Hyperspectral Image Analysis--A Robust Algorithm Using Support Vectors and Principal Components

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.

Different classification techniques are being designed and under usage for classification of hyper spectral images. The usage of these classifiers differ for different type of hyper spectral data and application domain. The performance of these classifiers are influenced by feature preprocessing stage. In this research work we have investigated the impact of feature preprocessing using Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) on classification stage. The experiment is carried out using three sets of hyperspectral data. Classifications were carried out using three different classification techniques namely Maximum Likelihood Estimation (MLE), Constraint Energy Minimization (CEM) and Spectral Angle Mapper (SAM) on the preprocessed hyperspectral data. It is observed that the impact of PCA and LDA on the classification techniques are in two aspects (a) The preprocessing techniques facilitates to achieve high classification accuracy even with less number of training features and (b) Preprocessing expedites the classification process for large data sets. Also it can be concluded that PCA outperforms LDA in case of noisy data.

Target detection is one of research focuses for precision chemical application. This study developed a method to identify seedling cabbages and weeds using hyperspectral imaging. In processing the image data with ENVI software, after dimension reduction, noise reduction, de-correlation for high-dimensional data, and selection of the region of interest, the SAM (Spectral Angle Mapping) model was built for automatic identification of cabbages and weeds. With the HSI (Hyper Spectral Imaging) Analyzer, the training pixels were used to calculate the average spectrum as the standard spectrum. The parameters of the SAM model, which had the best classification results with 3-point smoothing, zero-order derivative, and 6-degrees spectral angle, was determined to achieve the accurate identification of the background, weeds, and cabbages. In comparison, the SAM model can completely separate the plants from the soil background but not perfect for weeds to be separated from the cabbages. In conclusion, the SAM classification model with the HSI analyzer could completely distinguish weeds from background and cabbages. Keywords: hyperspectral imaging, weed identification, cabbage, seedlings DOI: 10.3965/j.ijabe.20150805.1492 Citation: Deng W, Huang Y B, Zhao C J, Wang X. Identification of seedling cabbages and weeds using hyperspectral imaging. Int J Agric & Biol Eng, 2015; 8(5): 65－72.

Hyperspectral image (HSI) classification has many applications in different diverse research fields. We propose a method for HSI classification using principal component analysis (PCA), 2D spatial convolution, and support vector machine (SVM). Our method takes advantage of correlation in both spatial and spectral domains in an HSI data cube at the same time. We use PCA to reduce the dimensionality of an HSI data cube. We then perform spatial convolution to the dimension-reduced data cube once and then to the convolved data cube for the second time. As a result, we have generated two convolved PCA output data cubes in a multiresolution way. We feed the two convolved data cubes to SVM to classify each pixel to one of the known classes. Experiments on three widely used hyperspectral data cubes (i.e., Indian Pines, Pavia University, and Salinas) demonstrate that our method can improve the classification accuracy significantly when compared to a few existing methods. Our method is relatively fast in terms of central processing unit computational time as well.

Hyperspectral Image (HSI) classification plays a key role remote sensing field. Recently, deep learning has demonstrated its effectiveness in HSI Classification field. This paper presents a spectral-spatial HSI classification technique established on the deep learning based deep belief network (DBN) for deep and abstract feature extraction and adaptive boundary adjustment based segmentation. Proposed approach focuses on integrating the deep learning based spectral features and segmentation based spatial features into a framework for improved performance. Specifically, first the deep DBN model is exploited as a spectral feature extraction based classifier to extract the deep spectral features. Second, spatial contextual features are obtained by utilizing effective adaptive boundary adjustment based segmentation technique. Finally, maximum voting based criteria is operated to integrate the results of extracted spectral and spatial information for improved HSI classification. In general, exploiting spectral features from DBN process and spatial features from segmentation and integration of spectral and spatial information by maximum voting based criteria, has a substantial effect on the performance of HSI classification. Experimental performance on real and widely used hyperspectral data sets with different contexts and resolutions demonstrates the accuracy of the proposed technique and performance is comparable to several recently proposed HSI classification techniques.

Target detection is a key issue in processing hyperspectral images (HSIs). Spectral-identification-based algorithms are sensitive to spectral variability and noise in acquisition. In most cases, both the target spatial distributions and the spectral signatures are unknown, so each pixel is separately tested and appears as a target when it significantly differs from the background. In this paper, we propose two algorithms to improve the signal-to-noise ratio (SNR) of hyperspectral data, leading to detectors that are robust to noise. These algorithms consist in integrating adaptive spatial/spectral filtering into the adaptive matched filter and adaptive coherence estimator. Considering the HSIs as tensor data, our approach introduces a data representation involving multidimensional processing. It combines the advantages of spatial and spectral information using an alternating least square algorithm. To estimate the signal subspace dimension in each spatial mode, we extend the Akaike information criterion, and we develop an iterative algorithm for spectral-mode rank estimation. We demonstrate the interest of integrating the quadtree decomposition to perform an adaptive 3-D filtering and thereby preserve the local image characteristics. This leads to a significant improvement in terms of denoised tensor SNR and, consequently, in terms of detection probability. The performance of our method is exemplified using simulated and real-world HYperspectral Digital Imagery Collection Experiment images.

In hyperspectral image (HSI) classification, feature extraction is one important step. Traditional methods, e.g., principal component analysis (PCA) and locality preserving projection, usually neglect the information of within-class similarity and between-class dissimilarity, which is helpful to the improvement of classification. On the other hand, most of these methods, e.g., PCA and linear discriminative analysis, consider that the HSI data lie on a low-dimensional manifold or each class is on a submanifold. However, some class data of HSI may lie on a multimanifold. To avoid these problems, we propose a method for feature extraction in HSIs, assuming that a local region resides on a submainfold. In our method, we deal with the data region by region by taking into account the different discriminative locality information. Then, under the metric learning framework, a robust distance metric is learned. It aims to learn a subspace in which the samples in the same class are as near as possible while the samples in different classes are as far as possible. Encouraging experimental results on two available hyperspectral data sets indicate that our proposed algorithm outperforms many existing feature extract methods for HSI classification.

Hyperspectral image (HSI) classification has become one of the most significant tasks in the field of hyperspectral analysis. However, classifying each pixel in HSI accurately is challenging due to the curse of dimensionality and limited training samples. In this paper, we present an HSI classification architecture called camera spectral response network (CSR-Net), which can learn the optimal camera spectral response (CSR) function for HSI classification problems and effectively reduce the spectral dimensions of HSI. Specifically, we design a convolutional layer to simulate the capturing process of cameras, which learns the optimal CSR function for HSI classification. Then, spectral and spatial features are further extracted by spectral and spatial attention modules. On one hand, the learned CSR can be implemented physically and directly used to capture scenes, which makes the image acquisition process more convenient. On the other hand, compared with ordinary HSIs, we only need images with far fewer bands, without sacrificing the classification precision and avoiding the curse of dimensionality. The experimental results of four popular public hyperspectral datasets show that our method, with only a few image bands, outperforms state-of-the-art HSI classification methods which utilize the full spectral bands of images.

Over the past decade, anomaly detection has been an alluring topic in hyperspectral imagery. Despite most anomaly detection methods that focus on spectral information for detecting targets, this letter proposes a method in which both spectral and spatial information about the hyperspectral image (HSI) has been utilized for detecting anomalies. The differential attribute profile anomaly detection (DAPAD) method utilizes principal component analysis and DAP to extract spectral and spatial information from HSI, respectively. DAPs can model different kinds of structural information in a scene, which makes better extraction of spatial information. The proposed method is applied in experiments on Hyperspectral Digital Imagery Collection Experiment remote sensing data and the experimental results confirm the DAPAD method's superiority over five commonly used state-of-the-art anomaly detection methods.

White mushrooms were subjected to mechanical injury by controlled shaking in a plastic box at 400 rpm for different times (0, 60, 120, 300 and 600 s). Immediately after shaking, hyperspectral images were obtained using two pushbroom line-scanning hyperspectral imaging instruments, one operating in the wavelength range of 400 - 1000 nm with spectroscopic resolution of 5 nm, the other operating in the wavelength range of 950 - 1700 nm with spectroscopic resolution of 7 nm. Different spectral and spatial pretreatments were investigated to reduce the effect of sample curvature on hyperspectral data. Algorithms based on Chemometric techniques (Principal Component Analysis and Partial Least Squares Discriminant Analysis) and image processing methods (masking, thresholding, morphological operations) were developed for pixel classification in hyperspectral images. In addition, correlation analysis, spectral angle mapping and scaled difference of sample spectra were investigated and compared with the chemometric approaches.

A kernel based nonlinear subspace projection (KNSP) method is proposed for reduction of hyperspectral image dimensionality. This method involves three steps: subspace partition of full data space, feature extraction based on kernel principal component analysis (KPCA) in subspace and feature selection based on class separability criterion. The main merit of the proposed method is that it is more suitable for feature extraction than linear principal component analysis (PCA) and segmented principal component: transformation (SPCT), in particular, when hyperspectral data have nonlinear characteristics. In order to testify the effectiveness of the KNSP method for reduction of hyperspectral image dimensionality, hyperspectral image classification is performed on AVIRIS data. Experimental results show that when the hyperspectral dimensionality is reduced to a few features, the average classification accuracy of the new method is higher than those of PCA and SPCT methods.

Hyperspectral image classification with limited labeled samples is a challenging task and still an open research issue. In this article, a novel technique is presented to address such an issue by exploiting dimensionality reduction, spectral-spatial information, and classification with active learning. The proposed technique is based on two phases. Considering the importance of dimensionality reduction and spatial information for the analysis of hyperspectral images, Phase I generates the patterns corresponding to each pixel of the image using both spectral and spatial information. To this end, first, principal component analysis is used to reduce the dimensionality of an hyperspectral image, then extended morphological profiles are exploited. The spectral-spatial information based patterns generated by extended morphological profiles are used as input to the Phase II. Phase II performs the classification task guided by an active learning technique. This technique is based on a novel query function that uses uncertainty, diversity, and cluster assumption criteria by exploiting the properties of k-means clustering, K-nearest neighbors algorithm, support vector machines, and genetic algorithms. Experiments on three benchmark hyperspectral datasets demonstrate that the proposed method outperforms five state-of-the-art active learning methods.

The spectral matching, statistical and kernel based methods are the most widely known classification algorithms for hyperspectral imaging. Spectral matching algorithms try to identify the similarity of the unknown spectral signature of test pixels with the expected signature. In this study, an efficient spectral similarity method employing Multi-Scale Vector Tunnel Algorithm (MS-VTA) for supervised classification of the materials in hyperspectral imagery is introduced. With the proposed algorithm, a simple spectral similarity based decision rule using some reference data or spectral signature is formed and compared with the Euclidian Distance (ED) and the Spectral Angle Map (SAM) classifiers. The prediction of multi-level upper and lower spectral boundaries of spectral signatures for all classes across spectral bands constitutes the basic principle of the proposed algorithm.

The lack of training samples remains one of the major obstacles in applying convolutional neural networks (CNNs) to the hyperspectral image (HSI) classification. In this letter, the accurate classification of HSI with limited training samples is investigated. Due to the advantages of minimizing the distance between samples in the same class and maximizing the distance between samples in different classes, siamese CNN is used for HSI classification with limited training samples. After that, to improve the classification performance, data augmentation is investigated for siamese CNN-based HSI classification. Specifically, pair data augmentation based on CutMix is proposed to generate the training pairs of the same or different classes and the new generated training pairs are used to train siamese CNN. Traditional data augmentation methods simply generate new training samples. It is not proper when data augmentation methods keep the loss function and change the content of the input at the same time. Therefore, a soft-loss-based siamese CNN, which changes its loss according to the coupled replacement data augmentation, is proposed to further address the HSI classification with limited training samples. In the experimental part, on two widely used hyperspectral datasets, the influences of different training samples and window sizes are discussed, and the experimental results reveal that the proposed soft-augmentation-based siamese CNN provides competitive results with limited training samples compared with state-of-the-art methods.

The significant capability of synoptic coverage of satellite remote sensing data at the time of advent providing accurate and immediate valuable information on various aspects. The progressive development of remote sensing increases its capability to identify and map the precious and valuable materials and minerals. Spectral Angle Mapper (SAM) is classifiers of supervised classification for mapping and classification. The characteristic of SAM is based on similarity between image spectra and reference spectra on the behalf of tolerance level of specified maximum angle of threshold. In this research work SAM algorithms applied for mapping of Chhabadiya talc mineral. In this research work SAM algorithms defines the applicability of similarity of angle and value of threshold parameters of spectral angle which show capability to interpret or map the maximum and minimum abundance of talc minerals. For this research work Hyperion hyperspectral remote sensing data used for study of applicability and efficiency of SAM algorithms for mineral mapping. The quality and abundance of minerals completely depend on the minimum degree of SAM threshold parameter. Maximum spectral angle shows maximum mapping area with minimum similarity, but low spectral angle shows small and more abundant mapping area with maximum similarity in the hyperspectral image. Conclusion of this research work verify the identification of minerals are depend on the spectral and spectral characteristics of hyperspectral remote sensing data and mapping with qualitative abundance of minerals depend on the lower value of spectral angle and threshold of SAM algorithms or maximum similarity of spectra.