Graph Scaling Cut with L1-Norm for Classification of Hyperspectral Images (original) (raw)
Related papers
A Graph-based Technique for the Spectral-spatial Hyperspectral Images Classification
Minimum Spanning Forest (MSF) is a graph-based technique used for segmenting and classification of images. In this article, a new method based on MSF is introduced that can be used to supervised classification of hyperspectral images. For a given hyperspectral image, a pixel-based classification, such as Support Vector Machine (SVM) or Maximum Likelihood (ML) is performed. On the other hand, dimensionality reduction is carried out by Principal Components Analysis (PCA) and the first eight components are considered as the reference data. The most reliable pixels, which are obtained from the result of pixel-based classifiers, are used as markers in the construction of MSF. In the next stage, three MSF's are created after considering three distinct criteria of similarity (dissimilarity). Ultimately, using the majority voting rule, the obtained classification maps are combined and the final classification map is formed. The simulation results presented on an AVRIS image of the vegetation area indicate that the proposed technique enhanced classification accuracy and provides an accurate classification map.
A Trace Lasso Regularized L1-norm Graph Cut for Highly Correlated Noisy Hyperspectral Image
2018
This work proposes an adaptive trace lasso regularized L1-norm based graph cut method for dimensionality reduction of Hyperspectral images, called as `Trace Lasso-L1 Graph Cut' (TL-L1GC). The underlying idea of this method is to generate the optimal projection matrix by considering both the sparsity as well as the correlation of the data samples. The conventional L2-norm used in the objective function is sensitive to noise and outliers. Therefore, in this work L1-norm is utilized as a robust alternative to L2-norm. Besides, for further improvement of the results, we use a penalty function of trace lasso with the L1GC method. It adaptively balances the L2-norm and L1-norm simultaneously by considering the data correlation along with the sparsity. We obtain the optimal projection matrix by maximizing the ratio of between-class dispersion to within-class dispersion using L1-norm with trace lasso as the penalty. Furthermore, an iterative procedure for this TL-L1GC method is proposed...
A Trace Lasso Regularized Ll-norm Graph Cut for Highly Correlated Noisy Hyperspectral Image
2018
Ahstract-This work proposes an adaptive trace lasso regularized Ll-norm based graph cut method for dimensionality reduction of Hyperspectral images, called as ‘Trace Lasso-Ll Graph Cut’ (TL-LIGC). The underlying idea of this method is to generate the optimal projection matrix by considering both the sparsity as well as the correlation of the data samples. The conventional L2-norm used in the objective function is sensitive to noise and outliers. Therefore, in this work Ll-norm is utilized as a robust alternative to L2-norm. Besides, for further improvement of the results, we use a penalty function of trace lasso with the LIGC method. It adaptively balances the L2-norm and Ll-norm simultaneously by considering the data correlation along with the sparsity. We obtain the optimal projection matrix by maximizing the ratio of between-class dispersion to within-class dispersion using Ll-norm with trace lasso as the penalty. Furthermore, an iterative procedure for this TL-LIGC method is pro...
2017
Containing hundreds of spectral bands (features), hyperspectral images (HSIs) have high ability in discrimination of land cover classes. Traditional HSIs data processing methods consider the same importance for all bands in the original feature space (OFS), while different spectral bands play different roles in identification of samples of different classes. In order to explore the relative importance of each feature, we learn a weighting matrix and obtain the relative weighted feature space (RWFS) as an enriched feature space for HSIs data analysis in this paper. To overcome the difficulty of limited labeled samples which is common case in HSIs data analysis, we extend our method to semisupervised framework. To transfer available knowledge to unlabeled samples, we employ graph based clustering where low rank representation (LRR) is used to define the similarity function for graph. After construction the RWFS, any arbitrary dimension reduction method and classification algorithm can...
Gaussian Process Graph-Based Discriminant Analysis for Hyperspectral Images Classification
Remote Sensing
Dimensionality Reduction (DR) models are highly useful for tackling Hyperspectral Images (HSIs) classification tasks. They mainly address two issues: the curse of dimensionality with respect to spectral features, and the limited number of labeled training samples. Among these DR techniques, the Graph-Embedding Discriminant Analysis (GEDA) framework has demonstrated its effectiveness for HSIs feature extraction. However, most of the existing GEDA-based DR methods largely rely on manually tuning the parameters so as to obtain the optimal model, which proves to be troublesome and inefficient. Motivated by the nonparametric Gaussian Process (GP) model, we propose a novel supervised DR algorithm, namely Gaussian Process Graph-based Discriminate Analysis (GPGDA). Our algorithm takes full advantage of the covariance matrix in GP to constructing the graph similarity matrix in GEDA framework. In this way, more superior performance can be provided with the model parameters tuned automatically...