An unsupervised band selection algorithm for hyperspectral imagery based on maximal information

Liu, Xuesong; Ge, Liang; Wang, Bin; Zhang, Liming

doi:10.3724/sp.j.1010.2012.00166

Cited by 19 publications

(11 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first hyperspectral image is the Indian Pines dataset, which has 145×145 pixels and 220 bands with a wavelength range from 400 to 2500 nm (Figure 3). In our experiments, bands 1-3, 103-112, 148-165, and 217-220 were removed due to atmospheric water vapor absorption and low signal to noise ratio (SNR) [14], leaving a total of 185 valid bands to be used. From the 16 land-cover classes available in the original ground truth, seven classes can be removed because of a lack of sufficient samples [14].…”

Section: Indian Pine Datasetmentioning

confidence: 99%

“…Some of them use different information criteria to measure the importance of hyperspectral bands, then all the bands are sorted and several top ranked bands would be selected. These kind of methods include information divergence BS (IDBS) [10], linearly constraint minimum variance (LCMV) [10], constrained band selection (CBS) [10], mutual information [12], maximum-variance principal component analysis (MVPCA) [13] and so on [14]. Other band selection methods take bands' correlation into consideration.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Discovering the Representative Subset with Low Redundancy for Hyperspectral Feature Selection

Zhang

Zhao

2019

Remote Sensing

View full text Add to dashboard Cite

In this paper, a novel unsupervised band selection (BS) criterion based on maximizing representativeness and minimizing redundancy (MRMR) is proposed for selecting a set of informative bands to represent the whole hyperspectral image cube. The new selection criterion is denoted as the MRMR selection criterion and the associated BS method is denoted as the MRMR method. The MRMR selection criterion can evaluate the band subset’s representativeness and redundancy simultaneously. For one band subset, its representativeness is estimated by using orthogonal projection (OP) and its redundancy is measured by the average of the Pearson correlation coefficients among the bands in this subset. To find the satisfactory subset, an effective evolutionary algorithm, i.e., the immune clone selection (ICS) algorithm, is applied as the subset searching strategy. Moreover, we further introduce two effective tricks to simplify the computation of the representativeness metric, thus the computational complexity of the proposed method is reduced significantly. Experimental results on different real-world datasets demonstrate that the proposed method is very effective and its selected bands can obtain good classification performances in practice.

show abstract

Section: Indian Pine Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Discovering the Representative Subset with Low Redundancy for Hyperspectral Feature Selection

Zhang

Zhao

2019

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The image was collected by the AVIRIS sensor over the Indian Pine region in Northwestern Indiana in 1992, and it has 145 × 145 pixels (about 20 m per pixel) and 220 bands with a wavelength range from 400 to 2500 nm (Figure 3a). In our experiments, bands 1-3, 103-112, 148-165, and 217-220 were removed due to atmospheric water vapor absorption and low signal to noise ratio (SNR) [16], leaving 185 valid bands to be used. Of the 16 classes in the image, only nine classes are used in our experiment and the others are removed because of the lack of sufficient samples (Table 1) [16].…”

Section: Hyperspectral Datasetsmentioning

confidence: 99%

“…In our experiments, bands 1-3, 103-112, 148-165, and 217-220 were removed due to atmospheric water vapor absorption and low signal to noise ratio (SNR) [16], leaving 185 valid bands to be used. Of the 16 classes in the image, only nine classes are used in our experiment and the others are removed because of the lack of sufficient samples (Table 1) [16]. (2) Salinas Dataset [41]: The second image was collected by the 224-band AVIRIS sensor over Salinas Valley, California, and was characterized by a high spatial resolution (3.7-m pixels) ( Figure 3b).…”

Section: Hyperspectral Datasetsmentioning

confidence: 99%

“…These include Information Divergence BS (IDBS) [10], Constrained Band Selection (CBS) [10], Linearly Constraint Minimum Variance (LCMV) [10], Maximum-Variance PCA (MVPCA) [11] and Mutual Information [12]. Other BS methods take bands' correlation into consideration and resort to finding the bands combination with the optimal indexes, such as Optimal Index Factor (OIF) [13,14], Maximum Ellipsoid Volume (MEV) [15], Maximum Information (MI) [16], Minimum Dependent Information (MDI) [17], Linear-Prediction-based BS (LPBS) [18,19], Manifold Ranking (MR) [20], Volume-Gradient-based BS (VGBS) [21] and other similar methods [22][23][24]. Recently, exploiting correlation through clustering algorithms has attracted more attentions in the field of BS [25].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Band Priority Index: A Feature Selection Framework for Hyperspectral Imagery

Zhang

Zhao

2018

Remote Sensing

View full text Add to dashboard Cite

Hyperspectral Band Selection (BS) aims to select a few informative and distinctive bands to represent the whole image cube. In this paper, an unsupervised BS framework named the band priority index (BPI) is proposed. The basic idea of BPI is to find the bands with large amounts of information and low correlation. Sequential forward search (SFS) is used to avoid an exhaustive search, and the objective function of BPI consist of two parts: the information metric and the correlation metric. We proposed a new band correlation metric, namely, the joint correlation coefficient (JCC), to estimate the joint correlation between a single band and multiple bands. JCC uses the angle between a band and the hyperplane determined by a band set to evaluate the correlation between them. To estimate the amount of information, the variance and entropy are used as the information metric for BPI, respectively. Since BPI is a framework for BS, other information metrics and different mathematic functions of the angle can also be used in the model, which means there are various implementations of BPI. The BPI-based methods have the advantages as follows: (1) The selected bands are informative and distinctive. (2) The BPI-based methods usually have good computational efficiencies. (3) These methods have the potential to determine the number of bands to be selected. The experimental results on different real hyperspectral datasets demonstrate that the BPI-based methods are highly efficient and accurate BS methods.

show abstract

Representativeness and Redundancy-Based Band Selection for Hyperspectral Image Classification`

Liu

Feng

et al. 2021

International Journal of Remote Sensing

View full text Add to dashboard Cite

An unsupervised band selection algorithm for hyperspectral imagery based on maximal information

Cited by 19 publications

References 11 publications

Discovering the Representative Subset with Low Redundancy for Hyperspectral Feature Selection

Discovering the Representative Subset with Low Redundancy for Hyperspectral Feature Selection

Band Priority Index: A Feature Selection Framework for Hyperspectral Imagery

Representativeness and Redundancy-Based Band Selection for Hyperspectral Image Classification`

Contact Info

Product

Resources

About