A Comparative Analysis of Machine Learning and Deep Learning Algorithms for Image Classification
Image classification is a popular and important area of image processing research in today's society. For machine learning, SVM is a very good classification model. CNN is a type of convolution neural network that has an unpredictable development and uses convolution calculations. It is one of...
Saved in:
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Published: |
Institute of Electrical and Electronics Engineers Inc.
2024
|
| Subjects: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1833351792322150400 |
|---|---|
| author | Madanan M. Gunasekaran S.S. Mahmoud M.A. |
| author2 | 57203784027 |
| author_facet | 57203784027 Madanan M. Gunasekaran S.S. Mahmoud M.A. |
| author_sort | Madanan M. |
| building | UNITEN Library |
| collection | Institutional Repository |
| content_provider | Universiti Tenaga Nasional |
| content_source | UNITEN Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | Image classification is a popular and important area of image processing research in today's society. For machine learning, SVM is a very good classification model. CNN is a type of convolution neural network that has an unpredictable development and uses convolution calculations. It is one of the most well-known deep learning algorithms. This review thinks about and inspects exemplary AI and profound learning picture classification procedures involving SVM and CNN as specific illustrations. Using a large sample mnist dataset, this study found that CNN has an accuracy of 0.97 and SVM has an accuracy of 0.89 |
| format | Conference Paper |
| id | my.uniten.dspace-34374 |
| institution | Universiti Tenaga Nasional |
| publishDate | 2024 |
| publisher | Institute of Electrical and Electronics Engineers Inc. |
| record_format | dspace |
| spelling | my.uniten.dspace-343742024-10-14T11:19:21Z A Comparative Analysis of Machine Learning and Deep Learning Algorithms for Image Classification Madanan M. Gunasekaran S.S. Mahmoud M.A. 57203784027 55652730500 55247787300 deep learning image classification machine learning Convolution Convolutional neural networks Deep learning Large datasets Learning algorithms Learning systems Support vector machines Classification models Classification procedure Comparative analyzes Convolution neural network Deep learning Images classification Images processing Machine-learning Small samples Standard ML Image classification Image classification is a popular and important area of image processing research in today's society. For machine learning, SVM is a very good classification model. CNN is a type of convolution neural network that has an unpredictable development and uses convolution calculations. It is one of the most well-known deep learning algorithms. This review thinks about and inspects exemplary AI and profound learning picture classification procedures involving SVM and CNN as specific illustrations. Using a large sample mnist dataset, this study found that CNN has an accuracy of 0.97 and SVM has an accuracy of 0.89 SVM has an accuracy of 0.85 and CNN has an accuracy of 0.82 when working with a small sample ImageNet dataset. Tests in this review show that for little example informational collections, standard ML has an improved arrangement impact than deep learning structure does. � 2023 IEEE. Final 2024-10-14T03:19:21Z 2024-10-14T03:19:21Z 2023 Conference Paper 10.1109/IC3I59117.2023.10398030 2-s2.0-85187300318 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85187300318&doi=10.1109%2fIC3I59117.2023.10398030&partnerID=40&md5=db61abffb0c90ade269079af699993f1 https://irepository.uniten.edu.my/handle/123456789/34374 2436 2439 Institute of Electrical and Electronics Engineers Inc. Scopus |
| spellingShingle | deep learning image classification machine learning Convolution Convolutional neural networks Deep learning Large datasets Learning algorithms Learning systems Support vector machines Classification models Classification procedure Comparative analyzes Convolution neural network Deep learning Images classification Images processing Machine-learning Small samples Standard ML Image classification Madanan M. Gunasekaran S.S. Mahmoud M.A. A Comparative Analysis of Machine Learning and Deep Learning Algorithms for Image Classification |
| title | A Comparative Analysis of Machine Learning and Deep Learning Algorithms for Image Classification |
| title_full | A Comparative Analysis of Machine Learning and Deep Learning Algorithms for Image Classification |
| title_fullStr | A Comparative Analysis of Machine Learning and Deep Learning Algorithms for Image Classification |
| title_full_unstemmed | A Comparative Analysis of Machine Learning and Deep Learning Algorithms for Image Classification |
| title_short | A Comparative Analysis of Machine Learning and Deep Learning Algorithms for Image Classification |
| title_sort | comparative analysis of machine learning and deep learning algorithms for image classification |
| topic | deep learning image classification machine learning Convolution Convolutional neural networks Deep learning Large datasets Learning algorithms Learning systems Support vector machines Classification models Classification procedure Comparative analyzes Convolution neural network Deep learning Images classification Images processing Machine-learning Small samples Standard ML Image classification |
| url_provider | http://dspace.uniten.edu.my/ |