The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper, we propose a blind motion deblurring method based on sparse representation and structural self-similarity from a single image. The priors for sparse representation and structural self-similarity are explicitly added into the recovery of the latent image by means of sparse and multi-scale nonlocal regularizations, and the down-sampled version of the observed blurry image is used as training...
Color images taken in low light scenes are deteriorated with noise and motion blur. The simultaneous reduction of noise and motion blur from the low-light color images is difficult because the imposed noise hinders accurate motion blur kernel estimation. To overcome this problem, we build a novel imaging system using a single sensor that captures red, green, blue (RGB) and near-infrared (NIR) images...
Conventional unsupervised image segmentation methods use color and geometric information and apply clustering algorithms over pixels. They preserve object boundaries well but often suffer from over-segmentation due to noise and artifacts in the images. In this paper, we contribute on a preprocessing step for image smoothing, which alleviates the burden of conventional unsupervised image segmentation...
Recently, total variation based image deconvolution has shown its superior performance. The restoration quality is generally sensitive to the value of regularization parameter. In this work, we develop a data-driven optimization scheme based on minimization of Stein's unbiased risk estimate (SURE)—statistically equivalent to mean squared error (MSE). Based on a typical alternating direction method...
In the modern age, the transmission of digital images is one of the major processes of communication system. Meanwhile, images are often corrupted by the noise. In many image processing applications the reconstruction of high quality image is an essential fact. To achieve this, we proposed a wavelet based hybrid image denoising. In which, after wavelet decomposition of a noisy image both the approximation...
Memory Forensics becomes indispensable in Cyber Forensics Investigation as Random Access Memory or Physical Memory of a Computer holds crucial evidence which is nowhere available on Hard Disks or in other non-volatile storage media. This is because, nowadays most of the malwares are memory resident which leaves no footprints in Hard Disk storage. In this paper, a novel methodology is described for...
This paper presents a fast deblurring algorithm to remove camera motion blur from a single photograph using built-in gyroscopes and strong edge prediction. An inaccurate blur kernel or point spread function (PSF) usually leads to an unsatisfying restored result. Hence, we propose a robust three-phase method for accurate PSF estimation. In the first stage, we utilize the embedded gyroscopes to compute...
Recent advancements in deep Convolutional Neural Networks (CNNs) have led to impressive progress in computer vision, especially in image classification. CNNs involve numerous hyperparameters that identify the network's structure such as depth of the network, kernel size, number of feature maps, stride, pooling size and pooling regions etc. These hyperparameters have a significant impact on the classification...
This paper concerns the square lattice to hexagonal lattice conversion in practical hexagonal image processing, and presents a simplified conversion method that converts the common two-dimensional (2-D) interpolation approach to one-dimensional (1-D) interpolation. This paper is motivated by the sampling interval relationship between the square lattice and the hexagonal lattice, and assumes the 2-D...
Multi-frame super resolution has been well studied in recent years, but blur kernel is always assumed to be known in video super resolution problem. Most blind deconvolution algorithm can both estimate the blur kernel and the sharp image. In this paper, we originally adopt a fast single image blind deconvolution algorithm in video super resolution to estimate high-resolution image and blur kernel...
Image blurring attenuate crucial textures and thus always result in a pretty dismal visual experience. Unfortunately, image blurring is difficult to avoid during the image acquisition, hence, lots of recent research focus on how to preserve subtle textures while suppress visual artifacts during image deblurring. Among all of the existing image deblurring methods, image priors, such as non-local priors...
For investigations of rapidly moving structures in opaque technical devices ultrafast electron beam X-ray computed tomography (CT) scanners are available at the Helmholtz-Zentrum Dresden-Rossendorf (HZDR). Currently, measurement data must be initially downloaded after each CT scan from the scanner to a data processing machine. Afterwards, cross-sectional images are reconstructed. This limits the application...
In human-machine interaction, the captured faces are usually low-resolution (LR), which will degrade the performance of the following face detection and face recognition. Face hallucination is the technology of obtaining a high-resolution (HR) face from its observed LR one. In order to recover more facial details, we propose a novel method called kernel locality-constraint adaptive iterative neighbor...
In this study, we investigated the utilization of multi-contrast MRI as well as PET information to guide PET image reconstruction with the aim of addressing the pitfalls of conventional MR-guided PET image reconstruction methods. We studied the conventional Tikhonov and total variation (TV) priors, and the anatomical priors such as Kaipio, non-local Tikhonov with Gaussian and Bowsher similarity kernels...
In a number of applications, positron emission tomography (PET) requires two or more scans to observe and even quantify changes in function (e.g. tissue metabolism, or receptor binding potentials). Conventionally the raw datasets are reconstructed into images independently, allowing no sharing of information. Kernelised EM (KEM) is a recently proposed PET reconstruction method that utilises one or...
Occluded images often affected the recognition rates in face recognition, thus the occlusion should be checked out and given a little weighting coefficient so as to weaken its impact on the recognition rate as much as possible. The traditional algorithms often use the reconstruction error operator based on principal component analysis (PCA) to estimate the weight for occluded face, which often need...
The kernel trick becomes a burden for some machine learning tasks such as dictionary learning, where a huge amount of training samples are needed, making the kernel matrix gigantic and infeasible to store or process. In this work, we propose to alleviate this problem and achieve Gaussian RBF kernel expansion explicitly for dictionary learning using Fastfood transform, which is an approximation of...
Most of current clustering methods are designed for general purpose other than a specific color pixel classification use. Color Line model representation emerged as the ultimate method for clustering pixels using RGB color components. However, this method is strongly sensitive to the adjustment of input parameters, which cannot conform to the frequent change of image structures and compositions. In...
A spectral-spatial hyperspectral image classification is proposed in this paper. The proposed method has two main contributions. 1- It removes the useless spatial information such as noise and distortions by applying the proposed smoothing filter. 2- It adds useful spatial information such as shape and size of objects presented in scene image by applying morphological filters. Moreover, the proposed...
In this work we explore the previously proposed approach of direct blind deconvolution and denoising with convolutional neural networks (CNN) in a situation where the blur kernels are partially constrained. We focus on blurred images from a real-life traffic surveillance system, on which we, for the first time, demonstrate that neural networks trained on artificial data provide superior reconstruction...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.