Abstract
Due to the complex and irregular shapes of handwritten text, it is challenging to spot and recognize the handwritten words. In low-resource scripts, retrieval of words is a difficult and laborious task. The need for increasing the number of samples and introducing variations in the extended training datasets occur with the use of deep learning and neural network models. All possible variations and occurrences cannot be covered in an efficient manner with the use of the existing preprocessing strategies and theories. A scalable and elastic methodology for wrapping the extracted features is presented with the introduction of an adversarial feature deformation and regularization module in this paper. In the original deep learning framework, this module is introduced between the intermediate layers while training in an alternative manner. When compared to the conventional models, highly informative features are learnt in an efficient manner with the help of this setup. Extensive word datasets are used for testing the proposed model, which is built on popular frameworks available for word recognition and spotting, while enhancing them with the proposed module. While varying the training data size, the results are recorded and compared with the conventional models. Improvement in the mAP scores, word-error rate and low data regime is observed from the results of comparison.
References
Pham, V., Bluche, T., Kermorvant, C., & Louradour, J. (2014, September). Dropout improves recurrent neural networks for handwriting recognition. In 2014 14th international conference on frontiers in handwriting recognition (pp. 285-290). IEEE.
Huang, K., Hussain, A., Wang, Q. F., & Zhang, R. (Eds.). (2019). Deep learning: fundamentals, theory and applications (Vol. 2). springer.
Hamdan, Y. B. (2021). Construction of Statistical SVM based Recognition Model for Handwritten Character Recognition. Journal of Information Technology, 3(02), 92-107.
Shibly, Mir Moynuddin Ahmed, Tahmina Akter Tisha, and Shamim H. Ripon. "Stacked Generalization Ensemble Method to Classify Bangla Handwritten Character." In Proceedings of International Conference on Sustainable Expert Systems, pp. 621-638. Springer, Singapore, 2021.
Baldominos, A., Saez, Y., & Isasi, P. (2019). Hybridizing evolutionary computation and deep neural networks: an approach to handwriting recognition using committees and transfer learning. Complexity, 2019.
Dutta, K., Krishnan, P., Mathew, M., & Jawahar, C. V. (2018, August). Improving cnn-rnn hybrid networks for handwriting recognition. In 2018 16th international conference on frontiers in handwriting recognition (ICFHR) (pp. 80-85). IEEE.
Sinha, Gita, and Shailja Sharma. "Offline Handwritten Devanagari Character Identification." In International conference on Computer Networks, Big data and IoT, pp. 457-464. Springer, Cham, 2019.
Altwaijry, N., & Al-Turaiki, I. (2021). Arabic handwriting recognition system using convolutional neural network. Neural Computing and Applications, 33(7), 2249-2261.
Raj, Jennifer S., and Mr C. Vijesh Joe. "Wi-Fi Network Profiling and QoS Assessment for Real Time Video Streaming." IRO Journal on Sustainable Wireless Systems 3, no. 1 (2021): 21-30.
Amin, Sujit S., and Lata Ragha. "Alphanumeric Character Recognition on Tiny Dataset." In International conference on Computer Networks, Big data and IoT, pp. 657-667. Springer, Cham, 2019.
Suma, V. (2019). Computer vision for human-machine interaction-review. Journal of trends in Computer Science and Smart technology (TCSST), 1(02), 131-139.
Carbune, V., Gonnet, P., Deselaers, T., Rowley, H. A., Daryin, A., Calvo, M., ... & Gervais, P. (2020). Fast multi-language LSTM-based online handwriting recognition. International Journal on Document Analysis and Recognition (IJDAR), 23(2), 89-102.
Jacob, I. J. (2019). Capsule network based biometric recognition system. Journal of Artificial Intelligence, 1(02), 83-94.
Boufenar, C., Kerboua, A., & Batouche, M. (2018). Investigation on deep learning for off-line handwritten Arabic character recognition. Cognitive Systems Research, 50, 180-195.
Dhaya, R. "Light Weight CNN based Robust Image Watermarking Scheme for Security." Journal of Information Technology and Digital World 3, no. 2 (2021): 118-132.
Koresh, H. James Deva, and Shanty Chacko. "Hybrid speckle reduction filter for corneal OCT images." In International Conference on Image Processing and Capsule Networks, pp. 87-99. Springer, Cham, 2020.
Baldominos, A., Saez, Y., & Isasi, P. (2018). Evolutionary convolutional neural networks: An application to handwriting recognition. Neurocomputing, 283, 38-52.
Smys, S., Chen, J. I. Z., & Shakya, S. (2020). Survey on Neural Network Architectures with Deep Learning. Journal of Soft Computing Paradigm (JSCP), 2(03), 186-194.
Ahlawat, S., Choudhary, A., Nayyar, A., Singh, S., & Yoon, B. (2020). Improved handwritten digit recognition using convolutional neural networks (CNN). Sensors, 20(12), 3344.
Jacob, I. J., & Darney, P. E. (2021). Design of Deep Learning Algorithm for IoT Application by Image based Recognition. Journal of ISMAC, 3(03), 276-290.
Indumathi, V., and S. Prabakeran. "A Comparative Analysis on Sensor-Based Human Activity Recognition Using Various Deep Learning Techniques." In Computer Networks, Big Data and IoT, pp. 919-938. Springer, Singapore, 2021.
Haoxiang, W., & Smys, S. (2020). MC-SVM Based Workflow Preparation in Cloud with Named Entity Identification. Journal of Soft Computing Paradigm (JSCP), 2(02), 130-139.
Sueiras, J., Ruiz, V., Sanchez, A., & Velez, J. F. (2018). Offline continuous handwriting recognition using sequence to sequence neural networks. Neurocomputing, 289, 119-128.
Manoharan, J. S. (2021). Capsule Network Algorithm for Performance Optimization of Text Classification. Journal of Soft Computing Paradigm (JSCP), 3(01), 1-9.
Maalej, R., & Kherallah, M. (2020). Improving the DBLSTM for on-line Arabic handwriting recognition. Multimedia Tools and Applications, 79(25), 17969-17990.
Sathesh, A., & Adam, E. E. B. (2021). Hybrid Parallel Image Processing Algorithm for Binary Images with Image Thinning Technique. Journal of Artificial Intelligence, 3(03), 243-258.
Sen, S., Shaoo, D., Paul, S., Sarkar, R., & Roy, K. (2018). Online Handwritten Bangla Character Recognition Using CNN: A Deep Learning Approach. In Intelligent Engineering Informatics (pp. 413-420). Springer, Singapore.