Varied Image Data Augmentation Methods for Building Ensemble
Convolutional Neural Networks (CNNs) are used in many domains but the requirement of large datasets for robust training sessions and no overfitting makes them hard to apply in medical fields and similar fields. However, when large quantities of samples cannot be easily collected, various methods can...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10025727/ |
| _version_ | 1797783596745883648 |
|---|---|
| author | Riccardo Bravin Loris Nanni Andrea Loreggia Sheryl Brahnam Michelangelo Paci |
| author_facet | Riccardo Bravin Loris Nanni Andrea Loreggia Sheryl Brahnam Michelangelo Paci |
| author_sort | Riccardo Bravin |
| collection | DOAJ |
| description | Convolutional Neural Networks (CNNs) are used in many domains but the requirement of large datasets for robust training sessions and no overfitting makes them hard to apply in medical fields and similar fields. However, when large quantities of samples cannot be easily collected, various methods can still be applied to stem the problem depending on the sample type. Data augmentation, rather than other methods, has recently been under the spotlight mostly because of the simplicity and effectiveness of some of the more adopted methods. The research question addressed in this work is whether data augmentation techniques can help in developing robust and efficient machine learning systems to be used in different domains for classification purposes. To do that, we introduce new image augmentation techniques that make use of different methods like Fourier Transform (FT), Discrete Cosine Transform (DCT), Radon Transform (RT), Hilbert Transform (HT), Singular Value Decomposition (SVD), Local Laplacian Filters (LLF) and Hampel filter (HF). We define different ensemble methods by combining various classical data augmentation methods with the newer ones presented here. We performed an extensive empirical evaluation on 15 different datasets to validate our proposal. The obtained results show that the newly proposed data augmentation methods can be very effective even when used alone. The ensembles trained with different augmentations methods can outperform some of the best approaches reported in the literature as well as compete with state-of-the-art custom methods. All resources are available at <uri>https://github.com/LorisNanni</uri>. |
| first_indexed | 2024-03-13T00:28:08Z |
| format | Article |
| id | doaj.art-799f4d53fb7f4ff4b56857e98431a6a0 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-13T00:28:08Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-799f4d53fb7f4ff4b56857e98431a6a02023-07-10T23:00:43ZengIEEEIEEE Access2169-35362023-01-01118810882310.1109/ACCESS.2023.323981610025727Varied Image Data Augmentation Methods for Building EnsembleRiccardo Bravin0https://orcid.org/0000-0002-5453-1988Loris Nanni1https://orcid.org/0000-0002-3502-7209Andrea Loreggia2https://orcid.org/0000-0002-9846-0157Sheryl Brahnam3https://orcid.org/0000-0001-7664-6930Michelangelo Paci4https://orcid.org/0000-0003-0510-1444Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, ItalyDepartment of Information Engineering (DEI), University of Padua, Padua, ItalyDepartment of Information Engineering (DII), University of Brescia, Brescia, ItalyInformation Technology and Cybersecurity, Missouri State University, Springfield, MO, USABioMediTech, Faculty of Medicine and Health Technology, Tampere University, Tampere, FinlandConvolutional Neural Networks (CNNs) are used in many domains but the requirement of large datasets for robust training sessions and no overfitting makes them hard to apply in medical fields and similar fields. However, when large quantities of samples cannot be easily collected, various methods can still be applied to stem the problem depending on the sample type. Data augmentation, rather than other methods, has recently been under the spotlight mostly because of the simplicity and effectiveness of some of the more adopted methods. The research question addressed in this work is whether data augmentation techniques can help in developing robust and efficient machine learning systems to be used in different domains for classification purposes. To do that, we introduce new image augmentation techniques that make use of different methods like Fourier Transform (FT), Discrete Cosine Transform (DCT), Radon Transform (RT), Hilbert Transform (HT), Singular Value Decomposition (SVD), Local Laplacian Filters (LLF) and Hampel filter (HF). We define different ensemble methods by combining various classical data augmentation methods with the newer ones presented here. We performed an extensive empirical evaluation on 15 different datasets to validate our proposal. The obtained results show that the newly proposed data augmentation methods can be very effective even when used alone. The ensembles trained with different augmentations methods can outperform some of the best approaches reported in the literature as well as compete with state-of-the-art custom methods. All resources are available at <uri>https://github.com/LorisNanni</uri>.https://ieeexplore.ieee.org/document/10025727/Convolutional neural networksdata augmentationensemble |
| spellingShingle | Riccardo Bravin Loris Nanni Andrea Loreggia Sheryl Brahnam Michelangelo Paci Varied Image Data Augmentation Methods for Building Ensemble IEEE Access Convolutional neural networks data augmentation ensemble |
| title | Varied Image Data Augmentation Methods for Building Ensemble |
| title_full | Varied Image Data Augmentation Methods for Building Ensemble |
| title_fullStr | Varied Image Data Augmentation Methods for Building Ensemble |
| title_full_unstemmed | Varied Image Data Augmentation Methods for Building Ensemble |
| title_short | Varied Image Data Augmentation Methods for Building Ensemble |
| title_sort | varied image data augmentation methods for building ensemble |
| topic | Convolutional neural networks data augmentation ensemble |
| url | https://ieeexplore.ieee.org/document/10025727/ |
| work_keys_str_mv | AT riccardobravin variedimagedataaugmentationmethodsforbuildingensemble AT lorisnanni variedimagedataaugmentationmethodsforbuildingensemble AT andrealoreggia variedimagedataaugmentationmethodsforbuildingensemble AT sherylbrahnam variedimagedataaugmentationmethodsforbuildingensemble AT michelangelopaci variedimagedataaugmentationmethodsforbuildingensemble |