEEE.
Ambili, P. S., & Abraham, B. (2022). A Predictive Model for Student Employability Using Deep Learning Techniques. ECS Transactions, 107(1), 10149.
Avadesh, M., & Goyal, N. (2018, April). Optical character recognition for Sanskrit using convolution neural networks. In 2018 13th IAPR International Workshop on Document Analysis Systems (DAS) (pp. 447-452). IEEE.
Sharma, A. S., Mridul, M. A., Jannat, M. E., & Islam, M. S. (2018, September). A deep cnn model for student learning pedagogy detection data collection using ocr. In 2018 International Conference on Bangla Speech and Language Processing (ICBSLP) (pp. 1-6). IEEE.
Jain, M., Mathew, M., & Jawahar, C. V. (2017, November). Unconstrained OCR for Urdu using deep CNN-RNN hybrid networks. In 2017 4th IAPR Asian Conference on Pattern Recognition (ACPR) (pp. 747-752). IEEE.
Jatowt, A., Coustaty, M., Nguyen, N. V., & Doucet, A. (2019, June). Deep statistical analysis of OCR errors for effective post-OCR processing. In 2019 ACM/IEEE Joint Conference on Digital Libraries (JCDL) (pp. 29-38). IEEE.
Alla, K., & Prasad, R. S. R. (2010, April). A new approach to Hindi text steganography using matraye, core classification and HHK scheme. In 2010 Seventh International Conference on Information Technology: New Generations (pp. 1223-1224). IEEE.
Abraham, B., & Ambili, P. S. (2023). An Enhanced Career Prospect Prediction System for Non-computer Stream Students in Software Companies. In Computational Intelligence for Engineering and Management Applications: Select Proceedings of CIEMA 2022 (pp. 811-819). Singapore: Springer Nature Singapore.
Bansal, V., & Sinha, M. K. (2001, September). A complete OCR for printed Hindi text in Devanagari script. In Proceedings of Sixth International Conference on Document Analysis and Recognition (pp. 0800-0800). IEEE Computer Society.
Shah, R., Gupta, M. K., & Kumar, A. (2021, November). Ancient Sanskrit Line-level OCR using OpenNMT Architecture. In 2021 Sixth International Conference on Image Information Processing (ICIIP) (Vol. 6, pp. 347-352). IEEE.
Xiao, W., & Wu, D. (2021, December). An improved siamese network model for handwritten signature verification. In 2021 IEEE International Conference on Networking, Sensing and Control (ICNSC) (Vol. 1, pp. 1-6). IEEE.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Ambili P S, Agnesh L, Arun K V
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
CC Attribution-NonCommercial-NoDerivatives 4.0
