Hyperspectral imagery contains a large number of mixed pixels, which limits its utility. Super-resolution mapping is a potential solution to this problem, designed to use the proportion of land covers to obtain a sharpened thematic map with higher resolution. Endmember is a fundamental variable in the process, which is a critical issue for decomposing the mixed pixels and sharpening the subpixel level images. In most cases, the forms of the endmember combination in diverse pixels are very distinct. However, traditional soft classification methods neglect this point and model endmembers as fixed composition entities. Due to the reliance on this flawed spectral mixture model, the super-resolution mapping is unable to represent detail in the following result image precisely and effectively. In this work, therefore, endmember variability is considered, focusing on identifying the most suitable form of the endmember combination. This issue is addressed by applying a new selective endmember spectral mixture (SESM) model, which allows the endmember number and type to vary at a per pixel level, and then super-resolution mapping can be subsequently performed according to the produced spectral abundances. Two different types of hyperspectral data are used in our experiments. First, the SESM model is tested individually for validation of its applicability. Then the complete algorithm integrating SESM and super-resolution mapping based on a back-propagation neural network is evaluated. It showed that a more accurate endmember combination in the parent pixel results in a finer representation image. The experimental results prove that the proposed algorithm can effectively improve the accuracy of the super-resolution mapping results compared to the traditional method.
A novel region-based adaptive anisotropic diffusion (RAAD) is presented for image enhancement and denoising. The main idea of this algorithm is to perform the region-based adaptive segmentation. To this end, we use the eigenvalue difference of the structure tensor of each pixel to classify an image into homogeneous detail, and edge regions. According to the different types of regions, a variable weight is incorporated into the anisotropic diffusion partial differential equation for compromising the forward and backward diffusion, so that our algorithm can adaptively encourage strong smoothing in homogeneous regions and suitable sharpening in detail and edge regions. Furthermore, we present an adaptive gradient threshold selection strategy. We suggest that the optimal gradient threshold should be estimated as the mean of local intensity differences on the homogeneous regions. In addition, we modify the anisotropic diffusion discrete scheme by taking into account edge orientations. We believe our algorithm to be a novel mechanism for image enhancement and denoising. Qualitative experiments, based on various general digital images and several T1- and T2-weighted magnetic resonance simulated images, show significant improvements when the RAAD algorithm is used versus the existing anisotropic diffusion and the previous forward and backward diffusion algorithms for enhancing edge features and improving image contrast. Quantitative analyses, based on peak signal-to-noise ratio, the universal image quality index, and the structural similarity confirm the superiority of the proposed algorithm.
In order to improve signal-to-noise ratio (SNR) and contrast-to-noise ratio, we introduces a novel tunable forward-and-backward (TFAB) diffusion approach for image restoration and edge enhancement. In the TFAB algorithm, an alternative forward-and-backward (FAB) diffusion process is presented, where it is possible to better modulate all aspects of the diffusion behavior and it shows better algorithm behavior compared to the existing FAB diffusion approaches. In addition, there is no necessity to laboriously determine the value of the gradient threshold. We believe the TFAB diffusion to be an adaptive mechanism for image restoration and enhancement. Qualitative experiments, based on various general digital images and a magnetic resonance image, show significant improvements when the TFAB diffusion algorithm is used versus the existing anisotropic diffusion and the previous FAB diffusion algorithms for enhancing edge features and improving image contrast. Quantitative analyses, based on peak SNR and the universal image quality index, confirm the superiority of the proposed algorithm.
In order to improve signal-to-noise ratio (SNR) and image quality, this paper introduces a wavelet-based multiscale
anisotropic diffusion algorithm to remove speckle noise and enhance edges. In our algorithm, we use the tool of wavelet
to construct a linear scale-space for the speckle image. Due to the smoothing functionality of the scaling function, the
wavelet-based multiscale representation of the speckle image is much more stationary than the raw speckle image. Noise
is mostly located in the finest scale and tends to decrease as the scale increases. Furthermore, a robust speckle reduction
anisotropic diffusion (SRAD) is to be proposed and we perform the improved SRAD on the stationary scale-space rather
than on the rough speckle image domain. Qualitative experiments based on a speckle Synthetic aperture radar (SAR)
image show the elegant characteristics of edge-preserving filtering versus the traditional adaptive filters. Quantitative
analyses, based on the first order statistics and Equivalent Number of Looks, confirm the validity and effectiveness of the
This paper presents a universal maximum a posteriori (MAP) based reconstruction method which can be used for
destriping, inpainting (the removal of dead pixels) and super resolution reconstruction (the recovery of a high resolution
image from several low resolution images). In the MAP framework, the likelihood probability density function (PDF) is
constructed based on a linear image observation model, and a robust Huber-Markov model is used as the prior PDF. A
gradient descent optimization method is employed to produce the desired image. The proposed algorithm has been tested
using MODIS images for destriping and super resolution reconstruction, and CBERS (China-Brazil Earth Resource
Satellite) and QuickBird images for simulated inpainting. The experiment results and quantitative analyses verify the
efficacy of this algorithm.
Among all enhancement techniques being developed over the past two decades, anisotropic diffusion has received a lot
of attention and has experienced significant developments, with promising results and applications in several specific
domains. The elegant property of the technique is that it can enhance images by reducing undesirable intensity variability
within the objects in image, while improving signal-to-noise ratio (SNR) and enhancing the contrast of the edges in
scalar and, more recently, in vector-valued images, such as color, multispectral and hyperspectral imagery. In this paper,
we firstly analyze two complementary schemes-variational methods and nonlinear diffusion partial differential
equations (PDEs), in terms of edge enhancement. Based on these analyses, a general flexible class of hyperspectral
forward-and-backward (FAB) diffusion process will be proposed, which can achieve the main requirements for edgepreserving
regularization with image enhancement. In addition, we use additive operator splitting (AOS) scheme to
speedup the numerical evolution of the nonlinear diffusion equation with respect to traditional explicit schemes. The
performance of the vector-valued FAB diffusion PDE is studied using some hyperspectral remote sensing images.
Experimental results on these images are shown the validity and effectiveness of the proposed method.
Recently, many researchers have shown interests in anisotropic diffusion methods in image processing. There are two key problems on image restoration techniques based on anisotropic diffusion: one is to build stable diffusion coefficients; the other is to select the optimal stopping time for iterative diffusion process. In this paper, a time-dependent robust anisotropic diffusion method is proposed. The new method is a robust anisotropic diffusion with incorporated time dependent cooling process, and the gradient threshold is the monotonic decreasing function of the time. Thus, the parameters settings and the estimate of the optimal stopping time can be easily resolved. Meanwhile, the proposed method can lessen the over-smooth in image edge features. In order to extent the applicability of the proposed method, we extent the model to the vector-valued form and present time-dependent multispectral robust anisotropic diffusion. Experimental results, performed on several gray images, color images and multispectral remote sensed images, have shown that the time-dependent robust anisotropic diffusion methods can effectively smooth out noise while preserving edge features.