Bangla-Meitei Mayek scripts handwritten character recognition using Convolutional Neural Network
- PDF / 11,495,703 Bytes
- 21 Pages / 595.224 x 790.955 pts Page_size
- 54 Downloads / 277 Views
Bangla-Meitei Mayek scripts handwritten character recognition using Convolutional Neural Network Abhishek Hazra1
· Prakash Choudhary2 · Sanasam Inunganbi3 · Mainak Adhikari4
© Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Recognition of handwritten characters in two Indic scripts Bangla and Meitei Mayek is one of the challenging responsibilities due to intricate patterns and scarcity of standard datasets. Convolutional Neural Network (CNN) is one of the stablest well-known techniques for classifying objects in distinctive specialties as it has an extraordinary capability of discovering complex patterns. In this paper, we hook a different layout and obtain a unique CNN architecture from scratch, which has manifold advantages over classical machine learning (ML) approaches, and it has a unique ability to consolidate feature extraction and classification altogether. Further, we stretch our work to uncover the mathematical rationale for using non-linearity in the deep learning (DL) model. Our proposed CNN architecture consists of four layers, including convolutional layer (CL), nonlinear activation layer (AL), pooling layer (PL), and fully connected layer (FCL), which are used in the existing two accessible Bangla datasets named cMATERdb and ISI Bangla datasets. The identical model also validates on proposed Manipuri Character dataset, called “Mayek27”. Moreover, we perform an in-depth comparison with different batch sizes and optimization techniques over all the datasets for understanding their functionality. We conceive a novel benchmark performance that has delivered state-of-the-art decisions on two regional handwritten character identifications. Keywords Convolutional neural network · Classification · Handwritten character recognition · “Mayek27”
Abhishek Hazra
1 Introduction
[email protected] Prakash Choudhary [email protected] Sanasam Inunganbi [email protected] Mainak Adhikari [email protected] 1
Department of Computer Science and Engineering, Indian Institute of Technology (Indian School of Mines), Dhanbad, Jharkhand, 826004, India
2
Department of Computer Science and Engineering, National Institute of Technology Hamirpur, Hamirpur, 177005, India
3
Department of Computer Science and Engineering, National Institute of Technology, Manipur, 795004, India
4
Mobile & Cloud Lab, Institute of Computer Science, Faculty of Science and Technology, University of Tartu, Tartu 50090, Estonia
Automated handwriting character identification has gained lots of theoretical and industrial interests [1]. The recent algorithms now excel in learning to acknowledge handwritten characters. The utmost challenge in handwritten character identification is the classification of proper leveling with the cosmic collection of handwriting methodologies by various writers in different languages [2]. Furthermore, some of the complex handwriting scripts comprised various styles of writing words. Depending on languages, characters are confined to an individual in some facts (e.
Data Loading...
