Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Soft Computing Approaches for Hyperspectral Image Classification


Affiliations
1 Department of Electronics and Communication Engineering, Nitte Meenakshi Institute of Technology, India
     

   Subscribe/Renew Journal


Hyperspectral image classification is one of the most emerging form of image classification. It is able to convey information about an image in a more detailed way as compared to RGB or multispectral data. When spectral measurement is performed using hundreds of narrow contiguous wavelength intervals, the resulting image is called a hyperspectral image. Spectral signature of thousands of materials have been measured in the laboratory and gathered into libraries. Library signatures are used as the basis for identification of materials in Hyperspectral Image (HSI) data. We analyze the spectral signature of the image to extract information. In HSI, each pixel is in fact a high dimensional vector typically containing reflectance measurement from hundreds of continuous narrow band spectral channels (FWHM between 2 and 20) and 400-2500 nm wavelength range. The range of spectrum in HSI data extends beyond the visible range. Hyperspectral data processing comes with many stages such as pre-processing, feature reduction, classification and followed by target detection. Various machine learning and deep learning algorithms have been used to classify HSI data where few of them are Support Vector Machine, Convolutional Neural Network, random forest, SSRN, etc. HSI is being used in variety of fields such as agriculture, mining, food quality, soil types, defense etc.

Keywords

Image Classification, Convolutional Neural Network, Support Vector Machine, Hyperspectral.
Subscription Login to verify subscription
User
Notifications
Font Size

  • Javier Plaza, Antonio Plaza, Roza Perez and Pablo Martinez, “Parallel Classification of Hyperspetral Images using Neural Networks”, Computational Intelligence for Remote Sensing, Vol. 133, pp. 193-216, 2018.
  • Alberto Signoroni, Mattia Sarvadia, Annalisa Baronio and Serigo Bennini, “Deep Learning Meets Hyperspectral Image Analysis: A Multidisciplinary Review”, Journal of Imaging, Vol. 5, No. 5, pp. 1-32, 2019.
  • Amol D. Vibhute, Karbhari V. Kale, Rajesh K.Dhumal, Ajay D. Nagne and Suresh C. Mehrotra, “Identification, Classification and Mapping of Surface Soil Types using Hyperspetral Remote Sensing Datasets”, International Journal of Scientific Research in Computer Science, Engineering and Information Technology, Vol. 3, No. 1, pp. 921-932, 2018.
  • M.K. Arora and S. Mathur, “Multi-Source Classification using Artificial Neural Network in Rugged Terrain”, Geocarto International, Vol. 16, No. 3, pp. 37-44, 2001.
  • A. Goetz, G. Vane, J.E. Solomon and B. Rock, “Imaging Spectrometry for Earth Remote Sensing”, Science, Vol. 228, pp. 1147-1153, 1985.
  • P. NilaRekha, R Gangadharan, S. M. Pillai, G. Ramnathan and A. Panigrahi, “Hyperspectral Image Processing to Detect the Soil Salinity”, Proceedings of 4th IEEE International Conference on Advanced Computing, pp. 1-5, 2012.
  • S. Mei, J. Ji, J. Hou, X. Li and Q. Du, “Learning Sensor-Specific Spatial-Spectral Features of Hyperspectral Images via Convolutional Neural Networks”, IEEE Transactions on Geoscience and Remote Sensing, Vol. 55, No. 8, pp. 4520-4533, 2017.
  • M.T. Eismann, “Hyperspectral Remote Sensing”, SPIE Press, 2012.
  • Yanan Luo, Jie Zou, Chengfei Yao, Tao Li and Ganga Bai, “HSI-CNN: A Novel Convolution Neural Network for Hyperspectral Image”, Proceedings of 4th IEEE International Conference on Pattern Recognition, pp. 1-7, 2018.
  • Mehmoodul Hassan, Saleem Ullah, Muhmmad Jaleed Khan and Khurram Khurshid, “Comparative Analysis of SVM, ANN and CNN for Classifying Vegetation Species using Hyperspectral Thermal Infrared Data”, Proceedings of International Workshop on ISPRS Geospatial Week, pp. 1-7, 2019.
  • D.P. Shrestha, D.E. Margate, F. Van Der Meer and H.V. Anh, “Analysis and Classification of Hyperspectral Data for Land Degradation: An Application in Southern Spain”, International Journal of Applied Earth Observation and Geoinformation, Vol. 7, No. 2, pp. 85-96, 2005.
  • Amol D. Vibhute and K.V. Kale, “Soil Type Classification and Mapping using Remote Sensing Data”, Proceedings of International Conference on Man and Machine Interfacing, pp. 17-21, 2015.
  • Sushma Suresh, H.S. Prashantha H.S and S Sandya, “Satellite Image Classification using Clustering Algorithms with Edge Detection Operators”, International Journal on Recent and Innovation Trends in Computing and Communication, Vol. 3, No. 10, pp. 1-12, 2015.
  • K.S. Gunasheela and H.S. Prasantha, “Satellite Image Compression-Detailed Survey of the Algorithms”, Proceedings of International Conference on Cognition and Recognition, pp. 187-198, 2017.
  • Jiabing Leng, Tao Li and Gang Bai, “Cube-CNN-SVM: A Novel Hyperspectral Image Classification Method”, Proceedings of IEEE International Conference on Tools with Artificial Intelligence, pp. 1027-1034, 2016.

Abstract Views: 15

PDF Views: 0




  • Soft Computing Approaches for Hyperspectral Image Classification

Abstract Views: 15  |  PDF Views: 0

Authors

H. S. Prasantha
Department of Electronics and Communication Engineering, Nitte Meenakshi Institute of Technology, India
Moon Moon Chatterjee
Department of Electronics and Communication Engineering, Nitte Meenakshi Institute of Technology, India
Pasupuleti Sai Roshitha
Department of Electronics and Communication Engineering, Nitte Meenakshi Institute of Technology, India
V. Roshitha
Department of Electronics and Communication Engineering, Nitte Meenakshi Institute of Technology, India

Abstract


Hyperspectral image classification is one of the most emerging form of image classification. It is able to convey information about an image in a more detailed way as compared to RGB or multispectral data. When spectral measurement is performed using hundreds of narrow contiguous wavelength intervals, the resulting image is called a hyperspectral image. Spectral signature of thousands of materials have been measured in the laboratory and gathered into libraries. Library signatures are used as the basis for identification of materials in Hyperspectral Image (HSI) data. We analyze the spectral signature of the image to extract information. In HSI, each pixel is in fact a high dimensional vector typically containing reflectance measurement from hundreds of continuous narrow band spectral channels (FWHM between 2 and 20) and 400-2500 nm wavelength range. The range of spectrum in HSI data extends beyond the visible range. Hyperspectral data processing comes with many stages such as pre-processing, feature reduction, classification and followed by target detection. Various machine learning and deep learning algorithms have been used to classify HSI data where few of them are Support Vector Machine, Convolutional Neural Network, random forest, SSRN, etc. HSI is being used in variety of fields such as agriculture, mining, food quality, soil types, defense etc.

Keywords


Image Classification, Convolutional Neural Network, Support Vector Machine, Hyperspectral.

References