Comparative Analysis of Scattering and Random Features in Hyperspectral Image Classification

Haridas, Nikhila; Sowmya, V.; Soman, K P

doi:10.1016/j.procs.2015.08.025

Cited by 6 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed algorithm was compared with some recent classification methods. The results of the hyperspectral reference dataset classification using the HCDA algorithm were compared with the results of other algorithms in previous studies [13,[42][43][44][45][46][47][48][49][50][51][52]. The overall accuracy of the reference dataset classification for various algorithms indicates that HCDA results were better than results of other algorithms.…”

Section: Nomentioning

confidence: 99%

Homogeneity Distance Classification Algorithm (HDCA): A Novel Algorithm for Satellite Image Classification

et al. 2019

View full text Add to dashboard Cite

Image classification is one of the most common methods of information extraction from satellite images. In this paper, a novel algorithm for image classification based on gravity theory was developed, which was called “homogeneity distance classification algorithm (HDCA)”. The proposed HDCA used texture and spectral information for classifying images in two iterative supplementary computing stages: (1) merging, (2) traveling and escaping operators. The HDCA was equipped by a new concept of distance, the weighted Manhattan distance (WMD). Moreover, an improved gravitational search algorithm (IGSA) was applied for selecting features and determining optimal feature space scale in HDCA. In the case of multispectral satellite image classification, the proposed method was compared with two well-known classification methods, Maximum Likelihood classifier (MLC) and Support Vector Machine (SVM). The results of the comparison indicated that overall accuracy values for HDCA, MLC, and SVM are 95.99, 93.15, and 95.00, respectively. Furthermore, the proposed HDCA method was also used for classifying hyperspectral reference datasets (Indian Pines, Salinas and Salinas-A scene). The classification results indicated substantial improvement over previous algorithms and studies by 2% in Indian Pines dataset, 0.7% in the Salinas dataset and 1.2% in the Salinas-A scene. These experimental results demonstrate that the proposed algorithm can classify both multispectral and hyperspectral remote sensing images with reliable accuracy because this algorithm uses the WMD in the classification process and the IGSA to select automatically optimal features for image classification based on spectral and texture information.

show abstract

Section: Nomentioning

confidence: 99%

Homogeneity Distance Classification Algorithm (HDCA): A Novel Algorithm for Satellite Image Classification

et al. 2019

View full text Add to dashboard Cite

show abstract

“…4) Integrated spectral-spatial methods combine information from spectral signatures and spatial neighborhoods simultaneously, and are also common. Some methods consider sequences of 1D spectra [20] (for example in variety of NN called Long Short Term Memory or LSTM) or flatten the HSI cube to a matrix and use 2D methods [33], but by far the most popular methods involve building 3D filters [22], [5], [15], [10], [14], [11], [16], [12], [17], [9]. 3D convolutional layers in NNs, CNNs, and RCNNs, both shallow and deep have been evaluated [5], [22].…”

Section: Related Work a Previous Workmentioning

confidence: 99%

“…However neural networks with multiple layers naturally model a hierarchical interaction of features, with as many degrees of interaction as number of layers in the network: [6], [20], [5], [4], [26], [23], [29], [22], [8], [21]. The same can be said for the layers of scattering networks: [17], [33], [13], [31], [27]. This distinguishes these two classes of approaches from purely wavelet [34], [12], [15], [16] or time-frequency methods [11], [9], [3], [10], and yields more sophisticated features that yield better classification results, as we show in Section IV.…”

Section: Related Work a Previous Workmentioning

confidence: 99%

Three-Dimensional Fourier Scattering Transform and Classification of Hyperspectral Images

Kavalerov,

Li,

Czaja

et al. 2019

Preprint

View full text Add to dashboard Cite

Recent research has resulted in many new techniques that are able to capture the special properties of hyperspectral data for hyperspectral image analysis, with hyperspectral image classification as one of the most active tasks. Timefrequency methods decompose spectra into multi-spectral bands, while hierarchical methods like neural networks incorporate spatial information across scales and model multiple levels of dependencies between spectral features. The Fourier scattering transform is an amalgamation of time-frequency representations with neural network architectures, both of which have recently been proven to provide significant advances in spectral-spatial classification. We test the proposed three dimensional Fourier scattering method on four standard hyperspectral datasets, and present results that indicate that the Fourier scattering transform is highly effective at representing spectral data when compared with other state-of-the-art spectral-spatial classification methods.

show abstract

“…Traditional techniques prove inefficient when confronted with the Hughes phenomenon caused by the high-dimensional nature of spectral channels. Moreover, the presence of redundant information and the increase in computational time due to high dimensionality may have a negative effect on HSI classification [12]. However, the advent of deep learning technology has injected new energy into HSI classification and demonstrated immense potential [13][14][15].…”

Section: Introductionmentioning

confidence: 99%

The Classification of Hyperspectral Images: A Double-Branch Multi-Scale Residual Network

Fu,

Chen,

Pirasteh

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

With the continuous advancement of deep learning technology, researchers have made further progress in the hyperspectral image (HSI) classification domain. We propose a double-branch multi-scale residual network (DBMSRN) framework for HSI classification to improve classification accuracy and reduce the number of required training samples. The DBMSRN consists of two branches designed to extract spectral and spatial features from the HSI. Thus, to obtain more comprehensive feature information, we extracted additional local and global features at different scales by expanding the network width. Moreover, we also increased the network depth to capture deeper feature information. Based on this concept, we devise spectral multi-scale residuals and spatial multi-scale residuals within a double-branch architecture. Additionally, skip connections are employed to augment the context information of the network. We demonstrate that the proposed framework effectively enhances classification accuracy in scenarios with limited training samples through experimental analysis. The proposed framework achieves an overall accuracy of 98.67%, 98.09%, and 96.76% on the Pavia University (PU), Kennedy Space Center (KSC), and Indian Pines (IP) datasets, respectively, surpassing the classification accuracy of existing advanced frameworks under identical conditions.

show abstract

Comparative Analysis of Scattering and Random Features in Hyperspectral Image Classification

Cited by 6 publications

References 6 publications

Homogeneity Distance Classification Algorithm (HDCA): A Novel Algorithm for Satellite Image Classification

Homogeneity Distance Classification Algorithm (HDCA): A Novel Algorithm for Satellite Image Classification

Three-Dimensional Fourier Scattering Transform and Classification of Hyperspectral Images

The Classification of Hyperspectral Images: A Double-Branch Multi-Scale Residual Network

Contact Info

Product

Resources

About