Data Augmentation for Handwritten Character Recognition of MODI Script Using Deep Learning Method
- Title
- Data Augmentation for Handwritten Character Recognition of MODI Script Using Deep Learning Method
- Creator
- Joseph S.; George J.
- Description
- Deep learning-based methods such as convolutional neural networks are extensively used for various pattern recognition tasks. To successfully carry out these tasks, a large amount of training data is required. The scarcity of a large number of handwritten images is a major problem in handwritten character recognition; this problem can be tackled using data augmentation techniques. In this paper, we have proposed a convolutional neural network-based character recognition method for MODI script in which the data set is subjected to augmentation. The MODI script was an official script used to write Marathi, until 1950, the script is no more used as an official script. The preparation of a large number of handwritten characters is a tedious and time-consuming task. Data augmentation is very useful in such situations. Our study uses different types of augmentation techniques, such as on-the-fly (real-time) augmentation and off-line method (data set expansion method or traditional method). A performance comparison between these methods is also performed. 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
- Source
- Smart Innovation, Systems and Technologies, Vol-196, pp. 515-522.
- Date
- 2021-01-01
- Publisher
- Springer Science and Business Media Deutschland GmbH
- Subject
- Convolutional neural network; Data augmentation techniques; Handwritten character recognition; MODI script
- Coverage
- Joseph S., CHRIST (Deemed to be University), Bangalore, India, Carmel College of Arts, Science and Commerce for Women, Goa, India; George J., CHRIST (Deemed to be University), Bangalore, India
- Rights
- Restricted Access
- Relation
- ISSN: 21903018; ISBN: 978-981157061-2
- Format
- Online
- Language
- English
- Type
- Conference paper
Collection
Citation
Joseph S.; George J., “Data Augmentation for Handwritten Character Recognition of MODI Script Using Deep Learning Method,” CHRIST (Deemed To Be University) Institutional Repository, accessed February 27, 2025, https://archives.christuniversity.in/items/show/20641.