Modified Tensor Locality Preserving Projection for Dimensionality Reduction of Hyperspectral Images

Deng, Yang‐Jun; Li, Heng-Chao; Pan, Lei; Shao, Liyang; Du, Qian; Emery, William J.

doi:10.1109/lgrs.2017.2786223

Cited by 63 publications

(31 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LPP is a widely used manifold learning method for HSI dimensionality reduction [16][17][18][19]26], while the region covariance descriptor is an effective spectral-spatial feature for HSI classification [26][27][28]. In the following, they are briefly introduced as backgrounds of our proposed method.…”

Section: Related Work and Backgroundmentioning

confidence: 99%

“…Region covariance descriptor has been applied in the computer vision and brain computer interface problem [30][31][32]. Deng et al introduced the descriptor to HSI processing [26][27][28]. Suppose that X ∈ R W×H×D represents the original HSI cube, X i ∈ R w×h×D denotes the spatial region around the ith pixel, and s = w × h is size of a spatially local window, then the region covariance descriptor is as follows:…”

Section: Region Covariance Descriptormentioning

confidence: 99%

“…Performing a region covariance descriptor can yield an excellent spectral-spatial covariance feature for HSI classification [26][27][28], which has the advantage of robustness to noise and spectral variabilities over traditional spectral feature (the original spectral signature) [33][34][35].…”

Section: Region Covariance Descriptormentioning

confidence: 99%

“…Our method utilizes the region covariance descriptor to construct the graph for an LPP. The descriptor can yield spectral-spatial covariance features more robust to noise and spectral variabilities than the spectral feature [26][27][28]. More specifically, we characterize pixels with their region covariance descriptors, calculate the pairwise distances among pixels in a superpixel with Log-Euclidean distance metric, find the nearest neighbors of the pixels in a superpixel, and compute their similarities as…”

Section: Divide-and-conquer-based Lpp Classificationmentioning

confidence: 99%

See 3 more Smart Citations

Multiscale Superpixelwise Locality Preserving Projection for Hyperspectral Image Classification

Chen

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

Manifold learning is a powerful dimensionality reduction tool for a hyperspectral image (HSI) classification to relieve the curse of dimensionality and to reveal the intrinsic low-dimensional manifold. However, a specific characteristic of HSIs, i.e., irregular spatial dependency, is not taken into consideration in the method design, which can yield many spatially homogenous subregions in an HSI scence. Conventional manifold learning methods, such as a locality preserving projection (LPP), pursue a unified projection on the entire HSI, while neglecting the local homogeneities on the HSI manifold caused by those spatially homogenous subregions. In this work, we propose a novel multiscale superpixelwise LPP (MSuperLPP) for HSI classification to overcome the challenge. First, we partition an HSI into homogeneous subregions with a multiscale superpixel segmentation. Then, on each scale, subregion specific LPPs and the associated preliminary classifications are performed. Finally, we aggregate the classification results from all scales using a decision fusion strategy to achieve the final result. Experimental results on three real hyperspectral data sets validate the effectiveness of our method.

show abstract

Section: Related Work and Backgroundmentioning

confidence: 99%

Section: Region Covariance Descriptormentioning

confidence: 99%

Section: Region Covariance Descriptormentioning

confidence: 99%

Section: Divide-and-conquer-based Lpp Classificationmentioning

confidence: 99%

See 2 more Smart Citations

Multiscale Superpixelwise Locality Preserving Projection for Hyperspectral Image Classification

Chen

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Neighborhood preserving embedding (NPE) [27], locality preserving projection (LPP) [28] and linear local tangent space alignment (LLTSA) [29] are proposed for hyperspectral FE [30,31]. The work in [32] develops a tensor version of the LPP algorithm for hyperspectral DR and classification. The work in [33] proposes a common minimization framework called graph-embedding (GE), which is based on estimating an undirected weighted graph to describe the desired intrinsic (statistical or geometrical) properties of the data.…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Feature Extraction Using Sparse and Smooth Low-Rank Analysis

2019

View full text Add to dashboard Cite

In this paper, we develop a hyperspectral feature extraction method called sparse and smooth low-rank analysis (SSLRA). First, we propose a new low-rank model for hyperspectral images (HSIs) where we decompose the HSI into smooth and sparse components. Then, these components are simultaneously estimated using a nonconvex constrained penalized cost function (CPCF). The proposed CPCF exploits total variation penalty, ℓ 1 penalty, and an orthogonality constraint. The total variation penalty is used to promote piecewise smoothness, and, therefore, it extracts spatial (local neighborhood) information. The ℓ 1 penalty encourages sparse and spatial structures. Additionally, we show that this new type of decomposition improves the classification of the HSIs. In the experiments, SSLRA was applied on the Houston (urban) and the Trento (rural) datasets. The extracted features were used as an input into a classifier (either support vector machines (SVM) or random forest (RF)) to produce the final classification map. The results confirm improvement in classification accuracy compared to the state-of-the-art feature extraction approaches.

show abstract

Supervised classification by thresholds: Application to automated text categorization and opinion mining

Cherif¹,

Madani

Kissi³

2021

Concurrency and Computation

View full text Add to dashboard Cite

Over recent years, the world has experienced explosive growth in the volume of textual data, which makes a manual analysis impossible. Machine learning techniques provided an effective solution to this problem. Due to its capacity to organize the huge and varied amounts of data, it offered valuable insights and it has become an emerging investigative field for the research community. Classification techniques are used to classify data into different classes according to desired criteria. By their simplicity, they give rise to a variety of applications: automated text categorization, opinion mining, and so forth. These processes go through three stages: text representation, features extraction, and the classification process; they still face many difficulties due both to the complex nature of text databases and to the high dimensionality of texts representations. This article presents a new classification approach that learns to classify texts from the most reliable features more accurately. The added advantage of the proposed approach is that it automatically classifies a text without necessarily processing all its features. The experimental results showed that this new classification by thresholds outperforms the state‐of‐the‐art methods. As a result, the obtained f‐measure on automatic text categorization was 95.06% while it is lower on opinion mining.

show abstract

Modified Tensor Locality Preserving Projection for Dimensionality Reduction of Hyperspectral Images

Cited by 63 publications

References 14 publications

Multiscale Superpixelwise Locality Preserving Projection for Hyperspectral Image Classification

Multiscale Superpixelwise Locality Preserving Projection for Hyperspectral Image Classification

Hyperspectral Feature Extraction Using Sparse and Smooth Low-Rank Analysis

Supervised classification by thresholds: Application to automated text categorization and opinion mining

Contact Info

Product

Resources

About