ResMorCNN Model: Hyperspectral Images Classification Using Residual-Injection Morphological Features and 3DCNN Layers
Hyperspectral imagery is widely used for analyzing substances and objects, specifically focusing on their classification. The advancement of processing capabilities and the emergence of cloud computing platforms have made deep learning (DL) models increasingly popular for accurately and efficiently...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10301532/ |
| _version_ | 1797448883144491008 |
|---|---|
| author | Mohammad Esmaeili Dariush Abbasi-Moghadam Alireza Sharifi Aqil Tariq Qingting Li |
| author_facet | Mohammad Esmaeili Dariush Abbasi-Moghadam Alireza Sharifi Aqil Tariq Qingting Li |
| author_sort | Mohammad Esmaeili |
| collection | DOAJ |
| description | Hyperspectral imagery is widely used for analyzing substances and objects, specifically focusing on their classification. The advancement of processing capabilities and the emergence of cloud computing platforms have made deep learning (DL) models increasingly popular for accurately and efficiently hyperspectral images (HSI) classification. In addition, utilizing image-processing techniques that employ specific mathematical operations for feature extraction and noise reduction further improves the precision of HSI classification. This study introduces the ResMorCNN model, which utilizes 3-D convolutional layers and morphology mathematics to extract structural information, shapes, and interregional interactions from HSIs. These features are then incorporated into the model's layers using residual connections. This approach significantly enhances the classification accuracy of datasets with different characteristics. In fact, the proposed model achieves an average accuracy higher than the top-performing DL method in a competition. To evaluate the overall effectiveness of the proposed method, it was tested on four distinct and comprehensive datasets, Indian Pines, Pavia University, Houston University, and Salinas. These datasets were carefully selected, taking into account factors such as scale, dispersion, and sample size. The overall accuracy results obtained for each evaluated dataset were 97.81%, 99.33%, 98.67%, and 99.71%, respectively. This demonstrates an average improvement of 3.37% compared to the results of the best-performing method. The results demonstrate the effectiveness of the proposed ResMorCNN model for various applications that require accurate and efficient classification of HSI. |
| first_indexed | 2024-03-09T14:16:52Z |
| format | Article |
| id | doaj.art-8c97ad2a060241b792acd3e7e43feafe |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-03-09T14:16:52Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-8c97ad2a060241b792acd3e7e43feafe2023-11-29T00:00:54ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352024-01-011721924310.1109/JSTARS.2023.332838910301532ResMorCNN Model: Hyperspectral Images Classification Using Residual-Injection Morphological Features and 3DCNN LayersMohammad Esmaeili0https://orcid.org/0000-0003-3026-6910Dariush Abbasi-Moghadam1https://orcid.org/0000-0003-2228-0595Alireza Sharifi2https://orcid.org/0000-0001-7110-7516Aqil Tariq3https://orcid.org/0000-0003-1196-1248Qingting Li4https://orcid.org/0000-0002-6322-8307Electrical Engineering Department, Shahid Bahonar University of Kerman, Kerman, IranElectrical Engineering Department, Shahid Bahonar University of Kerman, Kerman, IranDepartment of Surveying Engineering, Faculty of Civil Engineering, Shahid Rajaee Teacher Training University, Tehran, IranDepartment of Wildlife, Fisheries and Aquaculture, College of Forest Resources, Mississippi State University, Mississippi State, MS, USAAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaHyperspectral imagery is widely used for analyzing substances and objects, specifically focusing on their classification. The advancement of processing capabilities and the emergence of cloud computing platforms have made deep learning (DL) models increasingly popular for accurately and efficiently hyperspectral images (HSI) classification. In addition, utilizing image-processing techniques that employ specific mathematical operations for feature extraction and noise reduction further improves the precision of HSI classification. This study introduces the ResMorCNN model, which utilizes 3-D convolutional layers and morphology mathematics to extract structural information, shapes, and interregional interactions from HSIs. These features are then incorporated into the model's layers using residual connections. This approach significantly enhances the classification accuracy of datasets with different characteristics. In fact, the proposed model achieves an average accuracy higher than the top-performing DL method in a competition. To evaluate the overall effectiveness of the proposed method, it was tested on four distinct and comprehensive datasets, Indian Pines, Pavia University, Houston University, and Salinas. These datasets were carefully selected, taking into account factors such as scale, dispersion, and sample size. The overall accuracy results obtained for each evaluated dataset were 97.81%, 99.33%, 98.67%, and 99.71%, respectively. This demonstrates an average improvement of 3.37% compared to the results of the best-performing method. The results demonstrate the effectiveness of the proposed ResMorCNN model for various applications that require accurate and efficient classification of HSI.https://ieeexplore.ieee.org/document/10301532/3-D convolution neural network (3DCNN)deep learning (DL)hyperspectral image (HSI)image classificationresidual connectionspatial-spectral morphological features (SSMF) |
| spellingShingle | Mohammad Esmaeili Dariush Abbasi-Moghadam Alireza Sharifi Aqil Tariq Qingting Li ResMorCNN Model: Hyperspectral Images Classification Using Residual-Injection Morphological Features and 3DCNN Layers IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 3-D convolution neural network (3DCNN) deep learning (DL) hyperspectral image (HSI) image classification residual connection spatial-spectral morphological features (SSMF) |
| title | ResMorCNN Model: Hyperspectral Images Classification Using Residual-Injection Morphological Features and 3DCNN Layers |
| title_full | ResMorCNN Model: Hyperspectral Images Classification Using Residual-Injection Morphological Features and 3DCNN Layers |
| title_fullStr | ResMorCNN Model: Hyperspectral Images Classification Using Residual-Injection Morphological Features and 3DCNN Layers |
| title_full_unstemmed | ResMorCNN Model: Hyperspectral Images Classification Using Residual-Injection Morphological Features and 3DCNN Layers |
| title_short | ResMorCNN Model: Hyperspectral Images Classification Using Residual-Injection Morphological Features and 3DCNN Layers |
| title_sort | resmorcnn model hyperspectral images classification using residual injection morphological features and 3dcnn layers |
| topic | 3-D convolution neural network (3DCNN) deep learning (DL) hyperspectral image (HSI) image classification residual connection spatial-spectral morphological features (SSMF) |
| url | https://ieeexplore.ieee.org/document/10301532/ |
| work_keys_str_mv | AT mohammadesmaeili resmorcnnmodelhyperspectralimagesclassificationusingresidualinjectionmorphologicalfeaturesand3dcnnlayers AT dariushabbasimoghadam resmorcnnmodelhyperspectralimagesclassificationusingresidualinjectionmorphologicalfeaturesand3dcnnlayers AT alirezasharifi resmorcnnmodelhyperspectralimagesclassificationusingresidualinjectionmorphologicalfeaturesand3dcnnlayers AT aqiltariq resmorcnnmodelhyperspectralimagesclassificationusingresidualinjectionmorphologicalfeaturesand3dcnnlayers AT qingtingli resmorcnnmodelhyperspectralimagesclassificationusingresidualinjectionmorphologicalfeaturesand3dcnnlayers |