Hyperspectral image classification based on spatial and spectral features and sparse representation

To minimize the low classification accuracy and low utilization of spatial information in traditional hyperspectral image classification methods, we propose a new hyperspectral image classification method, which is based on the Gabor spatial texture features and nonparametric weighted spectral features, and the sparse representation classification method（Gabor–NWSF and SRC）, abbreviated GNWSF–SRC. The proposed（GNWSF–SRC） method first combines the Gabor spatial features and nonparametric weighted spectral features to describe the hyperspectral image, and then applies the sparse representation method. Finally, the classification is obtained by analyzing the reconstruction error. We use the proposed method to process two typical hyperspectral data sets with different percentages of training samples. Theoretical analysis and simulation demonstrate that the proposed method improves the classification accuracy and Kappa coefficient compared with traditional classification methods and achieves better classification performance.

Multi-task Joint Sparse Representation Classification Based on Fisher Discrimination Dictionary Learning

Recently,sparse representation classification(SRC)and fisher discrimination dictionary learning(FDDL)methods have emerged as important methods for vehicle classification.In this paper,inspired by recent breakthroughs of discrimination dictionary learning approach and multi-task joint covariate selection,we focus on the problem of vehicle classification in real-world applications by formulating it as a multi-task joint sparse representation model based on fisher discrimination dictionary learning to merge the strength of multiple features among multiple sensors.To improve the classification accuracy in complex scenes,we develop a new method,called multi-task joint sparse representation classification based on fisher discrimination dictionary learning,for vehicle classification.In our proposed method,the acoustic and seismic sensor data sets are captured to measure the same physical event simultaneously by multiple heterogeneous sensors and the multi-dimensional frequency spectrum features of sensors data are extracted using Mel frequency cepstral coefficients(MFCC).Moreover,we extend our model to handle sparse environmental noise.We experimentally demonstrate the benefits of joint information fusion based on fisher discrimination dictionary learning from different sensors in vehicle classification tasks.

Weighted Sparse Image Classification Based on Low Rank Representation

The conventional sparse representation-based image classification usually codes the samples independently,which will ignore the correlation information existed in the data.Hence,if we can explore the correlation information hidden in the data,the classification result will be improved significantly.To this end,in this paper,a novel weighted supervised spare coding method is proposed to address the image classification problem.The proposed method firstly explores the structural information sufficiently hidden in the data based on the low rank representation.And then,it introduced the extracted structural information to a novel weighted sparse representation model to code the samples in a supervised way.Experimental results show that the proposed method is superiority to many conventional image classification methods.

Low-Rank and Sparse Representation with Adaptive Neighborhood Regularization for Hyperspectral Image Classification

Low-Rank and Sparse Representation(LRSR)method has gained popularity in Hyperspectral Image(HSI)processing.However,existing LRSR models rarely exploited spectral-spatial classification of HSI.In this paper,we proposed a novel Low-Rank and Sparse Representation with Adaptive Neighborhood Regularization(LRSR-ANR)method for HSI classification.In the proposed method,we first represent the hyperspectral data via LRSR since it combines both sparsity and low-rankness to maintain global and local data structures simultaneously.The LRSR is optimized by using a mixed Gauss-Seidel and Jacobian Alternating Direction Method of Multipliers(M-ADMM),which converges faster than ADMM.Then to incorporate the spatial information,an ANR scheme is designed by combining Euclidean and Cosine distance metrics to reduce the mixed pixels within a neighborhood.Lastly,the predicted labels are determined by jointly considering the homogeneous pixels in the classification rule of the minimum reconstruction error.Experimental results based on three popular hyperspectral images demonstrate that the proposed method outperforms other related methods in terms of classification accuracy and generalization performance.

Metasample-Based Robust Sparse Representation for Tumor Classification

In this paper, based on sparse representation classification and robust thought, we propose a new classifier, named MRSRC (Metasample Based Robust Sparse Representation Classificatier), for DNA microarray data classification. Firstly, we extract Metasample from trainning sample. Secondly, a weighted matrix W is added to solve an l1-regular- ized least square problem. Finally, the testing sample is classified according to the sparsity coefficient vector of it. The experimental results on the DNA microarray data classification prove that the proposed algorithm is efficient.

Integrating absolute distances in collaborative representation for robust image classification

Conventional sparse representation based classification （SRC） represents a test sample with the coefficient solved by each training sample in all classes. As a special version and improvement to SRC, collaborative representation based classification （CRC） obtains representation with the contribution from all training samples and produces more promising results on facial image classification. In the solutions of representation coefficients, CRC considers original value of contributions from all samples. However, one prevalent practice in such kind of distance-based methods is to consider only absolute value of the distance rather than both positive and negative values. In this paper, we propose an novel method to improve collaborative representation based classification, which integrates an absolute distance vector into the residuals solved by collaborative representation. And we named it AbsCRC. The key step in AbsCRC method is to use factors a and b as weight to combine CRC residuals rescrc with absolute distance vector disabs and generate a new dviaetion r = a·rescrc b.disabs, which is in turn used to perform classification. Because the two residuals have opposite effect in classification, the method uses a subtraction operation to perform fusion. We conducted extensive experiments to evaluate our method for image classification with different instantiations. The experimental results indicated that it produced a more promising result of classification on both facial and non-facial images than original CRC method.

A new discriminative sparse parameter classifier with iterative removal for face recognition

Face recognition has been widely used and developed rapidly in recent years.The methods based on sparse representation have made great breakthroughs,and collaborative representation-based classification(CRC)is the typical representative.However,CRC cannot distinguish similar samples well,leading to a wrong classification easily.As an improved method based on CRC,the two-phase test sample sparse representation(TPTSSR)removes the samples that make little contribution to the representation of the testing sample.Nevertheless,only one removal is not sufficient,since some useless samples may still be retained,along with some useful samples maybe being removed randomly.In this work,a novel classifier,called discriminative sparse parameter(DSP)classifier with iterative removal,is proposed for face recognition.The proposed DSP classifier utilizes sparse parameter to measure the representation ability of training samples straight-forward.Moreover,to avoid some useful samples being removed randomly with only one removal,DSP classifier removes most uncorrelated samples gradually with iterations.Extensive experiments on different typical poses,expressions and noisy face datasets are conducted to assess the performance of the proposed DSP classifier.The experimental results demonstrate that DSP classifier achieves a better recognition rate than the well-known SRC,CRC,RRC,RCR,SRMVS,RFSR and TPTSSR classifiers for face recognition in various situations.

Robust Hierarchical Framework for Image Classification via Sparse Representation

The sparse representation-based classification algorithm has been used for human face recognition. But an image database was restricted to human frontal faces with only slight illumination and expression changes. Cropping and normalization of the face needs to be done beforehand. This paper uses a sparse representation-based algorithm for generic image classification with some intra-class variations and background clutter. A hierarchical framework based on the sparse representation is developed which flexibly combines different global and local features. Experiments with the hierarchical framework on 25 object categories selected from the Caltech101 dataset show that exploiting the advantage of local features with the hierarchical framework improves the classification performance and that the framework is robust to image occlusions, background clutter, and viewpoint changes.

Discriminative Structured Dictionary Learning for Image Classification

In this paper, a discriminative structured dictionary learning algorithm is presented. To enhance the dictionary's discriminative power, the reconstruction error, classification error and inhomogeneous representation error are integrated into the objective function. The proposed approach learns a single structured dictionary and a linear classifier jointly. The learned dictionary encourages the samples from the same class to have similar sparse codes, and the samples from different classes to have dissimilar sparse codes. The solution to the objective function is achieved by employing a feature-sign search algorithm and Lagrange dual method. Experimental results on three public databases demonstrate that the proposed approach outperforms several recently proposed dictionary learning techniques for classification.

Semi-Supervised Dimensionality Reduction of Hyperspectral Image Based on Sparse Multi-Manifold Learning

In this paper, we proposed a new semi-supervised multi-manifold learning method, called semi- supervised sparse multi-manifold embedding (S3MME), for dimensionality reduction of hyperspectral image data. S3MME exploits both the labeled and unlabeled data to adaptively find neighbors of each sample from the same manifold by using an optimization program based on sparse representation, and naturally gives relative importance to the labeled ones through a graph-based methodology. Then it tries to extract discriminative features on each manifold such that the data points in the same manifold become closer. The effectiveness of the proposed multi-manifold learning algorithm is demonstrated and compared through experiments on a real hyperspectral images.

Spatial-Aware Supervised Learning for Hyper-Spectral Image Classification Comprehensive Assessment

A comprehensive assessment of the spatial.aware mpervised learning algorithms for hyper.spectral image （HSI） classification was presented. For this purpose, standard support vector machines （ SVMs ）, mudttnomial logistic regression （ MLR ） and sparse representation （SR） based supervised learning algorithm were compared both theoretically and experimentally. Performance of the discussed techniques was evaluated in terms of overall accuracy, average accuracy, kappa statistic coefficients, and sparsity of the solutions. Execution time, the computational burden, and the capability of the methods were investigated by using probabilistie analysis. For validating the accuracy a classical benchmark AVIRIS Indian pines data set was used. Experiments show that integrating spectral.spatial context can further improve the accuracy, reduce the misclassltication error although the cost of computational time will be increased.

结合改进LBP和SRC的高光谱图像分类研究

针对传统局部二值模型(local binary pattern,LBP)提取高光谱图像纹理特征信息量庞大的难题,提出一种基于对称旋转不变等价局部二值模型(symmetrical rotation invariant uniform LBP,SRIULBP)的高光谱图像特征提取方法,以缩减特征维度;针对稀疏表示分类(sparse representation classification,SRC)模型中稀疏字典冗余的缺陷,采用近邻思想,提出最近邻稀疏表示(nearest neighbor SRC,NNSRC)分类方法,实现高光谱图像的高效、高准确度分类。数据实验结合表明,SRIULBP能快速提取图像特征,提出的分类方法不仅在分类精度上优于其他稀疏表示分类算法,并且具有更强的时效性与泛化能力。

基于自适应矩阵的核联合稀疏表示高光谱图像分类

针对高光谱图像丰富的空间信息和光谱信息未充分利用的问题,提出了基于自适应矩阵的核联合稀疏表示高光谱图像分类的方法。在特征表示阶段,定义了自适应矩阵特征,通过结合自适应邻域块策略与非线性相关熵度量构成的特征来描述原始光谱像素,充分融合了形状可变的空间信息与非线性光谱信息。在分类阶段,考虑自适应矩阵和高光谱图像非线性,采用对数欧式核函数,构建了核联合稀疏表示模型,以获得重构误差。同时利用字典空间信息构建了矩阵相关性,引入平衡参数实现了稀疏重构误差与矩阵相关性的联合分类。在两个数据集上的实验结果表明,该算法充分利用了高光谱图像的空间信息、光谱信息,能够有效提高分类精度。

基于EEMD样本熵和SRC的自确认气体传感器故障诊断方法

针对非线性、非平稳情况下自确认气体传感器的故障诊断问题,提出了对传感器不同故障模式信号进行特征提取和智能识别的在线故障诊断方法。首先,该方法根据传感器信号的变化进行集合经验模态分解(ensemble empirical mode decomposition,EEMD),自适应地获得一组固有模态函数(intrinsic mode functions,IMFs),对每个IMF及残余分量进行样本熵分析,提取传感器输出信号的完备特征;然后,利用稀疏表示分类(sparse representationbased classification,SRC)将各故障模式下训练样本的特征向量构成超完备字典。为了提高故障诊断方法的自适应能力,对SRC分类器进行在线更新。通过求解最小1范数约束问题,获得测试样本的稀疏表示系数,再由不同故障类型的重构误差确定测试样本归属,进行传感器故障类型识别。实验结果表明,与目前其他传感器故障诊断方法比较,本文提出的方法能够更显著地提取传感器故障信号特征,故障识别率提高4%以上,达到97.14%。

基于SVM和SRC级联决策融合的SAR图像目标识别方法

提出基于支持向量机(support vector machine,SVM)和稀疏表示分类(sparse representation-based classification,SRC)级联决策融合的合成孔径雷达(synthetic aperture radar,SAR)图像目标识别方法。首先,采用SVM对测试样本进行分类,根据各个训练类别输出的后验概率,采用门限判决法选取其中具有高置信度的候选类别;其次,基于候选训练样本构造字典,对测试样本进行SRC分类;最后,采用线性加权融合SVM和SRC的决策值,获得更为可靠的识别结果。SVM的预筛选分类有效降低了SRC中的字典规模,从而提高其分类效率,同时,SRC具有的噪声、遮挡稳健性也可以补充SVM在此方面的不足。因此,提出的方法可以有效综合SVM和SRC的优势,提高最终的识别性能。采用MSTAR数据集进行识别实验,结果验证了本文方法的有效性。

基于PCA和SRC算法的人脸识别储物柜系统的设计与实现

该文设计研究了人脸识别储物柜系统,针对影响识别率的因素,采用了压缩感知即结合主成分特征提取的稀疏表示分类算法(SRC)。阐述了主成分分析法(PCA)提取特征向量的工作原理和稀疏表示分类算法的实现,以及人脸识别储物柜的硬件实现和软件流程。试验结果表明,与传统的识别算法比对,结合压缩感知理论的人脸识别方法,识别率高,对噪声、有部分遮挡物情况的识别效果较好。

多源声发射信号混合重叠组稀疏分类研究

针对高速列车车体裂纹声发射检测的多源、波模式重叠及噪声干扰问题,提出一种基于本征模态的混合重叠组稀疏(MOGS)分类方法用于声发射源识别。MOGS是一种兼顾组间和组内稀疏,同时允许类间特征重叠的结构稀疏模型。设计了一种新的噪声预分解矩阵以降低本征模态分解计算量,选取目标特征频带模态为分类样本来提高类间差异。通过K-SVD层次稀疏组套索罚训练MOGS类别字典,并给出一种罚函数块坐标可分离的近似光滑处理过程以实现MOGS套索求解。实验表明,该方法对几类多源含噪信号分类准确率均高于80%,在识别率和波形重构效果上优于对比方法。

Volterra核优化的SRC人脸识别算法

为了提高稀疏表示分类算法对属于同一方向不同类别样本的分类准确率,提出了一种基于Volterra核优化的稀疏表示分类算法。该算法首先将原始的人脸图像分成不重叠的小块,并利用Volterra核映射到高维空间。在训练阶段遵循费舍尔标准,根据最大化类间距离和最小化类内距离来定义目标函数,从而获得优化Volterra核。与其他方法在ORL和YaleB标准数据集上进行对比实验,结果表明,采用Volterra核优化的SRC人脸识别分类方法在对样本的分类精度上提高了3%。

融合CNN和SRC决策的SAR图像目标识别方法

提出基于卷积神经网络(Convolutional Neural Network,CNN)与稀疏表示分类(Sparse Representation-based Classification,SRC)联合决策的合成孔径雷达(Synthetic Aperture Radar,SAR)目标识别方法。CNN通过深度网络学习SAR图像的多层次特征,进而对其所属的目标类别进行判决。研究表明,CNN在训练样本充足的条件下可以取得很好的识别性能。然而,对于训练样本未能包含的条件,CNN的分类性能通常会出现明显下降。因此,先采用CNN对待识别的测试样本进行分类,再根据输出的决策值(即,各个训练类别对应的后验概率)计算当前分类结果的可靠性。当分类结果判定可靠时,则直接采信CNN的决策,输出测试样本的目标类别。反之,则根据CNN输出的决策值筛选若干候选类别,然后基于它们的训练样本构建全局字典用于SRC分类。对于SRC的分类结果,进一步采用Bayesian融合算法将其与CNN的分类结果进行融合。最终,根据融合后的结果判定测试样本的目标类别。提出方法通过层次化的思路融合CNN和SRC的优势,有利于发挥两者对不同测试条件的优势,达到提高识别稳健性的目的。实验中,基于MSTAR数据集开展测试分析,结果验证了提出方法的有效性。

用于人脸识别的改进MKD-SRC方法

稀疏表示是近年来图像处理、模式识别及计算机视觉领域中的一个研究热点,广泛应用在图像压缩、图像去噪及修复、目标检测、物体识别等各个方向.在人脸识别的应用背景下,一种基于局部特征的多任务稀疏表示分类方法,即基于多任务多关键点特征描述子(multi-keypoint descriptors,MKD)的稀疏识别(MKD-SRC)方法虽具有良好的旋转、尺度不变性,但计算复杂度较高,且对光照的鲁棒性并不理想.本文就此问题分析了MKD-SRC方法的原理和前提,提出基于线性子空间和极大似然概率的改进方法,并在公开人脸数据库上对方法的性能进行了测试.实验结果表明,改进的MKD-SRC方法在计算效率以及对大块噪声污染和光照不均匀的鲁棒性这两个方面取得了良好的效果.