International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 10 Issue: 04 | Apr 2023
p-ISSN: 2395-0072
www.irjet.net
Survey On Broken and Joint Devanagari Handwritten Characters Recognition Using Deep Learning Prachi Pachang1, Jiya Shaikh2, Ms. Vina M. Lomate3, Tanishka Sinha4, Manjeet Kour5 3Hod Dept. of Computer Engineering, RMD Sinhgad School of Engineering, Warje Pune, India
1,2,4,5UG Student, Computer Engineering, RMD Sinhgad School of Engineering, Warje Pune, India
---------------------------------------------------------------------***--------------------------------------------------------------------complexity, as these characters are often written Abstract - The recognition of handwritten Devanagari differently by different individuals, making it difficult characters presents a significant challenge due to the to develop a robust recognition system. script's complexity and variability. The complexity is further compounded by the variability of broken and This survey paper aims to provide a comprehensive joint characters that are written differently by different overview of the existing approaches for broken and individuals. In recent years, deep learning models have joint handwritten Devanagari character recognition, emerged as a powerful solution for character with a particular focus on the involvement of wavelet recognition, achieving remarkable performance in transform and recent deep learning-based various applications. This survey paper presents an intechnologies. The paper will also discuss the depth analysis of the deep learning-based approaches advantages and limitations of each approach and used for recognizing handwritten Devanagari broken highlight the current techniques. Additionally, publicly and joint characters. We extensively review the available datasets such as the Devanagari Handwritten architectures and techniques applied in deep learning Character Dataset (DHCD) and Indian Language models such as convolutional neural networks (CNNs), Handwritten Character Dataset (ILHCD) will be recurrent neural networks (RNNs), and hybrid models, to reviewed, which have been widely used for training identify these characters. We also discuss the datasets and evaluation of various approaches. This survey utilized for training and testing these models and the paper will provide a useful resource for researchers performance metrics used for evaluating their and practitioners working in the field of handwritten performance. Additionally, we conduct a comparative Devanagari character recognition, with the aim of analysis of the different approaches, highlighting their improving the accuracy and efficiency of character respective strengths, and limitations, and proposing recognition systems. possible directions for future research. Our survey is intended to serve as a valuable resource for researchers 2. Main Terminologies: and practitioners engaged in the area of handwritten Devanagari character recognition using deep learning. 2.1 Devanagari script: A script used for
writing several languages, including Hindi, Marathi, and Nepali.
Feature extraction, Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), TensorFlow, ImageDataGenerator, Text recognition, Wavelets. Key Words:
2.2 Broken characters: Devanagari characters that are separated or disjointed, which require additional techniques for recognition.
1. INTRODUCTION
2.3 Joint characters: Devanagari characters that are connected to other characters, often written in a cursive manner, require additional techniques for recognition.
Handwritten character recognition is vital in computer vision and pattern recognition, with practical applications such as optical character recognition, automatic form processing, and intelligent handwriting recognition systems. Devanagari is a prominent script used in several languages such as Hindi, Marathi, and Nepali, and recognizing handwritten Devanagari characters is a challenging task due to the complexity and variability of the script. The recognition of broken and joint characters in Devanagari further adds to the © 2023, IRJET
|
Impact Factor value: 8.226
2.4 Handwritten character recognition: The process of identifying and transcribing handwritten characters from an image or document. 2.5 Devanagari Handwritten Character Dataset (DHCD): A publicly available dataset containing handwritten Devanagari characters. |
ISO 9001:2008 Certified Journal
|
Page 1767