Abstract
These days a large number of handwritten documents are available in scanned images. The aim of Handwritten Text Recognition (HTR) is to transcribe the offline document images by a computer through the use of deep neural networks. Even though hybrid architectures, designed for this purpose are gaining popularity, we aim to further optimize the prescribed models by changing the hyperparameters associated with the number of convolutional neural network layers on the overall accuracy. We explore the implementation of hybrid architectures and show that mainly the depth of the network plays a noteworthy role in improving the accuracy of the trained model.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. In: Proceedings of the IEEE (1998)
Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press (2016)
Greff, K., Srivastava, R.,KoutnÃk, J., Steunebrink, B., Schmidhuber, J.: LSTM:asearchspaceodyssey.IEEETrans.NeuralNetw. Learn. Syst. 2222–2232 (2017)
Graves, A., Fernandez, S., Schmidhuber, J.: Multidimensional recurrent neural networks. In: International Conference on Artificial Neural Networks. Porto, Portugal, Sept 2007
Hochreiter, S.:UntersuchungenzudynamischenneuronalenNetzen.Master’s thesis, TechnischeUniversität. München (1991)
Hochreiter. S.,Schmidhuber, J.: Longshort-termmemory. NeuralComput. (1997)
Graves, A.: Supervised sequence labelling with recurrent neural networks. Springer (2012)
Wu, Y.-C., Yin, F., Chen, Z., Liu, C.-L.: Handwritten Chinese text recognition using separable multi-dimensional recurrent neural network. In: 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). Kyoto (2017)
Stuner, B., Chatelain, C., Paquet, T.: Handwriting recognition using cohort of LSTM and lexicon verification with extremely large lexicon (2016). CoRR, abs/1612.07528
Jain, M., Mathew, M., Jawahar, C.V.: Unconstrained OCR for Urdu using deep CNN-RNN hybrid networks. In: 4th IAPR Asian Conference on Pattern Recognition (ACPR), pp. 747–752. Nanjing (2017)
Chen, Z., Wu, Y., Yin, F., Liu, C.L.: Simultaneous script identification and handwriting recognition via multi-task learning of recurrent neural networks. ICDAR (2017)
Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-basedsequencerecognitionanditsapplicationtoscenetextrecognition. IEEE Trans. Pattern Anal. Mach. Intel.
Pham, V., Bluche, T., Kermorvant, C., Louradour, J.: Dropout improves recurrent neural networks for handwriting recognition. In: International Conference on Frontiers in Handwriting Recognition (2014)
Scheidl, H., Fiel, S., Sablatnig, R.: Word Beam Search: A Connectionist Temporal Classification. ICFHR (2018)
Keren, G., Schuller, B.: Convolutional RNN: an enhanced model for extracting features from sequential data. In: International Joint Conference Neural Network, pp. 3412–3419 (2016)
Bluche, T.: Deep neural networks for large vocabulary handwritten text recognition. Ph.D. Thesis Université Paris Sud-Paris XI (2015)
Graves, A., Liwicki, M., Fernández, S., Bertolami, R., Bunke, H., Schmidhuber, J.: A novel connectionist system for unconstrained handwriting recognition. IEEE Trans. Pattern Anal. Mach. Intel. 31(5), 855–868 (2009)
Marti, U.-V., Bunke, H.: The IAM-database: an English sentence database for offline handwriting recognition. IJDAR (2002)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Goel, C., Chaudhary, A., Indu, S., Majumdar, S. (2021). Deep Neural Network Optimization for Handwritten Text Recognition. In: Panigrahi, C.R., Pati, B., Pattanayak, B.K., Amic, S., Li, KC. (eds) Progress in Advanced Computing and Intelligent Engineering. Advances in Intelligent Systems and Computing, vol 1299. Springer, Singapore. https://doi.org/10.1007/978-981-33-4299-6_7
Download citation
DOI: https://doi.org/10.1007/978-981-33-4299-6_7
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-33-4298-9
Online ISBN: 978-981-33-4299-6
eBook Packages: EngineeringEngineering (R0)