Stochastic Neighbor Embedding Feature-Based Hyperspectral Image Classification Using 3D Convolutional Neural Network
The ample amount of information from hyperspectral image (HSI) bands allows the non-destructive detection and recognition of earth objects. However, dimensionality reduction (DR) of hyperspectral images (HSI) is required before classification as the classifier may suffer from the curse of dimensiona...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/9/2082 |
| _version_ | 1797602771864649728 |
|---|---|
| author | Md. Moazzem Hossain Md. Ali Hossain Abu Saleh Musa Miah Yuichi Okuyama Yoichi Tomioka Jungpil Shin |
| author_facet | Md. Moazzem Hossain Md. Ali Hossain Abu Saleh Musa Miah Yuichi Okuyama Yoichi Tomioka Jungpil Shin |
| author_sort | Md. Moazzem Hossain |
| collection | DOAJ |
| description | The ample amount of information from hyperspectral image (HSI) bands allows the non-destructive detection and recognition of earth objects. However, dimensionality reduction (DR) of hyperspectral images (HSI) is required before classification as the classifier may suffer from the curse of dimensionality. Therefore, dimensionality reduction plays a significant role in HSI data analysis (e.g., effective processing and seamless interpretation). In this article, a sophisticated technique established as t-Distributed Stochastic Neighbor Embedding (tSNE) following the dimension reduction along with a blended CNN was implemented to improve the visualization and characterization of HSI. In the procedure, first, we employed principal component analysis (PCA) to reduce the HSI dimensions and remove non-linear consistency features between the wavelengths to project them to a smaller scale. Then we proposed tSNE to preserve the local and global pixel relationships and check the HSI information visually and experimentally. Lastly, it yielded two-dimensional data, improving the visualization and classification accuracy compared to other standard dimensionality-reduction algorithms. Finally, we employed deep-learning-based CNN to classify the reduced and improved HSI intra- and inter-band relationship-feature vector. The evaluation performance of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>95.21</mn><mo>%</mo></mrow></semantics></math></inline-formula> accuracy and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>6.2</mn><mo>%</mo></mrow></semantics></math></inline-formula> test loss proved the superiority of the proposed model compared to other state-of-the-art DR reduction algorithms. |
| first_indexed | 2024-03-11T04:21:20Z |
| format | Article |
| id | doaj.art-9f8b616028fa4da68121a73812a45c5a |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T04:21:20Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-9f8b616028fa4da68121a73812a45c5a2023-11-17T22:48:26ZengMDPI AGElectronics2079-92922023-05-01129208210.3390/electronics12092082Stochastic Neighbor Embedding Feature-Based Hyperspectral Image Classification Using 3D Convolutional Neural NetworkMd. Moazzem Hossain0Md. Ali Hossain1Abu Saleh Musa Miah2Yuichi Okuyama3Yoichi Tomioka4Jungpil Shin5Department of Computer Science & Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, BangladeshDepartment of Computer Science & Engineering, Rajshahi University of Engineering & Technology, Rajshahi 6204, BangladeshDepartment of Computer Science & Engineering, Bangladesh Army University of Science & Technology, Saidpur 5311, BangladeshSchool of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu 965-8580, JapanSchool of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu 965-8580, JapanSchool of Computer Science and Engineering, The University of Aizu, Aizuwakamatsu 965-8580, JapanThe ample amount of information from hyperspectral image (HSI) bands allows the non-destructive detection and recognition of earth objects. However, dimensionality reduction (DR) of hyperspectral images (HSI) is required before classification as the classifier may suffer from the curse of dimensionality. Therefore, dimensionality reduction plays a significant role in HSI data analysis (e.g., effective processing and seamless interpretation). In this article, a sophisticated technique established as t-Distributed Stochastic Neighbor Embedding (tSNE) following the dimension reduction along with a blended CNN was implemented to improve the visualization and characterization of HSI. In the procedure, first, we employed principal component analysis (PCA) to reduce the HSI dimensions and remove non-linear consistency features between the wavelengths to project them to a smaller scale. Then we proposed tSNE to preserve the local and global pixel relationships and check the HSI information visually and experimentally. Lastly, it yielded two-dimensional data, improving the visualization and classification accuracy compared to other standard dimensionality-reduction algorithms. Finally, we employed deep-learning-based CNN to classify the reduced and improved HSI intra- and inter-band relationship-feature vector. The evaluation performance of <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>95.21</mn><mo>%</mo></mrow></semantics></math></inline-formula> accuracy and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>6.2</mn><mo>%</mo></mrow></semantics></math></inline-formula> test loss proved the superiority of the proposed model compared to other state-of-the-art DR reduction algorithms.https://www.mdpi.com/2079-9292/12/9/2082hyperspectral imagedimensionality reductionvisualizationimage classificationprinciple component analysist-Distributed Stochastic Neighbor Embedding |
| spellingShingle | Md. Moazzem Hossain Md. Ali Hossain Abu Saleh Musa Miah Yuichi Okuyama Yoichi Tomioka Jungpil Shin Stochastic Neighbor Embedding Feature-Based Hyperspectral Image Classification Using 3D Convolutional Neural Network Electronics hyperspectral image dimensionality reduction visualization image classification principle component analysis t-Distributed Stochastic Neighbor Embedding |
| title | Stochastic Neighbor Embedding Feature-Based Hyperspectral Image Classification Using 3D Convolutional Neural Network |
| title_full | Stochastic Neighbor Embedding Feature-Based Hyperspectral Image Classification Using 3D Convolutional Neural Network |
| title_fullStr | Stochastic Neighbor Embedding Feature-Based Hyperspectral Image Classification Using 3D Convolutional Neural Network |
| title_full_unstemmed | Stochastic Neighbor Embedding Feature-Based Hyperspectral Image Classification Using 3D Convolutional Neural Network |
| title_short | Stochastic Neighbor Embedding Feature-Based Hyperspectral Image Classification Using 3D Convolutional Neural Network |
| title_sort | stochastic neighbor embedding feature based hyperspectral image classification using 3d convolutional neural network |
| topic | hyperspectral image dimensionality reduction visualization image classification principle component analysis t-Distributed Stochastic Neighbor Embedding |
| url | https://www.mdpi.com/2079-9292/12/9/2082 |
| work_keys_str_mv | AT mdmoazzemhossain stochasticneighborembeddingfeaturebasedhyperspectralimageclassificationusing3dconvolutionalneuralnetwork AT mdalihossain stochasticneighborembeddingfeaturebasedhyperspectralimageclassificationusing3dconvolutionalneuralnetwork AT abusalehmusamiah stochasticneighborembeddingfeaturebasedhyperspectralimageclassificationusing3dconvolutionalneuralnetwork AT yuichiokuyama stochasticneighborembeddingfeaturebasedhyperspectralimageclassificationusing3dconvolutionalneuralnetwork AT yoichitomioka stochasticneighborembeddingfeaturebasedhyperspectralimageclassificationusing3dconvolutionalneuralnetwork AT jungpilshin stochasticneighborembeddingfeaturebasedhyperspectralimageclassificationusing3dconvolutionalneuralnetwork |