An Innovative Intelligent System with Integrated CNN and SVM: Considering Various Crops through Hyperspectral Image Data
Generation of a thematic map is important for scientists and agriculture engineers in analyzing different crops in a given field. Remote sensing data are well-accepted for image classification on a vast area of crop investigation. However, most of the research has currently focused on the classifica...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-04-01
|
Series: | ISPRS International Journal of Geo-Information |
Subjects: | |
Online Access: | https://www.mdpi.com/2220-9964/10/4/242 |
id |
doaj-591eba528a314fa6ab079b3aa162e4a1 |
---|---|
record_format |
Article |
spelling |
doaj-591eba528a314fa6ab079b3aa162e4a12021-04-07T23:05:43ZengMDPI AGISPRS International Journal of Geo-Information2220-99642021-04-011024224210.3390/ijgi10040242An Innovative Intelligent System with Integrated CNN and SVM: Considering Various Crops through Hyperspectral Image DataShiuan Wan0Mei Ling Yeh1Hong Lin Ma2Department of Information Technology, Ling Tung University, Taichung 40851, TaiwanGIS Research Center, Director, Feng Chia University, Taichung 40724, TaiwanGIS Research Center, Feng Chia University, Taichung 40724, TaiwanGeneration of a thematic map is important for scientists and agriculture engineers in analyzing different crops in a given field. Remote sensing data are well-accepted for image classification on a vast area of crop investigation. However, most of the research has currently focused on the classification of pixel-based image data for analysis. The study was carried out to develop a multi-category crop hyperspectral image classification system to identify the major crops in the Chiayi Golden Corridor. The hyperspectral image data from CASI (Compact Airborne Spectrographic Imager) were used as the experimental data in this study. A two-stage classification was designed to display the performance of the image classification. More specifically, the study used a multi-class classification by support vector machine (SVM) + convolutional neural network (CNN) for image classification analysis. SVM is a supervised learning model that analyzes data used for classification. CNN is a class of deep neural networks that is applied to analyzing visual imagery. The image classification comparison was made among four crops (paddy rice, potatoes, cabbages, and peanuts), roads, and structures for classification. In the first stage, the support vector machine handled the hyperspectral image classification through pixel-based analysis. Then, the convolution neural network improved the classification of image details through various blocks (cells) of segmentation in the second stage. A series of discussion and analyses of the results are presented. The repair module was also designed to link the usage of CNN and SVM to remove the classification errors.https://www.mdpi.com/2220-9964/10/4/242image classificationsupport vector machineconvolution neural network |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Shiuan Wan Mei Ling Yeh Hong Lin Ma |
spellingShingle |
Shiuan Wan Mei Ling Yeh Hong Lin Ma An Innovative Intelligent System with Integrated CNN and SVM: Considering Various Crops through Hyperspectral Image Data ISPRS International Journal of Geo-Information image classification support vector machine convolution neural network |
author_facet |
Shiuan Wan Mei Ling Yeh Hong Lin Ma |
author_sort |
Shiuan Wan |
title |
An Innovative Intelligent System with Integrated CNN and SVM: Considering Various Crops through Hyperspectral Image Data |
title_short |
An Innovative Intelligent System with Integrated CNN and SVM: Considering Various Crops through Hyperspectral Image Data |
title_full |
An Innovative Intelligent System with Integrated CNN and SVM: Considering Various Crops through Hyperspectral Image Data |
title_fullStr |
An Innovative Intelligent System with Integrated CNN and SVM: Considering Various Crops through Hyperspectral Image Data |
title_full_unstemmed |
An Innovative Intelligent System with Integrated CNN and SVM: Considering Various Crops through Hyperspectral Image Data |
title_sort |
innovative intelligent system with integrated cnn and svm: considering various crops through hyperspectral image data |
publisher |
MDPI AG |
series |
ISPRS International Journal of Geo-Information |
issn |
2220-9964 |
publishDate |
2021-04-01 |
description |
Generation of a thematic map is important for scientists and agriculture engineers in analyzing different crops in a given field. Remote sensing data are well-accepted for image classification on a vast area of crop investigation. However, most of the research has currently focused on the classification of pixel-based image data for analysis. The study was carried out to develop a multi-category crop hyperspectral image classification system to identify the major crops in the Chiayi Golden Corridor. The hyperspectral image data from CASI (Compact Airborne Spectrographic Imager) were used as the experimental data in this study. A two-stage classification was designed to display the performance of the image classification. More specifically, the study used a multi-class classification by support vector machine (SVM) + convolutional neural network (CNN) for image classification analysis. SVM is a supervised learning model that analyzes data used for classification. CNN is a class of deep neural networks that is applied to analyzing visual imagery. The image classification comparison was made among four crops (paddy rice, potatoes, cabbages, and peanuts), roads, and structures for classification. In the first stage, the support vector machine handled the hyperspectral image classification through pixel-based analysis. Then, the convolution neural network improved the classification of image details through various blocks (cells) of segmentation in the second stage. A series of discussion and analyses of the results are presented. The repair module was also designed to link the usage of CNN and SVM to remove the classification errors. |
topic |
image classification support vector machine convolution neural network |
url |
https://www.mdpi.com/2220-9964/10/4/242 |
work_keys_str_mv |
AT shiuanwan aninnovativeintelligentsystemwithintegratedcnnandsvmconsideringvariouscropsthroughhyperspectralimagedata AT meilingyeh aninnovativeintelligentsystemwithintegratedcnnandsvmconsideringvariouscropsthroughhyperspectralimagedata AT honglinma aninnovativeintelligentsystemwithintegratedcnnandsvmconsideringvariouscropsthroughhyperspectralimagedata AT shiuanwan innovativeintelligentsystemwithintegratedcnnandsvmconsideringvariouscropsthroughhyperspectralimagedata AT meilingyeh innovativeintelligentsystemwithintegratedcnnandsvmconsideringvariouscropsthroughhyperspectralimagedata AT honglinma innovativeintelligentsystemwithintegratedcnnandsvmconsideringvariouscropsthroughhyperspectralimagedata |
_version_ |
1721535502791737344 |