An Efficient Ensemble Approach for Hyperspectral Image Classification

Extraction of efficient spectral - spatial features are one of the challenging tasks in HSI for remote sensing community. In this paper, a feature sub-cube is generated by concatenating three sub-cubes obtained from three feature extraction approaches. The generated cube from the ensembling approach is undergone an intrinsic recursive filter for spatial features. The generated cube is then trained with RBF kernel-based support vector machine for classification. The proposed framework is examined on Indian pines dataset. The reported OA is 96.28%, AA is 95.34% and Kappa coefficient is 95.74%. The robustness of the framework is tested with state-of-the-art methods and also with different Model input. This framework can be used for different applications such as mineral mapping and change detection.

• Publication year

  2023

• Venue

  2023 5th International Conference on Smart Systems and Inventive Technology (ICSSIT)

• Publication date

  2023-01-23

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/ICSSIT55814.2023.10061021
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A review on graph-based semi-supervised learning methods for hyperspectral image classification

  2020cited by this paper
• Robust Spatial–Spectral Block-Diagonal Structure Representation With Fuzzy Class Probability for Hyperspectral Image Classification

  2020cited by this paper
• A new neuro-fuzzy-based classification approach for hyperspectral remote sensing images

  2019cited by this paper
• Classification of Hyper Spectral Remote Sensing Imagery Using Intrinsic Parameter Estimation

  2018cited by this paper
• A New Spatial–Spectral Feature Extraction Method for Hyperspectral Images Using Local Covariance Matrix Representation

  2018cited by this paper
• Probabilistic PCA Based Hyper Spectral Image Classification for Remote Sensing Applications

  2018cited by this paper
• Comparative study of feature extraction techniques for hyper spectral remote sensing image classification : A survey

  2017cited by this paper
• Albedo recovery for hyperspectral image classification

  2017cited by this paper
• Survey on classification methods for hyper spectral remote sensing imagery

  2017cited by this paper
• Hyperspectral image classification using fuzzy C-means based composite kernel approach

  2017cited by this paper
• Semi-supervised techniques based hyper-spectral image classification: A survey

  2017cited by this paper
• A short survey of hyperspectral remote sensing applications in agriculture

  2013cited by this paper
• Locality-Preserving Dimensionality Reduction and Classification for Hyperspectral Image Analysis

  2012cited by this paper
• Locality-Preserving Discriminant Analysis in Kernel-Induced Feature Spaces for Hyperspectral Image Classification

  2011cited by this paper
• Hyperspectral Image Classification With Independent Component Discriminant Analysis

  2011cited by this paper
• A New Nonlinear Fuzzy Robust PCA Algorithm and Similarity Classifier in Classification of Medical Data Sets

  2011cited by this paper
• Morphological Attribute Profiles for the Analysis of Very High Resolution Images

  2010cited by this paper
• Robust kernel PCA using fuzzy membership

  2009cited by this paper
• Recent Advances in Techniques for Hyperspectral Image Processing

  2009cited by this paper
• Limitations of Principal Components Analysis for Hyperspectral Target Recognition

  2008influential reference
• Kernel-based methods for hyperspectral image classification

  2005cited by this paper
• Endmember selection for multiple endmember spectral mixture analysis using endmember average RMSE

  2003cited by this paper
• Remote Sensing Digital Image Analysis

  1986cited by this paper
• On the mean accuracy of statistical pattern recognizers

  1968cited by this paper
• Analysis of a complex of statistical variables into principal components.

  1933cited by this paper

• No citing papers are available for this paper.