Hongjun Su

Local Binary Patterns and Extreme Learning Machine for Hyperspectral Imagery Classification

It is of great interest in exploiting texture information for classification of hyperspectral imagery (HSI) at high spatial resolution. In this paper, a classification paradigm to exploit rich texture information of HSI is proposed. The proposed framework employs local binary patterns (LBPs) to extract local image features, such as edges, corners, and spots. Two levels of fusion (i.e., feature-level fusion and decision-level fusion) are applied to the extracted LBP features along with global Gabor features and original spectral features, where feature-level fusion involves concatenation of multiple features before the pattern classification process while decision-level fusion performs on probability outputs of each individual classification pipeline and soft-decision fusion rule is adopted to merge results from the classifier ensemble. Moreover, the efficient extreme learning machine with a very simple structure is employed as the classifier. Experimental results on several HSI data sets demonstrate that the proposed framework is superior to some traditional alternatives.

Spectral-Spatial Classification of Hyperspectral Image Based on Kernel Extreme Learning Machine

Extreme learning machine (ELM) is a single-layer feedforward neural network based classifier that has attracted significant attention in computer vision and pattern recognition due to its fast learning speed and strong generalization. In this paper, we propose to integrate spectral-spatial information for hyperspectral image classification and exploit the benefits of using spatial features for the kernel based ELM (KELM) classifier. Specifically, Gabor filtering and multihypothesis (MH) prediction preprocessing are two approaches employed for spatial feature extraction. Gabor features have currently been successfully applied for hyperspectral image analysis due to the ability to represent useful spatial information. MH prediction preprocessing makes use of the spatial piecewise-continuous nature of hyperspectral imagery to integrate spectral and spatial information. The proposed Gabor-filtering-based KELM classifier and MH-prediction-based KELM classifier have been validated on two real hyperspectral datasets. Classification results demonstrate that the proposed methods outperform the conventional pixel-wise classifiers as well as Gabor-filtering-based support vector machine (SVM) and MH-prediction-based SVM in challenging small training sample size conditions.

Land-use scene classification using multi-scale completed local binary patterns

In this paper, we introduce the completed local binary patterns (CLBP) operator for the first time on remote sensing land-use scene classification. To further improve the representation power of CLBP, we propose a multi-scale CLBP (MS-CLBP) descriptor to characterize the dominant texture features in multiple resolutions. Two different kinds of implementations of MS-CLBP equipped with the kernel-based extreme learning machine are investigated and compared in terms of classification accuracy and computational complexity. The proposed approach is extensively tested on the 21-class land-use dataset and the 19-class satellite scene dataset showing a consistent increase on performance when compared to the state of the arts.

Optimized Hyperspectral Band Selection Using Particle Swarm Optimization

A particle swarm optimization (PSO)-based system is proposed to select bands and determine the optimal number of bands to be selected simultaneously, which is near-automatic with only a few data-independent parameters. The proposed system includes two particle swarms, i.e., the outer one for estimating the optimal number of bands and the inner one for the corresponding band selection. To avoid employing an actual classifier within PSO so as to greatly reduce computational cost, criterion functions that can gauge class separability are preferred; specifically, minimum estimated abundance covariance (MEAC) and Jeffreys-Matusita (JM) distance are adopted in this research. The experimental results show that the 2PSO-based algorithm outperforms the popular sequential forward selection (SFS) method and PSO with one particle swarm in band selection.

Harmonic Analysis for Hyperspectral Image Classification Integrated With PSO Optimized SVM

A novel hyperspectral image classification approach named as HA-PSO-SVM is proposed by integrating the harmonic analysis (HA), particle swarm optimization (PSO), and support vector machine (SVM). In the combined method, HA is first proposed to transform the pixels from spectral domain into frequency domain expressed by amplitude, phase and residual, yielding more functional and discriminative features for classification purpose. In this step, the original pixel vector can also be reconstructed. Then, PSO is adapted to optimize the penalty parameter C and the kernel parameter γ for SVM, which leads to improved classification performance. Finally, the extracted features are classified with the optimized model. The experimental results with three hyperspectral data sets collected by the airborne visible infrared imaging spectrometer (AVIRIS) and the reflective optics spectrographic imaging system (ROSIS) indicate that the proposed method provides improved classification performance compared with some related techniques in terms of both the classification accuracy and the computational time.

Hyperspectral Band Selection Using Improved Firefly Algorithm

An improved firefly algorithm (FA)-based band selection method is proposed for hyperspectral dimensionality reduction (DR). In this letter, DR is formulated as an optimization problem that searches a small number of bands from a hyperspectral data set, and a feature subset search algorithm using the FA is developed. To avoid employing an actual classifier within the band searching process to greatly reduce computational cost, criterion functions that can gauge class separability are preferred; specifically, the minimum estimated abundance covariance and Jeffreys-Matusita distances are employed. The proposed band selection technique is compared with an FA-based method that actually employs a classifier, the well-known sequential forward selection, and particle swarm optimization algorithms. Experimental results show that the proposed algorithm outperforms others, providing an effective option for DR.

Firefly-Algorithm-Inspired Framework With Band Selection and Extreme Learning Machine for Hyperspectral Image Classification

A firefly algorithm (FA) inspired band selection and optimized extreme learning machine (ELM) for hyperspectral image classification is proposed. In this framework, FA is to select a subset of original bands to reduce the complexity of the ELM network. It is also adapted to optimize the parameters in ELM (i.e., regularization coefficient C, Gaussian kernel σ, and hidden number of neurons L). Due to very low complexity of ELM, its classification accuracy can be used as the objective function of FA during band selection and parameter optimization. In the experiments, two hyperspectral image datasets acquired by HYDICE and HYMAP are used, and the experiment results indicate that the proposed method can offer better performance, compared with particle swarm optimization and other related band selection algorithms.

Adaptive affinity propagation with spectral angle mapper for semi-supervised hyperspectral band selection

Band selection is a commonly used approach for dimensionality reduction in hyperspectral imagery. Affinity propagation (AP), a new clustering algorithm, is addressed in many fields, and it can be used for hyperspectral band selection. However, this algorithm cannot get a fixed number of exemplars during the message-passing procedure, which limits its uses to a great extent. This paper proposes an adaptive AP (AAP) algorithm for semi-supervised hyperspectral band selection and investigates the effectiveness of distance metrics for improving band selection. Specifically, the exemplar number determination algorithm and bisection method are addressed to improve AP procedure, and the relations between selected exemplar numbers and preferences are established. Experiments are conducted to evaluate the proposed AAP-based band selection algorithm, and the results demonstrate that the proposed method outperforms other popular methods, with lower computational cost and robust results.

Simultaneous Sparse Graph Embedding for Hyperspectral Image Classification

Sparse graph embedding (SGE) is a promising technique useful for the nonlinear feature extraction (FE) of hyperspectral images (HSIs). However, such images exhibit spatial variability and spectral multimodality, presenting challenges to existing FE methods, including SGE. To address this issue, this paper presents two novel SGE methods for HSI classification. One method, which is termed simultaneous SGE (SSGE), is designed to consider the spatial variability of spectral signatures by using a simultaneous sparse representation (SSR) model integrated with a shape-adaptive neighborhood building approach. In addition, a sparse graph is constructed via matrix computation based on sparse codes. Then, low-dimensional features are produced by employing linear graph embedding (LGE) based on the constructed sparse graph. The other method, which is termed simultaneous sparse multimanifold learning (SSMML), is proposed to handle the multimodality of an HSI. In SSMML, multiple views are generated to represent different modalities. Then, multiview-oriented submanifolds are produced by adopting SSGE, and they are further integrated via coregularization. SSGE is capable of modeling both local and global data structures. Furthermore, SSMML serves as a prototype that can model multimodal data structures. The proposed methods are evaluated by using sparse multinomial logistic regression for HSI classification. Experimental results with two popular hyperspectral data sets validate the good performance of the two methods in producing more representative low-dimensional features and yielding superior classification results compared with other related approaches.

Gabor-Filtering-Based Completed Local Binary Patterns for Land-Use Scene Classification

Remote sensing land-use scene classification has a wide range of applications including forestry, urban-growth analysis, and weather forecasting. This paper presents an effective image representation method, Gabor-filtering-based completed local binary patterns (GCLBP), for land-use scene classification. It employs the multi-orientation Gabor filters to capture the global texture information from an input image. Then, a local operator called completed local binary patterns (CLBP) is utilized to extract the local texture features, such as edges and corners, from the Gabor feature images and the input image. The resulting CLBP histogram features are concatenated to represent an input image. Experimental results on two datasets demonstrate that the proposed method is superior to several existing methods for land-use scene classification.