Super-resolution of hyperspectral image via superpixel-based sparse representation

Progressive Spatial Information-Guided Deep Aggregation Convolutional Network for Hyperspectral Spectral Super-Resolution

Fusion-based spectral super-resolution aims to yield a high-resolution hyperspectral image (HR-HSI) by integrating the available high-resolution multispectral image (HR-MSI) with the corresponding low-resolution hyperspectral image (LR-HSI). With the prosperity of deep convolutional neural networks, plentiful fusion methods have made breakthroughs in reconstruction performance promotions. Nevertheless, due to inadequate and improper utilization of cross-modality information, the most current state-of-the-art (SOTA) fusion-based methods cannot produce very satisfactory recovery quality and only yield desired results with a small upsampling scale, thus affecting the practical applications. In this article, we propose a novel progressive spatial information-guided deep aggregation convolutional neural network (SIGnet) for enhancing the performance of hyperspectral image (HSI) spectral super-resolution (SSR), which is decorated through several dense residual channel affinity learning (DRCA) blocks cooperating with a spatial-guided propagation (SGP) module as the backbone. Specifically, the DRCA block consists of an encoding part and a decoding part connected by a channel affinity propagation (CAP) module and several cross-layer skip connections. In detail, the CAP module is customized by exploiting the channel affinity matrix to model correlations among channels of the feature maps for aggregating the channel-wise interdependencies of the middle layers, thereby further boosting the reconstruction accuracy. Additionally, to efficiently utilize the two cross-modality information, we developed an innovative SGP module equipped with a simulation of the degradation part and a deformable adaptive fusion part, which is capable of refining the coarse HSI feature maps at pixel-level progressively. Extensive experimental results demonstrate the superiority of our proposed SIGnet over several SOTA fusion-based algorithms.

Polycaprolactone/polylactic acid nanofibers incorporated with butyl hydroxyanisole /HP-β-CD assemblies for improving fruit storage quality

In this study, the inclusion complex was prepared with butyl hydroxyanisole (BHA) as the functional substance and 2-hydroxypropyl beta-cyclodextrin (HP-β-CD) as the main molecule by ultrasound mediation. The inclusion complex was mixed with polycaprolactone (PCL)/polylactic acid (PLA), and nanofiber films loaded with different concentrations of BHA/HP-β-CD inclusion complex were prepared by electrospinning for fruit preservation. The scanning electron microscopy and infrared spectroscopy characterization results showed that HP-β-CD successfully embedded BHA in the cavity. The encapsulation of BHA increases the fiber diameter and thermal stability and decreases the crystallinity and hydrophobicity. The oxidation resistance experiment showed that the nanofiber film had a strong free radical scavenging ability. The BHA release rate of the nanofiber membrane was determined by high-performance liquid chromatography, and the release curve results showed that the inclusion complex prepared by ultrasonic self-assembly could significantly prolong the BHA release time. In addition, nanofiber films containing inclusion complex showed an effective fresh-keeping effect within 7 days of mango storage. In conclusion, a series of characterization tests show that the nanofiber film prepared in this study has a good market prospect in food preservation.

Hyperspectral Image Classification Based on Sparse Superpixel Graph

Hyperspectral image (HSI) classification is one of the major problems in the field of remote sensing. Particularly, graph-based HSI classification is a promising topic and has received increasing attention in recent years. However, graphs with pixels as nodes generate large size graphs, thus increasing the computational burden. Moreover, satisfactory classification results are often not obtained without considering spatial information in constructing graph. To address these issues, this study proposes an efficient and effective semi-supervised spectral-spatial HSI classification method based on sparse superpixel graph (SSG). In the constructed sparse superpixels graph, each vertex represents a superpixel instead of a pixel, which greatly reduces the size of graph. Meanwhile, both spectral information and spatial structure are considered by using superpixel, local spatial connection and global spectral connection. To verify the effectiveness of the proposed method, three real hyperspectral images, Indian Pines, Pavia University and Salinas, are chosen to test the performance of our proposal. Experimental results show that the proposed method has good classification completion on the three benchmarks. Compared with several competitive superpixel-based HSI classification approaches, the method has the advantages of high classification accuracy (>97.85%) and rapid implementation (<10 s). This clearly favors the application of the proposed method in practice.

A Non-Local Superpatch-Based Algorithm Exploiting Low Rank Prior for Restoration of Hyperspectral Images

We propose a novel algorithm for the restoration of a degraded hyperspectral image. The proposed algorithm exploits the spatial as well as the spectral redundancy of a degraded hyperspectral image in order to restore it without having any prior knowledge about the type of degradation present. Our work uses superpatches to exploit the spatial and spectral redundancies. We formulate a restoration algorithm incorporating structural similarity index measure as the data fidelity term and nuclear norm as the regularization term. The proposed algorithm is able to cope with additive Gaussian noise, signal dependent Poisson noise, mixed Poisson-Gaussian noise and can restore a hyperspectral image corrupted by dead lines and stripes. As we demonstrate with the aid of extensive experiments, our algorithm is capable of recovering the spectra even in the case of severe degradation. A comparison with the state-of-the-art low rank hyperspectral image restoration methods via experiments with real world and simulated data establishes the competitiveness of the proposed algorithm with the existing methods.

Dimensionality Reduction of Hyperspectral Image Based on Local Constrained Manifold Structure Collaborative Preserving Embedding

Graph learning is an effective dimensionality reduction (DR) manner to analyze the intrinsic properties of high dimensional data, it has been widely used in the fields of DR for hyperspectral image (HSI) data, but they ignore the collaborative relationship between sample pairs. In this paper, a novel supervised spectral DR method called local constrained manifold structure collaborative preserving embedding (LMSCPE) was proposed for HSI classification. At first, a novel local constrained collaborative representation (CR) model is designed based on the CR theory, which can obtain more effective collaborative coefficients to characterize the relationship between samples pairs. Then, an intraclass collaborative graph and an interclass collaborative graph are constructed to enhance the intraclass compactness and the interclass separability, and a local neighborhood graph is constructed to preserve the local neighborhood structure of HSI. Finally, an optimal objective function is designed to obtain a discriminant projection matrix, and the discriminative features of various land cover types can be obtained. LMSCPE can characterize the collaborative relationship between sample pairs and explore the intrinsic geometric structure in HSI. Experiments on three benchmark HSI data sets show that the proposed LMSCPE method is superior to the state-of-the-art DR methods for HSI classification.

Hyperspectral Image Super-Resolution with Self-Supervised Spectral-Spatial Residual Network

Recently, many convolutional networks have been built to fuse a low spatial resolution (LR) hyperspectral image (HSI) and a high spatial resolution (HR) multispectral image (MSI) to obtain HR HSIs. However, most deep learning-based methods are supervised methods, which require sufficient HR HSIs for supervised training. Collecting plenty of HR HSIs is laborious and time-consuming. In this paper, a self-supervised spectral-spatial residual network (SSRN) is proposed to alleviate dependence on a mass of HR HSIs. In SSRN, the fusion of HR MSIs and LR HSIs is considered a pixel-wise spectral mapping problem. Firstly, this paper assumes that the spectral mapping between HR MSIs and HR HSIs can be approximated by the spectral mapping between LR MSIs (derived from HR MSIs) and LR HSIs. Secondly, the spectral mapping between LR MSIs and LR HSIs is explored by SSRN. Finally, a self-supervised fine-tuning strategy is proposed to transfer the learned spectral mapping to generate HR HSIs. SSRN does not require HR HSIs as the supervised information in training. Simulated and real hyperspectral databases are utilized to verify the performance of SSRN.

Spatial-Spectral Structured Sparse Low-Rank Representation for Hyperspectral Image Super-Resolution

Hyperspectral image super-resolution by fusing high-resolution multispectral image (HR-MSI) and low-resolution hyperspectral image (LR-HSI) aims at reconstructing high resolution spatial-spectral information of the scene. Existing methods mostly based on spectral unmixing and sparse representation are often developed from a low-level vision task perspective, they cannot sufficiently make use of the spatial and spectral priors available from higher-level analysis. To this issue, this paper proposes a novel HSI super-resolution method that fully considers the spatial/spectral subspace low-rank relationships between available HR-MSI/LR-HSI and latent HSI. Specifically, it relies on a new subspace clustering method named "structured sparse low-rank representation" (SSLRR), to represent the data samples as linear combinations of the bases in a given dictionary, where the sparse structure is induced by low-rank factorization for the affinity matrix. Then we exploit the proposed SSLRR model to learn the SSLRR along spatial/spectral domain from the MSI/HSI inputs. By using the learned spatial and spectral low-rank structures, we formulate the proposed HSI super-resolution model as a variational optimization problem, which can be readily solved by the ADMM algorithm. Compared with state-of-the-art hyperspectral super-resolution methods, the proposed method shows better performance on three benchmark datasets in terms of both visual and quantitative evaluation.

Hyperspectral Image Super-Resolution via Deep Progressive Zero-Centric Residual Learning

This paper explores the problem of hyperspectral image (HSI) super-resolution that merges a low resolution HSI (LR-HSI) and a high resolution multispectral image (HR-MSI). The cross-modality distribution of the spatial and spectral information makes the problem challenging. Inspired by the classic wavelet decomposition-based image fusion, we propose a novel lightweight deep neural network-based framework, namely progressive zero-centric residual network (PZRes-Net), to address this problem efficiently and effectively. Specifically, PZRes-Net learns a high resolution and zero-centric residual image, which contains high-frequency spatial details of the scene across all spectral bands, from both inputs in a progressive fashion along the spectral dimension. And the resulting residual image is then superimposed onto the up-sampled LR-HSI in a mean-value invariant manner, leading to a coarse HR-HSI, which is further refined by exploring the coherence across all spectral bands simultaneously. To learn the residual image efficiently and effectively, we employ spectral-spatial separable convolution with dense connections. In addition, we propose zero-mean normalization implemented on the feature maps of each layer to realize the zero-mean characteristic of the residual image. Extensive experiments over both real and synthetic benchmark datasets demonstrate that our PZRes-Net outperforms state-of-the-art methods to a significant extent in terms of both 4 quantitative metrics and visual quality, e.g., our PZRes-Net improves the PSNR more than 3dB, while saving 2.3× parameters and consuming 15× less FLOPs. The code is publicly available at https://github.com/zbzhzhy/PZRes-Net.

A New Method on Super Pixel Reducing Stereo Matching Time of Integrated Imaging

Stereo vision and 3D reconstruction technologies are increasingly concerned in many fields. Stereo matching algorithm is the core of stereo vision and also a technical difficulty. A novel method based on super pixels is mentioned in this paper to reduce the calculating amount and the time. Stereo images from University of Tsukuba are used to test our method. The proposed method spends only 1% of the time spent by the conventional method. Through a two-step super-pixel matching optimization, it takes 6.72 s to match a picture, which is 12.96% of the pre-optimization.

Hyperspectral Images Super-Resolution via Learning High-Order Coupled Tensor Ring Representation

Hyperspectral image (HSI) super-resolution is a hot topic in remote sensing and computer vision. Recently, tensor analysis has been proven to be an efficient technology for HSI image processing. However, the existing tensor-based methods of HSI super-resolution are not able to capture the high-order correlations in HSI. In this article, we propose to learn a high-order coupled tensor ring (TR) representation for HSI super-resolution. The proposed method first tensorizes the HSI to be estimated into a high-order tensor in which multiscale spatial structures and the original spectral structure are represented. Then, a coupled TR representation model is proposed to fuse the low-resolution HSI (LR-HSI) and high-resolution multispectral image (HR-MSI). In the proposed model, some latent core tensors in TR of the LR-HSI and the HR-MSI are shared, and we use the relationship between the spectral core tensors to reconstruct the HSI. In addition, the graph-Laplacian regularization is introduced to the spectral core tensors to preserve the spectral information. To enhance the robustness of the proposed model, Frobenius norm regularizations are introduced to the other core tensors. Experimental results on both synthetic and real data sets show that the proposed method achieves the state-of-the-art super-resolution performance.

Entropy-Based Image Fusion with Joint Sparse Representation and Rolling Guidance Filter

Image fusion is a very practical technology that can be applied in many fields, such as medicine, remote sensing and surveillance. An image fusion method using multi-scale decomposition and joint sparse representation is introduced in this paper. First, joint sparse representation is applied to decompose two source images into a common image and two innovation images. Second, two initial weight maps are generated by filtering the two source images separately. Final weight maps are obtained by joint bilateral filtering according to the initial weight maps. Then, the multi-scale decomposition of the innovation images is performed through the rolling guide filter. Finally, the final weight maps are used to generate the fused innovation image. The fused innovation image and the common image are combined to generate the ultimate fused image. The experimental results show that our method’s average metrics are: mutual information (MI)—5.3377, feature mutual information (FMI)—0.5600, normalized weighted edge preservation value (QAB/F)—0.6978 and nonlinear correlation information entropy (NCIE)—0.8226. Our method can achieve better performance compared to the state-of-the-art methods in visual perception and objective quantification.

Improved Classification Method Based on the Diverse Density and Sparse Representation Model for a Hyperspectral Image

To solve the small sample size (SSS) problem in the classification of hyperspectral image, a novel classification method based on diverse density and sparse representation (NCM_DDSR) is proposed. In the proposed method, the dictionary atoms, which learned from the diverse density model, are used to solve the noise interference problems of spectral features, and an improved matching pursuit model is presented to obtain the sparse coefficients. Airborne hyperspectral data collected by the push-broom hyperspectral imager (PHI) and the airborne visible/infrared imaging spectrometer (AVIRIS) are applied to evaluate the performance of the proposed classification method. Results illuminate that the overall accuracies of the proposed model for classification of PHI and AVIRIS images are up to 91.59% and 92.83% respectively. In addition, the kappa coefficients are up to 0.897 and 0.91.

Kernel Entropy Component Analysis-Based Robust Hyperspectral Image Supervised Classification

Recently, the “noisy label" problem has become a hot topic in supervised classification of hyperspectral images (HSI). Nonetheless, how to effectively remove noisy labels from a training set with mislabeled samples is a nontrivial task for a multitude of supervised classification methods in HSI processing. This paper is the first to propose a kernel entropy component analysis (KECA)-based method for noisy label detection that can remove noisy labels of a training set with mislabeled samples and improve performance of supervised classification in HSI, which consists of the following steps. First, the kernel matrix of training samples with noisy labels for each class can be achieved by exploiting a nonlinear mapping function to enlarge the sample separability. Then, the eigenvectors and eigenvalues of the kernel matrix can be obtained by employing symmetric matrix decomposition. Next, the entropy corresponding to each training sample in each class is calculated based on entropy component analysis using the eigenvalues arranged in descending order and the corresponding eigenvectors. Finally, the sigmoid function is applied to the entropy of each sample to obtain the probability distribution. Meanwhile, a decision probability threshold is introduced into the above probability distribution to cleanse the noisy labels of training samples with mislabeled samples for each class. The effectiveness of the proposed method is evaluated by support vector machines on several real hyperspectral data sets. The experimental results show that the proposed KECA method is more efficient than other noisy label detection methods in terms of improving performance of the supervised classification of HSI.

Hyperspectral Image Super-Resolution via Adaptive Dictionary Learning and Double l1 Constraint

Hyperspectral image (HSI) super-resolution (SR) is an important technique for improving the spatial resolution of HSI. Recently, a method based on sparse representation improved the performance of HSI SR significantly. However, the spectral dictionary was learned under a fixed size, empirically, without considering the training data. Moreover, most of the existing methods fail to explore the relationship among the sparse coefficients. To address these crucial issues, an effective method for HSI SR is proposed in this paper. First, a spectral dictionary is learned, which can adaptively estimate a suitable size according to the input HSI without any prior information. Then, the proposed method exploits the nonlocal correlation of the sparse coefficients. Doubleregularized sparse representation is then introduced to achieve better reconstructions for HSI SR. Finally, a high spatial resolution HSI is generated by the obtained coefficients matrix and the learned adaptive size spectral dictionary. To evaluate the performance of the proposed method, we conduct experiments on two famous datasets. The experimental results demonstrate that it can outperform some relatively state-of-the-art methods in terms of the popular universal quality evaluation indexes.

Spatial-Spectral Multiple Manifold Discriminant Analysis for Dimensionality Reduction of Hyperspectral Imagery

Hyperspectral images (HSI) possess abundant spectral bands and rich spatial information, which can be utilized to discriminate different types of land cover. However, the high dimensional characteristics of spatial-spectral information commonly cause the Hughes phenomena. Traditional feature learning methods can reduce the dimensionality of HSI data and preserve the useful intrinsic information but they ignore the multi-manifold structure in hyperspectral image. In this paper, a novel dimensionality reduction (DR) method called spatial-spectral multiple manifold discriminant analysis (SSMMDA) was proposed for HSI classification. At first, several subsets are obtained from HSI data according to the prior label information. Then, a spectral-domain intramanifold graph is constructed for each submanifold to preserve the local neighborhood structure, a spatial-domain intramanifold scatter matrix and a spatial-domain intermanifold scatter matrix are constructed for each sub-manifold to characterize the within-manifold compactness and the between-manifold separability, respectively. Finally, a spatial-spectral combined objective function is designed for each submanifold to obtain an optimal projection and the discriminative features on different submanifolds are fused to improve the classification performance of HSI data. SSMMDA can explore spatial-spectral combined information and reveal the intrinsic multi-manifold structure in HSI. Experiments on three public HSI data sets demonstrate that the proposed SSMMDA method can achieve better classification accuracies in comparison with many state-of-the-art methods.

A Two-Stage Gradient Ascent-Based Superpixel Framework for Adaptive Segmentation

Superpixel segmentation usually over-segments an image into fragments to extract regional features, thus linking up advanced computer vision tasks. In this work, a novel coarse-to-fine gradient ascent framework is proposed for superpixel-based color image adaptive segmentation. In the first stage, a speeded-up Simple Linear Iterative Clustering (sSLIC) method is adopted to generate uniform superpixels efficiently, which assumes that homogeneous regions preserve high consistence during clustering, consequently, much redundant computation for updating can be avoided. Then a simple criterion is introduced to evaluate the uniformity in each superpixel region, once a superpixel region is under-segmented, an adaptive marker-controlled watershed algorithm processes a finer subdivision. Experimental results show that the framework achieves better performance on detail-rich regions than previous superpixel approaches with satisfactory efficiency.

Hyperspectral Image Super-Resolution by Deep Spatial-Spectral Exploitation

Limited by the existing imagery sensors, hyperspectral images are characterized by high spectral resolution but low spatial resolution. The super-resolution (SR) technique aiming at enhancing the spatial resolution of the input image is a hot topic in computer vision. In this paper, we present a hyperspectral image (HSI) SR method based on a deep information distillation network (IDN) and an intra-fusion operation. Specifically, bands are firstly selected by a certain distance and super-resolved by an IDN. The IDN employs distillation blocks to gradually extract abundant and efficient features for reconstructing the selected bands. Second, the unselected bands are obtained via spectral correlation, yielding a coarse high-resolution (HR) HSI. Finally, the spectral-interpolated coarse HR HSI is intra-fused with the input HSI to achieve a finer HR HSI, making further use of the spatial-spectral information these unselected bands convey. Different from most existing fusion-based HSI SR methods, the proposed intra-fusion operation does not require any auxiliary co-registered image as the input, which makes this method more practical. Moreover, contrary to most single-based HSI SR methods whose performance decreases significantly as the image quality gets worse, the proposal deeply utilizes the spatial-spectral information and the mapping knowledge provided by the IDN, which achieves more robust performance. Experimental data and comparative analysis have demonstrated the effectiveness of this method.

Domain Transfer Learning for Hyperspectral Image Super-Resolution

A Hyperspectral Image (HSI) contains a great number of spectral bands for each pixel; however, the spatial resolution of HSI is low. Hyperspectral image super-resolution is effective to enhance the spatial resolution while preserving the high-spectral-resolution by software techniques. Recently, the existing methods have been presented to fuse HSI and Multispectral Images (MSI) by assuming that the MSI of the same scene is required with the observed HSI, which limits the super-resolution reconstruction quality. In this paper, a new framework based on domain transfer learning for HSI super-resolution is proposed to enhance the spatial resolution of HSI by learning the knowledge from the general purpose optical images (natural scene images) and exploiting the cross-correlation between the observed low-resolution HSI and high-resolution MSI. First, the relationship between low- and high-resolution images is learned by a single convolutional super-resolution network and then is transferred to HSI by the idea of transfer learning. Second, the obtained Pre-high-resolution HSI (pre-HSI), the observed low-resolution HSI, and high-resolution MSI are simultaneously considered to estimate the endmember matrix and the abundance code for learning the spectral characteristic. Experimental results on ground-based and remote sensing datasets demonstrate that the proposed method achieves comparable performance and outperforms the existing HSI super-resolution methods.

Non-Destructive Trace Detection of Explosives Using Pushbroom Scanning Hyperspectral Imaging System

The aim of this study was to investigate the potential of the non-destructive hyperspectral imaging system (HSI) and accuracy of the model developed using Support Vector Machine (SVM) for determining trace detection of explosives. Raman spectroscopy has been used in similar studies, but no study has been published which is based on measurement of reflectance from hyperspectral sensor for trace detection of explosives. HSI used in this study has an advantage over existing techniques due to its combination of imaging system and spectroscopy, along with being contactless and non-destructive in nature. Hyperspectral images of the chemical were collected using the BaySpec hyperspectral sensor which operated in the spectral range of 400–1000 nm (144 bands). Image processing was applied on the acquired hyperspectral image to select the region of interest (ROI) and to extract the spectral reflectance of the chemicals which were stored as spectral library. Principal Component Analysis (PCA) and first derivative was applied to reduce the high dimensionality of the image and to determine the optimal wavelengths between 400 and 1000 nm. In total, 22 out of 144 wavelengths were selected by analysing the loadings of principal components (PC). SVM was used to develop the classification model. SVM model established on the whole spectrum from 400 to 1000 nm achieved an accuracy of 81.11%, whereas an accuracy of 77.17% with less computational load was achieved when SVM model was established on the optimal wavelengths selected. The results of the study demonstrate that the hyperspectral imaging system along with SVM is a promising tool for trace detection of explosives.

Design and implementation of novel hyperspectral imaging for dental carious early detection using laser induced fluorescence

Early detection of carious is vital for demineralization reversal, offering less pain, as well as precise carious removal. In this study, the difference in optical properties of normal tissue and human carious lesion has been used for early diagnosis, using laser induced fluorescence spectroscopy. The optical system consists of light source in visible band and hyperspectral camera, associated with designed digital image processing algorithm. The human tooth sample was illuminated with visible band sources at 488, and 514 nm with energy of 5 m watt. The reflected and emitted light from the tested sample was captured using hyperspectral camera in an attempt to generate multispectral images (cubic image). The variation of reflected and emitted energy as function of wavelength was employed to generate characteristic spectrum of each tooth tissue. Human teeth carious tissue lesion releases its excess energy by emitting fluorescence light producing chemical footprint signature; this signature is dependent on the elemental composition of tooth elements and carious state. This non-invasive, non-contact and non-ionizing imaging system with associated novel pattern recognition algorithm was employed to diagnose and classify different carious types and stages. It was reported that the perceived fluorescence emission is function of the illuminating wavelength. While enamel and dentin carious were distinguished and characterized at 514 nm illuminating wavelength; white spot lesion were contoured and recognized at 488 nm. Therefore, full recognition could be achieved through generated cubic image after sample irradiation at 488 nm and 514 nm. In conclusion, this study reports on a customized optical image system that can offer high sensitivity, high resolution, and early carious detection with optimum performance at 514 nm and 488 nm.

Optical coherence tomography retinal image reconstruction via nonlocal weighted sparse representation

We present a nonlocal weighted sparse representation (NWSR) method for reconstruction of retinal optical coherence tomography (OCT) images. To reconstruct a high signal-to-noise ratio and high-resolution OCT images, utilization of efficient denoising and interpolation algorithms are necessary, especially when the original data were subsampled during acquisition. However, the OCT images suffer from the presence of a high level of noise, which makes the estimation of sparse representations a difficult task. Thus, the proposed NWSR method merges sparse representations of multiple similar noisy and denoised patches to better estimate a sparse representation for each patch. First, the sparse representation of each patch is independently computed over an overcomplete dictionary, and then a nonlocal weighted sparse coefficient is computed by averaging representations of similar patches. Since the sparsity can reveal relevant information from noisy patches, combining noisy and denoised patches' representations is beneficial to obtain a more robust estimate of the unknown sparse representation. The denoised patches are obtained by applying an off-the-shelf image denoising method and our method provides an efficient way to exploit information from noisy and denoised patches' representations. The experimental results on denoising and interpolation of spectral domain OCT images demonstrated the effectiveness of the proposed NWSR method over existing state-of-the-art methods.

Automatic classification of retinal three-dimensional optical coherence tomography images using principal component analysis network with composite kernels

We present an automatic method, termed as the principal component analysis network with composite kernel (PCANet-CK), for the classification of three-dimensional (3-D) retinal optical coherence tomography (OCT) images. Specifically, the proposed PCANet-CK method first utilizes the PCANet to automatically learn features from each B-scan of the 3-D retinal OCT images. Then, multiple kernels are separately applied to a set of very important features of the B-scans and these kernels are fused together, which can jointly exploit the correlations among features of the 3-D OCT images. Finally, the fused (composite) kernel is incorporated into an extreme learning machine for the OCT image classification. We tested our proposed algorithm on two real 3-D spectral domain OCT (SD-OCT) datasets (of normal subjects and subjects with the macular edema and age-related macular degeneration), which demonstrated its effectiveness.