Hyperspectral image (HSI) classification is major and necessary task related to HSI analysis in the field of remote sensing. The fundamental steps in this task are band selection (BS), spatial feature extraction, and classification. HSIs generally equipped with rich spectral and spatial information and having the properties such as non-stationary and non-Gaussian. To process such rich information, wavelet transform (WT) is the perfect candidate. Also, the multiscale system in wavelets will be used in complete information extraction. So, classification task is implemented by the application of WT in BS and spatial feature extraction. Here, BS is achieved by the combination of clustering based on key band identification and ranking using wavelet entropy (WE). Discrete wavelet transform is applied along three dimensions to extract spatial features. The extracted spectral and spatial features are used in final classification by convolution neural networks classifier. From the obtained results it is observed that, with the advantage of using WT, the proposed method has successfully addressed overfitting and huge data dimensionality problems. Comparison and detailed analysis of the class-wise accuracies also clearly shows the impact of using WT in HSI classification. Evaluation results on three publicly used datasets namely Indian Pines, University of Pavia, and Salinas shows the significant performance over state-of-the-art methods. The proposed method has attained overall accuracy of 93.85%, 99.05%, and 97.13% for the three datasets, respectively.
Hyperspectral image (HSI) classification is one of the significant research topics in the remote sensing community. The high dimensionality of the hyperspectral data, the high correlation among pixels, and the availability of fewer numbers of training samples affect the HSI classification accuracy. We propose an approach to extract the best representative bands from the high-dimensional imagery for better classification. Initially, the spectral bands are extracted by re-representing the traditional principal component analysis in terms of Hebbian learning, formulated and solved as a fuzzy optimization problem. Next, a spatial filter is applied to these spectral bands to obtain the smoothed image that preserves the spatial details. Finally, the spectral and spatial features are trained with the nonlinear support vector machine with the radial basis function kernel to obtain the classification map. Performance of the proposed approach is tested by varying different values of the parameters used in our model. The classification accuracy of the proposed approach is compared with the state-of-the-art techniques, which proves the effectiveness of the proposed methodology. The proposed approach can be applied in real-world applications, such as food quality, environment change detection, mineralogy, and pharmaceutical drug design.
The presence of a significant amount of information in the hyperspectral image makes it suitable for numerous applications. However, extraction of the suitable and informative features from the high-dimensional data is a tedious task. A feature extraction technique using expectation–maximization (EM) clustering and weighted average fusion technique is proposed. Bhattacharya distance measure is used for computing the distance among all the spectral bands. With this distance information, the spectral bands are grouped into the clusters by employing the EM clustering method. The EM algorithm automatically converges to an optimum number of clusters, thereby specifying the absence of need for the required number of clusters. The bands in each cluster are fused together applying the weighted average fusion method. The weight of each band is calculated on the basis of the criteria of minimizing the distance inside the cluster and maximizing the distance among the different clusters. The fused bands from each cluster are then considered as the extracted features. These features are used to train the support vector machine for classification of the hyperspectral image. The performance of the proposed technique has been validated against three small-size standard bench-mark datasets, Indian Pines, Pavia University, Salinas, and one large-size dataset, Botswana. The proposed method achieves an overall accuracy (OA) of 92.19%, 94.10%, 93.96%, and 84.92% for Indian Pines, Pavia University, Salinas, and Botswana datasets, respectively. The experimental results prove that the proposed technique attains significant classification performance in terms of the OA, average accuracy, and Cohen’s kappa coefficient (k) when compared to the other competing methods.
The hyperspectral remote sensor acquires hundreds of contiguous spectral images, resulting in large data that contain a significant amount of redundant information. This high-dimensional and redundant data always influence the efficiency of the data processing. Therefore, feature extraction becomes one of the critical tasks in hyperspectral image classification. A transform-domain-based feature extraction technique, three-dimensional discrete cosine transform (3-D DCT), is proposed. The reason behind the transform domains is that, generally, an invertible linear transform reconstructs the image data to provide the independent information about the spectra or more separable transformation coefficients. Moreover, DCT has excellent energy compaction properties for highly correlated images, such as hyperspectral images, which reduces the complexity of the separation significantly. Unlike the discrete wavelet transform that requires sequential transform to obtain the approximation and detailed coefficients, DCT extracts all coefficients simultaneously. As a result, computation time in the feature extraction can be reduced. The experimental results on three benchmark datasets (Indian Pines, Pavia University, and Salinas) show that the proposed approach produces a good classification in terms of overall accuracy, average accuracy as well as Cohen’s kappa coefficient (κ) when compared with some traditional as well as transform-based feature extraction algorithms. Experimental result also shows that the proposed method requires less computational time than the transform-based feature extraction method.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.