Band Selection Of Hyperspectral Images Research Articles

Boltzmann Entropy-Based Unsupervised Band Selection for Hyperspectral Image Classification

Band selection for hyperspectral images helps improve the efficiency of data processing and even the accuracy of classification. It is to reduce the dimensionality of a hyperspectral image by selecting representative bands. In such a process, the quantification of band similarity is the fundamental issue, and it is usually achieved by using an information-theoretic measure, such as mutual information or relative entropy. However, these measures are incapable of quantifying similarity in terms of both composition and configuration. To solve this problem, the Boltzmann entropy (BE), which captures both configurational and compositional information, is employed in this letter. More precisely, the difference in BE between two bands is used for such quantification. The corresponding search strategy is designed for band selection. Experimental evaluation was carried out using remote sensing images for classification. The results clearly demonstrate the superiority of the proposed band selection method over traditional information-theoretic methods: an increase of up to 27% in classification accuracy was observed when using the difference in relative BE with 20 selected bands. In addition, another comparison with some state-of-the-art methods was conducted. The results show that the proposed method is still very competitive; it outperformed all the others when the number of selected bands ranges from 18 to 23. This letter, the first of its kind, reveals that the BE may form a new base for information-theoretic approaches to image processing and even for spatial information science in a broad sense.

Supervised band selection in hyperspectral images using single-layer neural networks

ABSTRACTHyperspectral images provide fine details of the scene under analysis in terms of spectral information. This is due to the presence of contiguous bands that make possible to distinguish different objects even when they have similar colour and shape. However, neighbouring bands are highly correlated, and, besides, the high dimensionality of hyperspectral images brings a heavy burden on processing and also may cause the Hughes phenomenon. It is therefore advisable to make a band selection pre-processing prior to the classification task. Thus, this paper proposes a new supervised filter-based approach for band selection based on neural networks. For each class of the data set, a binary single-layer neural network classifier performs a classification between that class and the remainder of the data. After that, the bands related to the biggest and smallest weights are selected, so, the band selection process is class-oriented. This process iterates until the previously defined number of bands is achieved. A comparison with three state-of-the-art band selection approaches shows that the proposed method yields the best results in 43.33% of the cases even with greatly reduced training data size, whereas the competitors have achieved between 13.33% and 23.33% on the Botswana, KSC and Indian Pines datasets.

Superpixel-Based Unsupervised Band Selection for Classification of Hyperspectral Images

This paper presents an unsupervised approach to band selection in hyperspectral images that considers both spectral and spatial information in data dimensionality reduction. The approach exploits the concepts of superpixel and chunklets for identifying the spectral channels most suitable to be used in classification for discriminating land-cover classes. The segmented superpixels can be regarded as many small spectral homogeneous and spatial neighboring pixel chunklets. Based on the observation that the superpixel chunklets achieve high homogeneity and consistency within land-cover classes, a series of band criteria (BC) is identified by learning the optimal band transformation that results in low within-class variability and high total variability. Then, the learned BC, which are called band measures, are given in input to an efficient clustering algorithm, i.e., the affinity propagation, for selecting highly separable bands with low redundancy. The effectiveness of proposed approach was assessed on three hyperspectral data sets. The results point out the advantages of the proposed methods over five state-of-the-art unsupervised methods.

Hyperspectral band selection based on multi-objective optimization with high information and low redundancy

For band selection in hyperspectral images, there are two crucial aspects, information preservation and redundancy reduction, which have a great influence on the subsequent applications. Most of current works have a fixed preference on these two aspects. However, since different data sets possess different numerical characteristics, optimal preferences on these two aspects may be different and difficult to be decided. Therefore, a method is required, which can explore optimal trade-offs of these two aspects according to different characteristics of data sets. To address this challenge, a novel multi-objective optimization model for band selection is proposed. Two conflicting objective functions compose the proposed model. One measures the amount of information and the other one measures the redundancy contained in the selected bands. Through this model, the two aspects are quantified, which makes it possible to optimize them simultaneously. To optimize this model, a new multi-objective immune algorithm is designed to fit the characteristics of hyperspectral data. And it has the ability to obtain a series of Pareto optimal solutions which represent different optimal trade-offs between the two objective functions. In this way, the proposed method can explore the optimal trade-offs between the two aspects and provide decision makers more options according to different characteristics of data sets. Experiments are implemented on three real hyperspectral data sets. The results show the superiority of the proposed method.

A Band Selection Method for Hyperspectral Image Based on Particle Swarm Optimization Algorithm with Dynamic Sub-Swarms

Band selection is an effective means to reduce the hyperspectral data size and to overcome the Hughes phenomenon in ground object classification. This paper presents a band selection method based on particle swarm dynamic with sub-swarms optimization, aiming at the deficiency of particle swarm optimization algorithm being easy to fall into local optimum when applied to hyperspectral image band selection. This algorithm treats fitness function as criterion, dividing all particles into different adaptation degree interval corresponding to the dynamic subgroup and adopting different optimization methods for different subgroups as well as sub -swarms parallel iterative searching for the optimal band. In this way, we can make achievement of clustering optimization of particle with different optimization capability, ensuring the diversity of particles in order to reduce the risk of falling into local optimum. Finally, we prove the effectiveness of this algorithm through selected bands validation by support vector machine.

Discriminative Feature Metric Learning in the Affinity Propagation Model for Band Selection in Hyperspectral Images

Traditional supervised band selection (BS) methods mainly consider reducing the spectral redundancy to improve hyperspectral imagery (HSI) classification with class labels and pairwise constraints. A key observation is that pixels spatially close to each other in HSI have probably the same signature, while pixels further away from each other in the space have a high probability of belonging to different classes. In this paper, we propose a novel discriminative feature metric-based affinity propagation (DFM-AP) technique where the spectral and the spatial relationships among pixels are constructed by a new type of discriminative constraint. This discriminative constraint involves chunklet and discriminative information, which are introduced into the BS process. The chunklet information allows for grouping of spectrally-close and spatially-close pixels together without requiring explicit knowledge of their class labels, while discriminative information provides important separability information. A discriminative feature metric (DFM) is proposed with the discriminative constraints modeled in terms of an optimal criterion for identifying an efficient distance metric learning method, which involves discriminative component analysis (DCA). Following this, the representative subset of bands can be identified by means of an exemplar-based clustering algorithm, which is also known as the process of affinity propagation. Experimental results show that the proposed approach yields a better performance in comparison with several representative class label and pairwise constraint-based BS algorithms. The proposed DFM-AP improves the classification performance with discriminative constraints by selecting highly discriminative bands with low redundancy.

Band selection for hyperspectral images based on particle swarm optimization and differential evolution algorithms with hybrid encoding

Band selection for hyperspectral images based on particle swarm optimization and differential evolution algorithms with hybrid encoding

Approach Based on Fuzzy C-Means for Band Selection in Hyperspectral Images

Approach Based on Fuzzy C-Means for Band Selection in Hyperspectral Images

Unsupervised Band Selection Based on Evolutionary Multiobjective Optimization for Hyperspectral Images

Band selection is an important preprocessing step for hyperspectral image processing. Many valid criteria have been proposed for band selection, and these criteria model band selection as a single-objective optimization problem. In this paper, a novel multiobjective model is first built for band selection. In this model, two objective functions with a conflicting relationship are designed. One objective function is set as information entropy to represent the information contained in the selected band subsets, and the other one is set as the number of selected bands. Then, based on this model, a new unsupervised band selection method called multiobjective optimization band selection (MOBS) is proposed. In the MOBS method, these two objective functions are optimized simultaneously by a multiobjective evolutionary algorithm to find the best tradeoff solutions. The proposed method shows two unique characters. It can obtain a series of band subsets with different numbers of bands in a single run to offer more options for decision makers. Moreover, these band subsets with different numbers of bands can communicate with each other and have a coevolutionary relationship, which means that they can be optimized in a cooperative way. Since it is unsupervised, the proposed algorithm is compared with some related and recent unsupervised methods for hyperspectral image band selection to evaluate the quality of the obtained band subsets. Experimental results show that the proposed method can generate a set of band subsets with different numbers of bands in a single run and that these band subsets have a stable good performance on classification for different data sets.

Combination of Clustering and Ranking Techniques for Unsupervised Band Selection of Hyperspectral Images

Curse of dimensionality is a major disadvantage for classification of hyperspectral imagery since a large number of bands need to be dealt with. Band selection is a task to reduce the number of bands. An unsupervised band selection method is proposed in this article. It is a three-step procedure. In the first step, characteristics (attributes) of the bands are found out. Next, redundancy among the bands is removed by executing clustering operation. At last, the remaining bands, which are nonredundant among themselves, are ranked according to their discriminating capability. Discriminating capability is calculated by measuring the capacitory discrimination of the bands. Results are compared with four state-of-the-art methods: a band elimination method, a ranking-based, and two clustering-based band selection methods to demonstrate the effectiveness of the proposed method. Four evaluation measures, namely: 1) classification accuracy; 2) Kappa coefficient; 3) class separability, and 4) entropy, are calculated over the selected bands to assess the efficiency of the selected bands. The proposed method shows promising results compared to them.

Band Selection for Hyperspectral Images Using Non-Negativity Constraints

This paper presents a new factorization technique for hyperspectral signal processing based on a constrained singular value decomposition (SVD) approach. Hyperpectral images typically have a large number of contiguous bands that are highly correlated. Likewise the field of view typically contains a limited number of materials and the spectra are also correlated. Only a selected number of bands, the extreme bands that include the dominant materials spectral signatures, are needed to express the data. Factorization can provide a means for interpretation and compression of the spectral data. Hyperspectral images are represented as non-negative matrices by graphic concatenation, with the pixels arranged into columns and each row corresponding to a spectral band. SVD and principal component analysis enjoy a broad range of applications, including, rank estimation, noise reduction, classification and compression, with the resulting singular vectors forming orthogonal basis sets for subspace projection techniques. A key property of non-negative matrices is that their columns/rows form non-negative cones, with any non-negative linear combination of the columns/rows belonging to the cone. Data sets of spectral images and time series reside in non-negative orthants and while subspaces spanned by SVD include all orthants, SVD projections can be constrained to the non-negative orthants. In this paper we utilize constraint sets that confine projections of SVD singular vectors to lie within the cones formed by the spectral data. The extreme vectors of the cone are found and these vectors form a basis for the factorization of the data. The approach is illustrated in an application to hyperspectral data of a mining area collected by an airborne sensor.

Band Selection for Hyperspectral Image Classification Based on Improved Particle Swarm Optimization Algorithm

Hyperspectral images have been widely used in earth observation. However, there are some problems such as huge amount of data and high correlation between bands. An application of particle swarm optimization algorithm based on B distance was proposed to band selection of hyperspectral images. First of all, bands are grouping by the correlation coefficient of the band and adjacent bands. B distance was used as separability criterion between classes and the fitness function comes into being. Finally, the classification results illustrate that the total classification accuracy of the proposed method is higher than the traditional method.

Evolutionary refinement approaches for band selection of hyperspectral images with applications to automatic monitoring of animal feed quality

This paper presents methods for spectral band selection in hyperspectral image HSI cubes based on classification of reflectance data acquired from samples of livestock feed materials and ruminant-derived bonemeal. Automated detection of ruminant-derived bonemeal in animal feed is tested as part of an on-going research into development of automated, reliable fast and cost-effective quality control systems. HSI cubes contain spectral reflectance in both spatial dimensions and spectral bands. Support vector machines are used for classification of data in various domains. Selecting a subset of the spectral bands speeds processing and increases accuracy by reducing over-fitting. We developed two methods utilizing divergence values for selecting spectral band sets, 1 evolutionary search method and 2 divergence-based recursive feature elimination approach.

Band Selection of Hyperspectral Image Based on Differential Evolution Algorithm

Band Selection of Hyperspectral Image Based on Differential Evolution Algorithm

Band selection of hyperspectral-image based weighted indipendent component analysis

Huge amounts of data in hyperspectral images have been caused to represent approaches for the band selection of these images. In this paper, a new approach based on independent component analysis (ICA) is proposed. The idea of projection pursuit is used to order the bands on the basis of a non-gaussianity distribution. Applying a negentropy function to weight bands is a novel idea that leads to the selection of bands with minimum mutual information (MI) and besides maximum entropy, with respected to the bands selected using other methods.

Band selection of hyperspectral images based on Bhattacharyya distance

With the development of sensor technology, the spectral resolution of remote sensing image is continuously improved. The appearance of the hyperspectral remote sensing is a tremendous leap in the f...