Discriminative spatial-spectral manifold embedding for hyperspectral image classification

In hyperspectral images (HSI) classification, it is important to combine multiple features of a certain pixel in both spatial and spectral domains to improve the classification accuracy. To achieve this goal, this article proposes a novel spatial-spectral feature dimensionality reduction algorithm based on manifold learning. For each feature, a graph Laplacian matrix is constructed based on discriminative information from training samples, and then the graph Laplacian matrices of the various features are linearly combined using a set of empirically defined weights. Finally, the feature mapping is obtained by an eigen-decomposition problem. Based on the classification results of the public Indiana Airborne Visible Infrared Imaging Spectrometer dataset and Texas Hyperspectral Digital Imagery Collection Experiment data set, the technical accuracies show that our method achieves superior performance compared to some representative HSI feature extraction and dimensionality reduction algorithms.     

Salient feature extraction for hyperspectral image classification

Hyperspectral image (HSI) classification has been a vibrant area of research in recent years. In this letter, a salient feature extraction method is designed to improve the HSI classification performance. First, three consecutive bands of HSI are decomposed into several elements in order to better extract salient feature. Second, two measures of contrast that rate the uniqueness and the spatial distribution of these elements are computed. Thirdly, two measures of contrast are combined to form the saliency value of an element. The final saliency of a pixel is formed by a weighted linear combination of its surrounding elements saliency. Finally, three band sliding window is used over the spectral dimension of HSI and salient features extracted from each three adjacent bands are stacked to form the final features. The important characteristic of the proposed approach is that both local spatial information and global spatial information are taken into account in the process of feature extraction. Experimental results on two real HSI datasets demonstrate that the designed feature extraction method could improve the classification performance.     

Semi-Supervised hyperspectral image classification using local low-rank representation

In the area of hyperspectral image (HSI) classification, graph-based semi-supervised learning (SSL) has been proved to be highly effective. Constructing a proper graph is critical for graph-based SSL tasks. In HSI, spectral distance is widely used to calculate the weight of graph edge, though it can be influenced by noise and outliers. Meanwhile, links among all the data points are incorporated in the graph, including those from different subspaces. Thus the constructed graph might contain incorrect information. In this letter, a novel semi-supervised HSI classification method using local low-rank representation (SL²R) is proposed. Edge weight calculation will not be affected by noise or outliers thanks to the robustness of low-rank representation (LRR). Since each graph is constructed at local level, where pixels are basically embedded in the same subspace, links among uncorrelated pixels can be removed. Moreover, spatial context is naturally characterized by low-rank constraint on adjacent pixels. Experimental results on two data sets (Indian Pines and Botswana) confirm the effectiveness of the proposed method.     

Local histogram and discriminative learning-based hyperspectral data classification

A spectral–spatial hyperspectral image classification method is proposed in this article. The proposed method is local histogram and discriminative based classification (LHD). It is implemented in two steps. In the first step, a projection matrix is obtained by maximizing the class discrimination and preserving the local structure of data using both the spectral and spatial neighbours. In the second step, the contextual features are extracted from the local regions using the histogram as a nonparametric statistical estimate. Finally, with incorporating spectral and spatial features, the classification map is obtained. The experimental results demonstrate that the proposed method is superior to some state-of-the-art alternatives.     

Latent subclass learning-based unsupervised ensemble feature extraction method for hyperspectral image classification

A novel unsupervised ensemble feature learning method for hyperspectral image classification is proposed in this study. Firstly, we randomly sample multiple discriminative subsets from a hyperspectral image with the novel spatially constrained similarity measurement. Each subset consists of a small amount of representative pixels. Each pixel in the subset was assigned with a latent-subclass/pseudo label. Multiple multinomial logistic regression classifiers are then adopted to build relations between pixels and their latent subclass labels, where each classifier is trained with one subset. Finally, the predicted results of different classifiers for a given pixel are assembled as its ensemble feature. More discriminative features are extracted by the proposed method compared with features extracted by traditional unsupervised methods such as principal component analysis and non-negative matrix factorization. Experimental results on hyperspectral image classification demonstrate the effectiveness of the proposed method.     

Membranous nephropathy classification using microscopic hyperspectral imaging and tensor patch-based discriminative linear regression

Optical kidney biopsy, serological examination, and clinical symptoms are the main methods for membranous nephropathy (MN) diagnosis. However, false positives and undetectable biochemical components in the results of optical inspections lead to unsatisfactory diagnostic sensitivity and pose obstacles to pathogenic mechanism analysis. In order to reveal detailed component information of immune complexes of MN, microscopic hyperspectral imaging technology is employed to establish a hyperspectral database of 68 patients with two types of MN. Based on the characteristic of the medical HSI, a novel framework of tensor patch-based discriminative linear regression (TDLR) is proposed for MN classification. Experimental results show that the classification accuracy of the proposed model for MN identification is 98.77%. The combination of tensor-based classifiers and hyperspectral data analysis provides new ideas for the research of kidney pathology, which has potential clinical value for the automatic diagnosis of MN.     

An unsupervised feature extraction method based on band correlation clustering for hyperspectral image classification using limited training samples

Due to the advancement of sensor technology, hyperspectral sensors are now able to record reflectance of the earth’s surface in hundreds of bands. This makes hyperspectral images a rich source for a diverse range of applications, including classification tasks. Based on Hughes phenomenon, classification accuracy decreases as dimensionality increases while a limited number of training samples are within reach. In a hyperspectral image adjacent and non-adjacent bands may have a high correlation; therefore removing this redundancy reduces the amount of data for further analysis including classification. Extraction of a few features which lead to high classification accuracy is a need. In this article, we propose an unsupervised feature extraction method called band correlation clustering (BCC). The proposed method includes three main steps: 1) Calculation of the bands’ correlation coefficient and generating correlation coefficient matrix, 2) Grouping the bands based on correlation coefficient matrix using the k-means clustering algorithm, and 3) Mean calculation of each cluster as a newly extracted feature. The proposed method is evaluated by two different criteria: classification accuracy and time consumption. For performance evaluation, the extracted features are fed to two supervised classifiers of non-parametric SVM and parametric ML. The results are compared with the ones obtained by unsupervised extracted features using principle component analysis (PCA), independent component analysis (ICA), and minimum noise fraction (MNF) and supervised ones using generalized discriminant analysis (GDA) and clustering-based feature extraction (CBFE). Comparison of the results shows promising performance for proposed BCC both in terms of computational costs and classification accuracy.     

Classification of hyperspectral and LIDAR data using extinction profiles with feature fusion

Hyperspectral images comprise hundreds of narrow contiguous wavelength bands which include wealth spectral information, and a great potential of Light detection and ranging (LIDAR) data lies in its benefits of height measurements, which can be used as complementary information for the classification of hyperspectral data. In this paper, a feature-fusion strategy of hyperspectral and LIDAR data is taken into account in order to develop a new classification framework for the accurate analysis of a surveyed area. The proposed approach employs extinction profiles (EPs) extracted with extinction filters computed on both hyperspectral and LIDAR images, leading to a fusion of the spectral, spatial, and elevation features. Experimental results obtained by using a real hyperspectral image along with LIDAR-derived digital surface model (DSM) collected over the University of Houston campus and its neighboring urban area demonstrate the effectiveness of the proposed framework.     

Semi-supervised deep learning for hyperspectral image classification

Recently, a series of deep learning methods based on the convolutional neural networks (CNNs) have been introduced for classification of hyperspectral images (HSIs). However, in order to obtain the optimal parameters, a large number of training samples are required in the CNNs to avoid the overfitting problem. In this paper, a novel method is proposed to extend the training set for deep learning based hyperspectral image classification. First, given a small-sample-size training set, the principal component analysis based edge-preserving features (PCA-EPFs) and extended morphological attribute profiles (EMAPs) are used for HSI classification so as to generate classification probability maps. Second, a large number of pseudo training samples are obtained by the designed decision function which depends on the classification probabilities. Finally, a deep feature fusion network (DFFN) is applied to classify HSI with the training set consists of the original small-sample-size training set and the added pseudo training samples. Experiments performed on several hyperspectral data sets demonstrate the state-of-the-art performance of the proposed method in terms of classification accuracies.     

A deep learning framework for hyperspectral image classification using spatial pyramid pooling

In this letter, a new deep learning framework for spectral–spatial classification of hyperspectral images is presented. The proposed framework serves as an engine for merging the spatial and spectral features via suitable deep learning architecture: stacked autoencoders (SAEs) and deep convolutional neural networks (DCNNs) followed by a logistic regression (LR) classifier. In this framework, SAEs is aimed to get useful high-level features for the one-dimensional features which is suitable for the dimension reduction of spectral features, while DCNNs can learn rich features from the training data automatically and has achieved state-of-the-art performance in many image classification databases. Though the DCNNs has shown robustness to distortion, it only extracts features of the same scale, and hence is insufficient to tolerate large-scale variance of object. As a result, spatial pyramid pooling (SPP) is introduced into hyperspectral image classification for the first time by pooling the spatial feature maps of the top convolutional layers into a fixed-length feature. Experimental results with widely used hyperspectral data indicate that classifiers built in this deep learning-based framework provide competitive performance.     

Robust joint nearest subspace for hyperspectral image classification

This letter presents a novel hyperspectral image (HSI) classification method based on robust joint nearest subspace and contextual prototype learning. First, we present a robust joint nearest subspace method to solve the HSI classification problem by exploiting a set-to-class distance with robust distance metric to consider both spectral and spatial characteristics effectively. Second, we develop an objective function to learn contextual prototypes robustly and present an iteration algorithm to solve it. Based on the learned contextual prototypes, the HSI classification performance can be further improved. Finally, we conduct numerous experiments to validate the effects of different parameters and components and to compare the proposed method with other algorithms on three popular data sets. The experimental results show that the proposed method achieves better performance than other competing algorithms.     

A hybrid neural network for hyperspectral image classification

ABSTRACT

Recent research shows that deep learning-based methods can achieve promissing performance when applied to hyperspectral image (HSI) classification in remote sensing, some challenging issues still exist. For example, after a number of 2D convolutions, each feature map may only correspond to a unique dimension of the hyperspectral image. As a result, the relationship between different feature maps from multiple dimensional hyperspectral image can not be extracted well. Another issue is information in extracted feature maps may be erased by pooling operations. To address these problems, we propose a novel hybrid neural network (HNN) for hyperspectral image classification. The HNN uses a multi-branch architecture to extract hyperspectral image features in order to improve its prediction accuracy. Moreover, we build a deconvolution structure to recover the lost information in the pooling operation. In addition, to improve convergence and prevent overfitting, the HNN applies batch normalization (BN) and parametric rectified linear units (PReLU). In the experiments, two public benchmark HSIs are utilized to evaluate the performance of the proposed method. The experimental results demonstrate the superiority of HNN over several well-known methods.     

Superpixel-guided multiscale kernel collaborative representation for hyperspectral image classification

This article presents a superpixel-guided multiscale kernel collaborative representation method for robust classification of hyperspectral images. This novel method first exploits the spatial multiscale information of hyperspectral images by extending a superpixel segmentation algorithm, and then proposes a spatial-spectral information fusion technique to encode the spatial multiscale similarities and the spectral similarities between the pixels in the framework of kernel collaborative representation classification. The advantages of it mainly consist in (1) avoiding choosing empirical parameters in the spatial feature extraction process of superpixels and (2) enhanced classification accuracy as compared to traditional spatial-spectral kernel techniques. Experimental results with two widely used hyperspectral images demonstrate the effectiveness of the proposed method.     

A semi-supervised convolutional neural network for hyperspectral image classification

Convolutional neural network (CNN) for hyperspectral image classification can provide excellent performance when the number of labeled samples for training is sufficiently large. Unfortunately, a small number of labeled samples are available for training in hyperspectral images. In this letter, a novel semi-supervised convolutional neural network is proposed for the classification of hyperspectral image. The proposed network can automatically learn features from complex hyperspectral image data structures. Furthermore, skip connection parameters are added between the encoder layer and decoder layer in order to make the network suitable for semi-supervised learning. Semi-supervised method is adopted to solve the problem of limited labeled samples. Finally, the network is trained to simultaneously minimize the sum of supervised and unsupervised cost functions. The proposed network is conducted on a widely used hyperspectral image data. The experimental results demonstrate that the proposed approach provides competitive results to state-of-the-art methods.     

Random walker with spatial constraint and hyperspectral image classification

In this article, a spatially constrained random walker approach is proposed for hyperspectral image (HSI) classification. This proposed method uses both spectral and spatial information. Image pixels are partitioned into two sets: a labelled set and an unlabelled set. The proposed method aims to label all the unlabelled pixels. The proposed technique consists of two steps. In the first step, random walker computes the posterior probability that an unlabelled pixel has the same label as a labelled pixel by using the spectral information. In order to improve the classification accuracy, Markov random fields is applied to account for spatial information in the second step. Evaluation of the developed method is done on HSIs. Experimental results are compared with those obtained using other HSI classification methods. The proposed approach performs better than other ones in terms of classification accuracy.     

A dense convolutional neural network for hyperspectral image classification

In this letter, a dense convolutional neural network (DCNN) is proposed for hyperspectral image classification, aiming to improve classification performance by promoting feature reuse and strengthening the flow of features and gradients. In the network, features are learned mainly through designed dense blocks, where feature maps generated in each layer can connect directly to the subsequent layers by a concatenation mode. Experiments are conducted on two well-known hyperspectral image data sets, using the proposed method and four comparable methods. Results demonstrate that overall accuracies of the DCNN reached 97.61 and 99.50% for the respective image data sets, representing an obvious improvement over the accuracies of the compared methods. The study confirms that the DCNN can provide more discriminable features for hyperspectral image classification and can offer higher classification accuracies and smoother classification maps.     

A spectral-spatial SVM-based multi-layer learning algorithm for hyperspectral image classification

Conventional Markov random field (MRF) or Graph cut (GC) based support vector machine (SVM) methods for hyperspectral image (HSI) classification use MRF or GC to adjust spectral-based SVM results to increase the spatial consistency in an unsupervised way, thus, the pixels on the border and small-sized regions may be misclassified. In this letter, we propose a new framework of spectral-spatial SVM based multi-layer learning algorithm (SSMLL) for HSI classification. In the first layer of SSMLL, the spectral-based SVM is adopted to process the original HSI datasets; the nonlinear mapping is used to scale the first layer output and enhance the nonlinear structure in the second layer; in the last layer, the spatial information is incorporated into the SVM to obtain the final classification results in a supervised way. Experimental results show that the proposed SSMLL framework provides superior classification accuracy when compared to several state-of-the-art spectral-spatial SVM-based algorithms.     

White blood cell classification via a discriminative region detection assisted feature aggregation network

White blood cell (WBC) classification plays an important role in human pathological diagnosis since WBCs will show different appearance when they fight with various disease pathogens. Although many previous white blood cell classification have been proposed and earned great success, their classification accuracy is still significantly affected by some practical issues such as uneven staining, boundary blur and nuclear intra-class variability. In this paper, we propose a deep neural network for WBC classification via discriminative region detection assisted feature aggregation (DRFA-Net), which can accurately locate the WBC area to boost final classification performance. Specifically, DRFA-Net uses an adaptive feature enhancement module to refine multi-level deep features in a bilateral manner for efficiently capturing both high-level semantic information and low-level details of WBC images. Considering the fact that background areas could inevitably produce interference, we design a network branch to detect the WBC area with the supervision of segmented ground truth. The bilaterally refined features obtained from two directions are finally aggregated for final classification, and the detected WBC area is utilized to highlight the features of discriminative regions by an attention mechanism. Extensive experiments on several public datasets are conducted to validate that our proposed DRFA-Net can obtain higher accuracies when compared with other state-of-the-art WBC classification methods.     

Spectral-Spatial classification of hyperspectral images using functional data analysis

In this letter, a spectral-spatial classification method using functional data analysis (FDA) is proposed. Since the efficacy of the FDA for hyperspectral image analysis instead of analysis in multivariate analysis framework (MAF) was proved previously, we apply FDA to better extract spectral and spatial information for hyperspectral image classification. Therefore, in the FDA framework a support vector machine (SVM) classifier is used for hyperspectral image classification and a watershed segmentation algorithm is applied in order to extract spatial structures. Several approaches to figure a one-band gradient image, as an input to watershed transformation, are examined and investigated. As a result, the extracted segmentation map is used to improve the pixel-wise classification accuracy on which the classification and the segmentation results are combined together using majority vote approach. The efficiency of the proposed method is evaluated on two hyperspectral data sets. The experimental results show that the proposed spectral-spatial classification method provides better classification accuracies compared to some state-of-the-art spectral-spatial classification methods.