Unsupervised Hyperspectral Band Selection With Multigraph Integrated Embedding and Robust Self-Contained Regression

Abstract :  Band selection is an effective means to alleviate the curse of dimensionality in hyperspectral data. Many methods select a compact and low redundant band subset, which is inadequate as it may degrade the classification performance. Instead, more emphasis shall be put on selecting representative bands. In this paper, we propose a robust unsupervised band selection method to address this issue. Our method reveals bandwise representativeness based on the comprehensive inter-band neighborhood structure. It incorporates an inter-band neighborhood graph into a sparse self-contained regression model in order to provide a reasonable measure for band-wise representativeness.The derived coefficient matrix not only uncovers band-wise importance values, but also is coherent to the generalized interband local neighborhood structure. For constructing the interband neighboring structural graph, an integrated multi-graph model is employed to achieve better generalization performance. It combines the benefit of multiple graphs but is insusceptible to the defects of a single one. To enhance the reliability of this model, a joint trace minimum and non-negative constraint is imposed on the coefficient matrix. Accordingly, a multi-graph integrated embedding and robust self-contained regression model (MGRSR) is formulated. In addition, an iterative update algorithm is developed to solve the problem. Comparative experiments on three hyperspectral datasets illustrate that MGRSR is robust to various data and has superior performance when compared with several state-of-the-art methods.

 EXISTING SYSTEM :

 ? To overcome these shortcomings, this article proposes a patch tensor-based multigraph embedding (PTMGE) framework for the DR of HSIs, in which three different types of subgraphs are constructed to comprehensively describe the intrinsic geometrical structures of HSIs. ? First, a tensor subgraph is constructed to capture the spatial information and local geometrical structure. Second, for each two neighboring patch tensors in the tensor graph, a bipartite graph is designed to characterize the pixel-based relationships between the patch tensors. ? Then, considering that the diversity of pixels may be existed in each patch tensor, a pixel-based subgraph is built to describe the inner geometrical structures of every patch tensor.

 DISADVANTAGE :

 ? To solve the presented problem, this paper also develops an iterative update algorithm in line with ADMM. ? In addition, concerning evaluating the performance of MGRSR, comparative experiments are carried out on three widely adopted hyperspectral datasets. ? Experimental results demonstrate that compared with others, the proposed method is robust and exhibits obvious superiority. ? Although these manifold learning methods can reveal data nonlinear structure, they often suffer from the so-called out-of-sample problem

 PROPOSED SYSTEM :

 • We compare the proposed method with other six unsupervised band selection algorithms. • Therefore, in this paper, a new unsupervised method for band selection based on clustering and neural network is proposed. • A comparison with six other band selection frameworks shows the strength of the proposed method. • They propose a sparse representation of bands with row-sparsity constraint. Besides, a dissimilarity-weighted regularization term is integrated with the self-representation model, to avoid contiguous bands.

 ADVANTAGE :

 ? Graph-based dimensionality reduction (DR) techniques are of great interest in the field of image processing and especially on the analysis of hyperspectral images (HSIs). Considering the characteristics of hyperspectral data, many different types of graphs were designed to describe the structure of HSIs. ? Generally, the algorithms based on these graphs achieved promising performance. However, most of them only focus on how to improve the measurement of similarity between the data points by a single graph. ? To improve the robustness of TLPP, the graph construction is modified with the local region covariance descriptor by using the duality between feature space and original data space . Following the idea of constructing more robust adjacency graph in tensor space to improve the performance of tensor graph-based methods, Pan et al. proposed tensor SLGDA (TSLGDA).