Deep Learning-Based Dzongkha Handwritten Digit Classification
In computer vision applications, pattern recognition is one of the important fields in artificial intelligence. With the advancement in deep learning technology, many machine learning algorithms were developed to tackle the problem of pattern recognition. The purpose of conducting the research is t...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Andalas University
2024-03-01
|
| Series: | JITCE (Journal of Information Technology and Computer Engineering) |
| Subjects: | |
| Online Access: | http://10.250.30.20/index.php/JITCE/article/view/202 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823864568673206272 |
|---|---|
| author | Yonten Jamtsho Pema Yangden Sonam Wangmo Nima Dema |
| author_facet | Yonten Jamtsho Pema Yangden Sonam Wangmo Nima Dema |
| author_sort | Yonten Jamtsho |
| collection | DOAJ |
| description |
In computer vision applications, pattern recognition is one of the important fields in artificial intelligence. With the advancement in deep learning technology, many machine learning algorithms were developed to tackle the problem of pattern recognition. The purpose of conducting the research is to create the first-ever Dzongkha handwritten digit dataset and develop a model to classify the digit. In the study, the 3 layer set of CONV → ReLU → POOL, followed by a fully connected layer, dropout layer, and softmax function were used to train the digit. In the dataset, each class (0-9) contains 1500 images which are split into train, validation, and test sets: 70:20:10. The model was trained on three different image dimensions: 28 by 28, 32 by 32, and 64 by 64. Compared to image dimensions 28 by 28 and 32 by 32, 64 by 64 gave the highest train, validation, and test accuracy of 98.66%, 98.9%, and 99.13% respectively. In the future, the sample of digits needs to be increased and use the transfer learning concept to train the model.
|
| format | Article |
| id | doaj-art-8329c5e5cd9441b9a742be856675df8e |
| institution | Kabale University |
| issn | 2599-1663 |
| language | English |
| publishDate | 2024-03-01 |
| publisher | Andalas University |
| record_format | Article |
| series | JITCE (Journal of Information Technology and Computer Engineering) |
| spelling | doaj-art-8329c5e5cd9441b9a742be856675df8e2025-02-08T21:25:59ZengAndalas UniversityJITCE (Journal of Information Technology and Computer Engineering)2599-16632024-03-018110.25077/jitce.8.1.1-7.2024Deep Learning-Based Dzongkha Handwritten Digit ClassificationYonten Jamtsho0Pema Yangden1Sonam Wangmo2Nima Dema3Gyalpozhing College of Information TechnologyGyalpozhing College of Information TechnologyGyalpozhing College of Information TechnologyGyalpozhing College of Information Technology In computer vision applications, pattern recognition is one of the important fields in artificial intelligence. With the advancement in deep learning technology, many machine learning algorithms were developed to tackle the problem of pattern recognition. The purpose of conducting the research is to create the first-ever Dzongkha handwritten digit dataset and develop a model to classify the digit. In the study, the 3 layer set of CONV → ReLU → POOL, followed by a fully connected layer, dropout layer, and softmax function were used to train the digit. In the dataset, each class (0-9) contains 1500 images which are split into train, validation, and test sets: 70:20:10. The model was trained on three different image dimensions: 28 by 28, 32 by 32, and 64 by 64. Compared to image dimensions 28 by 28 and 32 by 32, 64 by 64 gave the highest train, validation, and test accuracy of 98.66%, 98.9%, and 99.13% respectively. In the future, the sample of digits needs to be increased and use the transfer learning concept to train the model. http://10.250.30.20/index.php/JITCE/article/view/202BhutanDzongkha digitsDeep learningCNNPattern Recognition |
| spellingShingle | Yonten Jamtsho Pema Yangden Sonam Wangmo Nima Dema Deep Learning-Based Dzongkha Handwritten Digit Classification JITCE (Journal of Information Technology and Computer Engineering) Bhutan Dzongkha digits Deep learning CNN Pattern Recognition |
| title | Deep Learning-Based Dzongkha Handwritten Digit Classification |
| title_full | Deep Learning-Based Dzongkha Handwritten Digit Classification |
| title_fullStr | Deep Learning-Based Dzongkha Handwritten Digit Classification |
| title_full_unstemmed | Deep Learning-Based Dzongkha Handwritten Digit Classification |
| title_short | Deep Learning-Based Dzongkha Handwritten Digit Classification |
| title_sort | deep learning based dzongkha handwritten digit classification |
| topic | Bhutan Dzongkha digits Deep learning CNN Pattern Recognition |
| url | http://10.250.30.20/index.php/JITCE/article/view/202 |
| work_keys_str_mv | AT yontenjamtsho deeplearningbaseddzongkhahandwrittendigitclassification AT pemayangden deeplearningbaseddzongkhahandwrittendigitclassification AT sonamwangmo deeplearningbaseddzongkhahandwrittendigitclassification AT nimadema deeplearningbaseddzongkhahandwrittendigitclassification |