An Efficient CNN Model for Automated Digital Handwritten Digit Classification
Background: Handwriting recognition becomes an appreciable research area because of its important practical applications, but varieties of writing patterns make automatic classification a challenging task. Classifying handwritten digits with a higher accuracy is needed to improve the limitations fro...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Universitas Airlangga
2021-04-01
|
Series: | Journal of Information Systems Engineering and Business Intelligence |
Online Access: | https://e-journal.unair.ac.id/JISEBI/article/view/24237 |
_version_ | 1811159667008602112 |
---|---|
author | Angona Biswas Md. Saiful Islam |
author_facet | Angona Biswas Md. Saiful Islam |
author_sort | Angona Biswas |
collection | DOAJ |
description | Background: Handwriting recognition becomes an appreciable research area because of its important practical applications, but varieties of writing patterns make automatic classification a challenging task. Classifying handwritten digits with a higher accuracy is needed to improve the limitations from past research, which mostly used deep learning approaches.
Objective: Two most noteworthy limitations are low accuracy and slow computational speed. The current study is to model a Convolutional Neural Network (CNN), which is simple yet more accurate in classifying English handwritten digits for different datasets. Novelty of this paper is to explore an efficient CNN architecture that can classify digits of different datasets accurately.
Methods: The author proposed five different CNN architectures for training and validation tasks with two datasets. Dataset-1 consists of 12,000 MNIST data and Dataset-2 consists of 29,400-digit data of Kaggle. The proposed CNN models extract the features first and then performs the classification tasks. For the performance optimization, the models utilized stochastic gradient descent with momentum optimizer.
Results: Among the five models, one was found to be the best performer, with 99.53% and 98.93% of validation accuracy for Dataset-1 and Dataset-2 respectively. Compared to Adam and RMSProp optimizers, stochastic gradient descent with momentum yielded the highest accuracy.
Conclusion: The proposed best CNN model has the simplest architecture. It provides a higher accuracy for different datasets and takes less computational time. The validation accuracy of the proposed model is also higher than those of in past works. |
first_indexed | 2024-04-10T05:45:03Z |
format | Article |
id | doaj.art-26847b63812f4b43ab8769c042155103 |
institution | Directory Open Access Journal |
issn | 2598-6333 2443-2555 |
language | English |
last_indexed | 2024-04-10T05:45:03Z |
publishDate | 2021-04-01 |
publisher | Universitas Airlangga |
record_format | Article |
series | Journal of Information Systems Engineering and Business Intelligence |
spelling | doaj.art-26847b63812f4b43ab8769c0421551032023-03-06T02:56:32ZengUniversitas AirlanggaJournal of Information Systems Engineering and Business Intelligence2598-63332443-25552021-04-0171425510.20473/jisebi.7.1.42-5519873An Efficient CNN Model for Automated Digital Handwritten Digit ClassificationAngona Biswas0Md. Saiful Islam1Chittagong University of Engineering & TechnologyChittagong University of Engineering & TechnologyBackground: Handwriting recognition becomes an appreciable research area because of its important practical applications, but varieties of writing patterns make automatic classification a challenging task. Classifying handwritten digits with a higher accuracy is needed to improve the limitations from past research, which mostly used deep learning approaches. Objective: Two most noteworthy limitations are low accuracy and slow computational speed. The current study is to model a Convolutional Neural Network (CNN), which is simple yet more accurate in classifying English handwritten digits for different datasets. Novelty of this paper is to explore an efficient CNN architecture that can classify digits of different datasets accurately. Methods: The author proposed five different CNN architectures for training and validation tasks with two datasets. Dataset-1 consists of 12,000 MNIST data and Dataset-2 consists of 29,400-digit data of Kaggle. The proposed CNN models extract the features first and then performs the classification tasks. For the performance optimization, the models utilized stochastic gradient descent with momentum optimizer. Results: Among the five models, one was found to be the best performer, with 99.53% and 98.93% of validation accuracy for Dataset-1 and Dataset-2 respectively. Compared to Adam and RMSProp optimizers, stochastic gradient descent with momentum yielded the highest accuracy. Conclusion: The proposed best CNN model has the simplest architecture. It provides a higher accuracy for different datasets and takes less computational time. The validation accuracy of the proposed model is also higher than those of in past works.https://e-journal.unair.ac.id/JISEBI/article/view/24237 |
spellingShingle | Angona Biswas Md. Saiful Islam An Efficient CNN Model for Automated Digital Handwritten Digit Classification Journal of Information Systems Engineering and Business Intelligence |
title | An Efficient CNN Model for Automated Digital Handwritten Digit Classification |
title_full | An Efficient CNN Model for Automated Digital Handwritten Digit Classification |
title_fullStr | An Efficient CNN Model for Automated Digital Handwritten Digit Classification |
title_full_unstemmed | An Efficient CNN Model for Automated Digital Handwritten Digit Classification |
title_short | An Efficient CNN Model for Automated Digital Handwritten Digit Classification |
title_sort | efficient cnn model for automated digital handwritten digit classification |
url | https://e-journal.unair.ac.id/JISEBI/article/view/24237 |
work_keys_str_mv | AT angonabiswas anefficientcnnmodelforautomateddigitalhandwrittendigitclassification AT mdsaifulislam anefficientcnnmodelforautomateddigitalhandwrittendigitclassification AT angonabiswas efficientcnnmodelforautomateddigitalhandwrittendigitclassification AT mdsaifulislam efficientcnnmodelforautomateddigitalhandwrittendigitclassification |