Hyperspectral Image Classification Using Deep Genome Graph-Based Approach
Recently developed hybrid models that stack 3D with 2D CNN in their structure have enjoyed high popularity due to their appealing performance in hyperspectral image classification tasks. On the other hand, biological genome graphs have demonstrated their effectiveness in enhancing the scalability an...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/19/6467 |
| _version_ | 1797515765623029760 |
|---|---|
| author | Haron Tinega Enqing Chen Long Ma Richard M. Mariita Divinah Nyasaka |
| author_facet | Haron Tinega Enqing Chen Long Ma Richard M. Mariita Divinah Nyasaka |
| author_sort | Haron Tinega |
| collection | DOAJ |
| description | Recently developed hybrid models that stack 3D with 2D CNN in their structure have enjoyed high popularity due to their appealing performance in hyperspectral image classification tasks. On the other hand, biological genome graphs have demonstrated their effectiveness in enhancing the scalability and accuracy of genomic analysis. We propose an innovative deep genome graph-based network (GGBN) for hyperspectral image classification to tap the potential of hybrid models and genome graphs. The GGBN model utilizes 3D-CNN at the bottom layers and 2D-CNNs at the top layers to process spectral–spatial features vital to enhancing the scalability and accuracy of hyperspectral image classification. To verify the effectiveness of the GGBN model, we conducted classification experiments on Indian Pines (IP), University of Pavia (UP), and Salinas Scene (SA) datasets. Using only 5% of the labeled data for training over the SA, IP, and UP datasets, the classification accuracy of GGBN is 99.97%, 96.85%, and 99.74%, respectively, which is better than the compared state-of-the-art methods. |
| first_indexed | 2024-03-10T06:51:55Z |
| format | Article |
| id | doaj.art-3413057c0e21469ca8d9e630867a949c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T06:51:55Z |
| publishDate | 2021-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-3413057c0e21469ca8d9e630867a949c2023-11-22T16:46:33ZengMDPI AGSensors1424-82202021-09-012119646710.3390/s21196467Hyperspectral Image Classification Using Deep Genome Graph-Based ApproachHaron Tinega0Enqing Chen1Long Ma2Richard M. Mariita3Divinah Nyasaka4School of Information Engineering, Zhengzhou University, No. 100 Science Avenue, Zhengzhou 450001, ChinaSchool of Information Engineering, Zhengzhou University, No. 100 Science Avenue, Zhengzhou 450001, ChinaSchool of Information Engineering, Zhengzhou University, No. 100 Science Avenue, Zhengzhou 450001, ChinaMicrobial BioSolutions, 33 Greene Street, Troy, NY 12180, USAThe Kenya Forest Service, Nairobi P.O. Box 30513-00100, KenyaRecently developed hybrid models that stack 3D with 2D CNN in their structure have enjoyed high popularity due to their appealing performance in hyperspectral image classification tasks. On the other hand, biological genome graphs have demonstrated their effectiveness in enhancing the scalability and accuracy of genomic analysis. We propose an innovative deep genome graph-based network (GGBN) for hyperspectral image classification to tap the potential of hybrid models and genome graphs. The GGBN model utilizes 3D-CNN at the bottom layers and 2D-CNNs at the top layers to process spectral–spatial features vital to enhancing the scalability and accuracy of hyperspectral image classification. To verify the effectiveness of the GGBN model, we conducted classification experiments on Indian Pines (IP), University of Pavia (UP), and Salinas Scene (SA) datasets. Using only 5% of the labeled data for training over the SA, IP, and UP datasets, the classification accuracy of GGBN is 99.97%, 96.85%, and 99.74%, respectively, which is better than the compared state-of-the-art methods.https://www.mdpi.com/1424-8220/21/19/6467convolutional neural networkshyperspectral imageshyperspectral image classificationspectral–spatial featureshybrid convolution networksgenome graphs |
| spellingShingle | Haron Tinega Enqing Chen Long Ma Richard M. Mariita Divinah Nyasaka Hyperspectral Image Classification Using Deep Genome Graph-Based Approach Sensors convolutional neural networks hyperspectral images hyperspectral image classification spectral–spatial features hybrid convolution networks genome graphs |
| title | Hyperspectral Image Classification Using Deep Genome Graph-Based Approach |
| title_full | Hyperspectral Image Classification Using Deep Genome Graph-Based Approach |
| title_fullStr | Hyperspectral Image Classification Using Deep Genome Graph-Based Approach |
| title_full_unstemmed | Hyperspectral Image Classification Using Deep Genome Graph-Based Approach |
| title_short | Hyperspectral Image Classification Using Deep Genome Graph-Based Approach |
| title_sort | hyperspectral image classification using deep genome graph based approach |
| topic | convolutional neural networks hyperspectral images hyperspectral image classification spectral–spatial features hybrid convolution networks genome graphs |
| url | https://www.mdpi.com/1424-8220/21/19/6467 |
| work_keys_str_mv | AT harontinega hyperspectralimageclassificationusingdeepgenomegraphbasedapproach AT enqingchen hyperspectralimageclassificationusingdeepgenomegraphbasedapproach AT longma hyperspectralimageclassificationusingdeepgenomegraphbasedapproach AT richardmmariita hyperspectralimageclassificationusingdeepgenomegraphbasedapproach AT divinahnyasaka hyperspectralimageclassificationusingdeepgenomegraphbasedapproach |