Recognition of Handwritten Devanagari Character using Convolutional Neural Network

Dokare, Indu; Gadge, Siddhesh; Kharde, Kedar; Bhere, Siddhesh; Jadhav, Rohit B

doi:10.1109/icspc51351.2021.9451716

Cited by 10 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With an accuracy of 93.73%, the CNN algorithm was discovered to perform better than the results suggested by employing Naivs Bayes, SVM, and Decision Tree to recognize old Devanagari manuscripts. The recognition of handwritten Devanagari characters using a convolutional neural network was presented by [24]. They achieved a consonant accuracy of 96.86%, a vowel accuracy of 99%, and a numeric accuracy of 99.29%.…”

Section: Introductionmentioning

confidence: 99%

Ranjana Script Handwritten Character Recognition using CNN

Bati,

Raj Dawadi

2023

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

This paper proposes a public image database for Ranjana script Handwritten Character Datasets (RHCD), publicly available for Ranjana script researchers or anyone interested in the subject. To the best of our knowledge, the Ranjana script Handwritten Character Dataset (RHCD) is the first publicly available database for Ranjana script researchers. Ranjana script descended from the Brahmi script, consists of 36 consonant letters, 16 vowel letters, and 10 numerical letters. The focus of this research is three-fold: the first is to create a new database for Ranjana script Handwritten Character Recognition; the second is to test the character recognition accuracy of the created RHCD using existing CNN algorithms like LeNET-5, AlexNET, and ZFNET algorithm; the third is to propose a model by investigating different hyper-tuning parameters to improve the recognition accuracy of the created RHCD. The research method applied in this study is dataset collection, digitization & cropping, pre-processing, dataset splitting, data augmentation, and finally, implementing the CNN model (existing and proposed). Performance evaluation is based on the test accuracy, precision, recall, and F1-score. The experiment result shows that our model ranks first, with a testing accuracy of 99.73% for 64x64 pixels resolution with precision, recall, and F1-score value 1. Creation and recognition of Ranjana script characters, vowel modifiers, and compound characters can be the next milestone to be achieved. Segmentation of words and sentences into characters and recognizing each character individually can be the next research domain.

show abstract

Section: Introductionmentioning

confidence: 99%

Ranjana Script Handwritten Character Recognition using CNN

Bati,

Raj Dawadi

2023

JOIV : Int. J. Inform. Visualization

View full text Add to dashboard Cite

show abstract

“…Repetition is a vital component of learning how to write a character. Only in this manner can kids automate the right muscle moments [3][4][5][6]. A teacher can hold a student's hand and assist them acquire a new sensorimotor capacity, although this is not recommended in large schools because it takes time.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning and Image Processing for Character Recognition: An Application in Handwriting Instruction

2023

IRJMETS

View full text Add to dashboard Cite

This research paper presents an innovative application of machine learning and image processing techniques for teaching handwriting skills. The proposed system utilizes a convolutional neural network (CNN) to accurately recognize characters written by students and provides valuable feedback on their handwriting. To enhance the input images' quality, an image processing algorithm incorporating edge detection, binarization, and noise reduction is employed. The system's potential applications extend to educational settings, where it can offer personalized feedback on students' handwriting skills, and to individuals seeking to improve their handwriting abilities through systematic practice. Feedback is provided on crucial aspects such as letter formation, size, spacing, and slant, enabling users to address specific areas for improvement. Experimental results demonstrate that the proposed system achieves high recognition accuracy for both uppercase and lowercase letters. Additionally, the system successfully identifies errors in input images, enabling targeted feedback to highlight areas requiring improvement. Leveraging recent technological advances, this research emphasizes the use of tablets as a tool to foster independent learning while respecting the perspectives, knowledge, and preferences of teachers.

show abstract

“…I choose this subject to research. With the aid of a strong and powerful dataset and a combination of different neural network techniques, they can increase the accuracy rate and we can preserve more historical records for our access.Digit Recognition of Handwriting on CNN [15]. A particular type of neural network is the convolutional neural network (CNN).…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-based Recognition of Devanagari Handwritten Characters

Kolhe

2023

IJRITCC

View full text Add to dashboard Cite

Numerous techniques have been used over many years to study handwriting recognition. There are two methods for reading handwriting, one of which is online and the other offline. Image recognition is the main part of the handwriting recognition process. Image recognition gives careful consideration to the picture's dimensions, viewing angle, and image quality. Machine learning and deep learning techniques are the two areas of focus for developers looking to increase the intelligence of computers. A person may learn to perform a task by repeatedly exercising it until they recall how to do it. His brain's neurons begin to work automatically, enabling him to carry out the task he has quickly learned. This and deep learning are fairly similar. It uses a variety of neural network designs to address a range of problems. The convolution neural network (CNN) is a very effective technique for handwriting and picture detection.

show abstract

Recognition of Handwritten Devanagari Character using Convolutional Neural Network

Cited by 10 publications

References 6 publications

Ranjana Script Handwritten Character Recognition using CNN

Ranjana Script Handwritten Character Recognition using CNN

Machine Learning and Image Processing for Character Recognition: An Application in Handwriting Instruction

Deep Learning-based Recognition of Devanagari Handwritten Characters

Contact Info

Product

Resources

About