Semi-supervised fuzzy neighborhood preserving analysis for feature extraction in hyperspectral remote sensing images

Neural Computing and Applications - Semi-supervised feature extraction methods are an important focus of interest in data mining and machine learning areas. These methods are improved methods based...     

Relevance-based feature extraction for hyperspectral images.

Hyperspectral imagery affords researchers all discriminating details needed for fine delineation of many material classes. This delineation is essential for scientific research ranging from geologic to environmental impact studies. In a data mining scenario, one cannot blindly discard information because it can destroy discovery potential. In a supervised classification scenario, however, the preselection of classes presents one with an opportunity to extract a reduced set of meaningful features without degrading classification performance. Given the complex correlations found in hyperspectral data and the potentially large number of classes, meaningful feature extraction is a difficult task. We turn to the recent neural paradigm of generalized relevance learning vector quantization (GRLVQ) [B. Hammer and T. Villmann, Neural Networks vol. 15, pp. 1059-1068, 2002], which is based on, and substantially extends, learning vector quantization (LVQ) [T. Kohonen, Self-Organizing Maps, Berlin, Germany: Springer-Verlag, 2001] by learning relevant input dimensions while incorporating classification accuracy in the cost function. By addressing deficiencies in GRLVQ, we produce an improved version, GRLVQI, which is an effective analysis tool for high-dimensional data such as remotely sensed hyperspectral data. With an independent classifier, we show that the spectral features deemed relevant by our improved GRLVQI result in a better classification for a predefined set of surface materials than using all available spectral channels.     

基于局部特征与核低秩表示的人脸识别算法

针对人脸识别中的遮挡、伪装、光照及表情变化等问题,提出一种基于局部特征与核低秩表示的人脸识别算法。首先,对训练和测试的样本图片进行LBP特征的提取;然后将其通过映射函数投影到高维特征空间中进行后续操作,投影到高维空间中的特征矩阵通过降维处理后采用低秩表示的方法来提取样本之间的共同特征;最后根据低秩表示的结果进行分类识别。实验证明算法在对遮挡、伪装以及光照变化等噪声的影响鲁棒性更强,同时较当前的一些人脸识别算法的识别率也有了显著的提高。     

A non-negative low-rank representation for hyperspectral band selection

Hyperspectral images are widely used in real applications due to their rich spectral information. However, the large volume brings a lot of inconvenience, such as storage and transmission. Hyperspectral band selection is an important technique to cope with this issue by selecting a few spectral bands to replace the original image. This article proposes a novel band selection algorithm that first estimates the redundancy through analysing relationships among spectral bands. After that, spectral bands are ranked according to their relative importance. Subsequently, in order to remove redundant spectral bands and preserve the original information, a maximal linearly independent subset is constructed as the optimal band combination. Contributions of this article are listed as follows: (1) A new strategy for band selection is proposed to preserve the original information mostly; (2) A non-negative low-rank representation algorithm is developed to discover intrinsic relationships among spectral bands; (3) A smart strategy is put forward to adaptively determine the optimal combination of spectral bands. To verify the effectiveness, experiments have been conducted on both hyperspectral unmixing and classification. For unmixing, the proposed algorithm decreases the average root mean square errors (RMSEs) by 0.05, 0.03, and 0.05 for the Urban, Cuprite, and Indian Pines data sets, respectively. With regard to classification, our algorithm achieves the overall accuracies of 77.07% and 89.19% for the Indian Pines and Pavia University data sets, respectively. These results are close to the performance with original images. Thus, comparative experiments not only illustrate the superiority of the proposed algorithm, but also prove the validity of band selection on hyperspectral image processing.     

Moment-based feature extraction from high spatial resolution hyperspectral images

In this article, we propose a method for extracting spatio-spectral features from high spatial resolution hyperspectral (HS) images. The method is based on extracting two-dimensional moments from neighbourhoods of pixels. Three different types of moments are considered: geometric, complex Zernike and Legendre. Moments of a given type are extracted from a few principal components (PC) of HS data, and are stacked on the original HS data to form a joint spatio-spectral feature space. These features are classified using a support vector machine (SVM) classifier. The influence of the moments orders and the size of the neighbourhood window on the quality of the extracted features are analysed. A few experiments are conducted on two widely used HS data sets, Pavia University and Salinas. The results demonstrate high capabilities of the proposed method in comparison with some state-of-the-art spatio-spectral HS classification methods.     

Semi-supervised dimension reduction based on hypergraph embedding for hyperspectral images

Dimension reduction (DR) is an efficient and effective preprocessing step of hyperspectral images (HSIs) classification. Graph embedding is a frequently used model for DR, which preserves some geometric or statistical properties of original data set. The embedding using simple graph only considers the relationship between two data points, while in real-world application, the complex relationship between several data points is more important. To overcome this problem, we present a linear semi-supervised DR method based on hypergraph embedding (SHGE) which is an improvement of semi-supervised graph learning (SEGL). The proposed SHGE method aims to find a projection matrix through building a semi-supervised hypergraph which can preserve the complex relationship of the data and the class discrimination for DR. Experimental results demonstrate that our method achieves better performance than some existing DR methods for HSIs classification and is time saving compared with the existed method SEGL which used simple graph.     

Sparse representation based single image super-resolution with low-rank constraint and nonlocal self-similarity

Single image super-resolution reconstruction (SISR) plays an important role in many computer vision applications. It aims to estimate a high-resolution image from an input low-resolution image. In existing reconstruction methods, the nonlocal self-similarity based sparse representation methods exhibit good performance. However, for this kind of methods, due to the independent coding process of each image patch to be encoded, the global similarity information among all similar image patches in whole image is lost in reconstruction. As a result, similar image patches may be encoded as totally different code coefficients. Considering that the low-rank constraint is better at capturing the global similarity information, we propose a new sparse representation model, which concerns the low-rank constraint and the nonlocal self-similarity in the sparse representation model simultaneously, to preserve such global similarity information. The linearized alternating direction method with adaptive penalty is introduced to effectively solve the proposed model. Extensive experimental results demonstrate that the proposed model achieves convincing improvement over many state-of-the-art SISR models. Moreover, these good results also demonstrate the effectiveness of the proposed model in preserving the global similarity information.     

Fast hyperspectral band selection based on spatial feature extraction

Hyperspectral images usually consist of hundreds of spectral bands, which can be used to precisely characterize different land cover types. However, the high dimensionality also has some disadvantages, such as the Hughes effect and a high storage demand. Band selection is an effective method to address these issues. However, most band selection algorithms are conducted with the high-dimensional band images, which will bring high computation complexity and may deteriorate the selection performance. In this paper, spatial feature extraction is used to reduce the dimensionality of band images and improve the band selection performance. The experiment results obtained on three real hyperspectral datasets confirmed that the spatial feature extraction-based approach exhibits more robust classification accuracy when compared with other methods. Besides, the proposed method can dramatically reduce the dimensionality of each band image, which makes it possible for band selection to be implemented in real time situations.     

Latent representation learning based autoencoder for unsupervised feature selection in hyperspectral imagery

In hyperspectral image (HSI) analysis, high-dimensional data may contain noisy, irrelevant and redundant information. To mitigate the negative effect from these information, feature selection is one of the useful solutions. Unsupervised feature selection is a data preprocessing technique for dimensionality reduction, which selects a subset of informative features without using any label information. Different from the linear models, the autoencoder is formulated to nonlinearly select informative features. The adjacency matrix of HSI can be constructed to extract the underlying relationship between each data point, where the latent representation of original data can be obtained via matrix factorization. Besides, a new feature representation can be also learnt from the autoencoder. For a same data matrix, different feature representations should consistently share the potential information. Motivated by these, in this paper, we propose a latent representation learning based autoencoder feature selection (LRLAFS) model, where the latent representation learning is used to steer feature selection for the autoencoder. To solve the proposed model, we advance an alternative optimization algorithm. Experimental results on three HSI datasets confirm the effectiveness of the proposed model.

     

A collaborative representation based projections method for feature extraction

In graph embedding based methods, we usually need to manually choose the nearest neighbors and then compute the edge weights using the nearest neighbors via L2 norm (e.g. LLE). It is difficult and unstable to manually choose the nearest neighbors in high dimensional space. So how to automatically construct a graph is very important. In this paper, first, we give a L2-graph like L1-graph. L2-graph calculates the edge weights using the total samples, avoiding manually choosing the nearest neighbors; second, a L2-graph based feature extraction method is presented, called collaborative representation based projections (CRP). Like SPP, CRP aims to preserve the collaborative representation based reconstruction relationship of data. CRP utilizes a L2 norm graph to characterize the local compactness information. CRP maximizes the ratio between the total separability information and the local compactness information to seek the optimal projection matrix. CRP is much faster than SPP since CRP calculates the objective function with L2 norm while SPP calculate the objective function with L1 norm. Experimental results on FERET, AR, Yale face databases and the PolyU finger-knuckle-print database demonstrate that CRP works well in feature extraction and leads to a good recognition performance.     

Transfer subspace learning joint low-rank representation and feature selection

Multimedia Tools and Applications - Transfer learning is proposed to solve a general problem in practical applications faced by traditional machine learning methods, that is, the training and test...     

Ridge regression-based feature extraction for hyperspectral data

Feature extraction based on ridge regression (FERR) is proposed in this article. In FERR, a feature vector is defined in each spectral band using the mean of all classes in that dimension. Then, it is modelled using a linear combination of its farthest neighbours from among other defined feature vectors. The representation coefficients obtained by solving the ridge regression model compose the projection matrix for feature extraction. FERR can extract each desired number of features while the other methods such as linear discriminant analysis (LDA) and generalized discriminant analysis (GDA) have limitations in the number of extracted features. Experimental results on four popular real hyperspectral images show that the efficiency of FERR is superior to those of other supervised feature extraction methods in small sample-size situations. For example, for the Indian Pines dataset, the comparison between the highest average classification accuracies achieved by different feature extraction methods using a support vector machine (SVM) classifier and 16 training samples per class shows that FERR is 7% more accurate than nonparametric weighted feature extraction and is also 9% better than GDA. LDA, having the singularity problem in the small sample-size situations, has 40% less accuracy than FERR. The experiments show that generally the performance of FERR using the SVM classifier is better than when using the maximum likelihood classifier.     

A fast algorithm for feature extraction of hyperspectral images using the first order statistics

Multimedia Tools and Applications - A new supervised feature extraction method appropriate for small sample size situations is proposed in this work. The proposed method is based on the first-order...     

Phase correlation based redundancy removal in feature weighting band selection for hyperspectral images

Feature weighting based band selection provides a computationally undemanding approach to reduce the number of hyperspectral bands in order to decrease the computational requirements for processing large hyperspectral data sets. In a recent feature weighting based band selection method, a pair‐wise separability criterion and matrix coefficients analysis are used to assign weights to original bands, after which bands identified to be redundant using cross correlation are removed, as it is noted that feature weighting itself does not consider spectral correlation. In the present work, it is proposed to use phase correlation instead of conventional cross correlation to remove redundant bands in the last step of feature weighting based hyperspectral band selection. Support Vector Machine (SVM) based classification of hyperspectral data with a reduced number of bands is used to evaluate the classification accuracy obtained with the proposed approach, and it is shown that feature weighting band selection with the proposed phase correlation based redundant band removal method provides increased classification accuracy compared to feature weighting band selection with conventional cross correlation based redundant band removal.     

基于成对约束的主动半监督聚类算法

为了解决半监督聚类先验知识少、聚类偏差大的问题,提出了基于成对约束的主动半监督聚类算法.引入主动学习算法,增加约束集的信息量以使聚类效果更好;利用该约束集建立投影矩阵映射数据到低维空间,便于计算并提高聚类效果.算法中提出闭包替代思想,试图简化样本空间,以期获得降低聚类偏差的可能.由于聚类算法的实施对象是低维数据,成对约束集信息量大,聚类的时间效率以及性能均可保证.实验结果表明,采用主动学习的半监督聚类算法聚类效果提升显著,高效合理.     

Relaxed local preserving regression for image feature extraction

The latest linear least regression (LSR) methods improved the performance of image feature extraction effectively by relaxing strict zero-one labels as slack forms. However, these methods have the following three disadvantages: 1) LSR-based methods are sensitive to the noises and may lose effectiveness in feature extraction task; 2) they only focus on the global structures of data, but ignore locality which is important to improve the performance; 3) they suffer from small-class problem, which means the number of projections learned by methods is limited by the number of classes. To address these problems, we propose a novel method called Relaxed Local Preserving Regression (RLPR) for image feature extraction. By incorporating the relaxed label matrix and similarity graph-based regularization term, RLPR can not only explore the latent structure information of data, but also solve the small-class problem. In order to enhance the robustness to noises, we further proposed an extended version of RLPR based on l_{2, 1}-norm, termed as ERLPR. The experimental results on image databases consistently show that the recognition rates of RLPR and ERLPR are superior to the compared methods and can achieve 98% in normal cases. Especially, even on the corrupted databases, the proposed methods can also achieve the classification accuracy of more than 58%.

     

基于低秩评分的非监督特征选择算法

为将数据的全局结构信息引入特征选择中,提升特征评分机制的有效性,提出一种基于低秩评分的非监督特征选择算法。利用“干净”字典约束的低秩表示模型,获得权值矩阵,该权值矩阵能够揭示数据全局结构信息,具有一定的鉴别能力,将其引入拉普拉斯评分机制,构建低秩评分机制,用于数据的特征选择。在不同的数据库上进行聚类和分类实验,实验结果表明,同传统的特征选择算法相比,该算法的性能更优。     

Textile fabric defect detection based on low-rank representation

In this paper, we propose a novel and robust fabric defect detection method based on the low-rank representation (LRR) technique. Due to the repeated texture structure we model a defects-free fabric image as a low-rank structure. In addition, because defects, if exist, change only the texture of fabric locally, we model them with a sparse structure. Based on the above idea, we represent a fabric image into the sum of a low-rank matrix which expresses fabric texture and a sparse matrix which expresses defects. Then, the LRR method is applied to obtain the corresponding decomposition. Especially, in order to make better use of low-rank structure characteristics we propose LRREB (low-rank representation based on eigenvalue decomposition and blocked matrix) method to improve LRR. LRREB is implemented by dividing a image into some corresponding blocked matrices to reduce dimensions and applying eigen-value decomposition (EVD) on blocked matrix instead of singular value decomposition (SVD) on original fabric image, which improves the accuracy and efficiency. No training samples are required in our methods. Experimental results show that the proposed fabric defect detection method is feasible, effective, and simple to be employed.